tag:blogger.com,1999:blog-78537929807266400182024-03-15T00:59:27.066-07:00Raspberry Pi ProjectsAndroid Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.comBlogger60125tag:blogger.com,1999:blog-7853792980726640018.post-21591566195124864702024-01-25T05:27:00.000-08:002024-02-14T07:06:59.451-08:00Raspberry pi5 TensorFlow-lite Object Detection<iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/cYvlx9KGClw?si=gToLEy7QLOlsaTCR" title="YouTube video player" width="560"></iframe>
<h1 style="text-align: left;"><span style="color: #2b00fe;">Raspberry pi5 TensorFlow-lite Object Detection</span></h1><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhEH-ErtzkitDdiofxSxgnIM6I_ed9ilajuhrvyxO3r0-V0RP7qxR7GH6zIUqcZDlBU2wytCrY0pvinyzsjGTdTjUAe5DUOxEQBAy2ZjwDl0Iuz0tnkY-4Jco_OW-sGKzKUndOazo_FVudQPSl-upX5LJ-TkhComYKsilyrBlYG8-fP2uw-fYSbIEQPakkS/s2000/Rpi5.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1518" data-original-width="2000" height="243" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhEH-ErtzkitDdiofxSxgnIM6I_ed9ilajuhrvyxO3r0-V0RP7qxR7GH6zIUqcZDlBU2wytCrY0pvinyzsjGTdTjUAe5DUOxEQBAy2ZjwDl0Iuz0tnkY-4Jco_OW-sGKzKUndOazo_FVudQPSl-upX5LJ-TkhComYKsilyrBlYG8-fP2uw-fYSbIEQPakkS/s320/Rpi5.jpg" width="320" /></a></div><h2 style="text-align: left;"><span style="color: #ff00fe;">Hardware : Raspberry pi5</span></h2><div><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">Specification</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><ul style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px; line-height: 1.4; margin: 0.5em 0px; padding: 0px 2.5em;"><li style="margin: 0px 0px 0.25em; padding: 0px;">Broadcom BCM2712 2.4GHz quad-core 64-bit Arm Cortex-A76 CPU, with cryptography extensions, 512KB per-core L2 caches and a 2MB shared L3 cache</li><li style="margin: 0px 0px 0.25em; padding: 0px;">VideoCore VII GPU, supporting OpenGL ES 3.1, Vulkan 1.2</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Dual 4Kp60 HDMI® display output with HDR support</li><li style="margin: 0px 0px 0.25em; padding: 0px;">4Kp60 HEVC decoder</li><li style="margin: 0px 0px 0.25em; padding: 0px;">LPDDR4X-4267 SDRAM (4GB and 8GB SKUs available at launch)</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Dual-band 802.11ac Wi-Fi®</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Bluetooth 5.0 / Bluetooth Low Energy (BLE)</li><li style="margin: 0px 0px 0.25em; padding: 0px;">microSD card slot, with support for high-speed SDR104 mode</li><li style="margin: 0px 0px 0.25em; padding: 0px;">2 × USB 3.0 ports, supporting simultaneous 5Gbps operation</li><li style="margin: 0px 0px 0.25em; padding: 0px;">2 × USB 2.0 ports</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Gigabit Ethernet, with PoE+ support (requires separate PoE+ HAT)</li><li style="margin: 0px 0px 0.25em; padding: 0px;">2 × 4-lane MIPI camera/display transceivers</li><li style="margin: 0px 0px 0.25em; padding: 0px;">PCIe 2.0 x1 interface for fast peripherals (requires separate M.2 HAT or other adapter)</li><li style="margin: 0px 0px 0.25em; padding: 0px;">5V/5A DC power via USB-C, with Power Delivery support</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Raspberry Pi standard 40-pin header</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Real-time clock (RTC), powered from external battery</li><li style="margin: 0px 0px 0.25em; padding: 0px;">Power button</li></ul><div><span face="Trebuchet MS, Trebuchet, Verdana, sans-serif" style="color: #666666;"><span style="font-size: 13.2px;"><br /></span></span></div></div><div><span face="Trebuchet MS, Trebuchet, Verdana, sans-serif" style="color: #666666;"><span style="font-size: 13.2px;"><br /></span></span></div><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiRI5p_4meruYgmCiqq1Uq4MvvzkXvZn-R3Cek7SX0k0Xg_JRuiKi_WiGZg620CB1xqsGFOce0L9f0EKJnf3B7udt8fPTViJo7emHa4FdMTPkW6f5cHddJf0VjN0Vs9PHdQtl7uWV8UehbbxBGzSDAb7-c1xzr1YQjbJeHo1Ut8mWuzA2fL2uoZ6NHJtj9T/s716/Screen%20Shot%202567-01-17%20at%2011.00.44.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="127" data-original-width="716" height="57" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiRI5p_4meruYgmCiqq1Uq4MvvzkXvZn-R3Cek7SX0k0Xg_JRuiKi_WiGZg620CB1xqsGFOce0L9f0EKJnf3B7udt8fPTViJo7emHa4FdMTPkW6f5cHddJf0VjN0Vs9PHdQtl7uWV8UehbbxBGzSDAb7-c1xzr1YQjbJeHo1Ut8mWuzA2fL2uoZ6NHJtj9T/s320/Screen%20Shot%202567-01-17%20at%2011.00.44.png" width="320" /></a></div><h2 style="text-align: left;">Software </h2><p>Raspberry pi OS : 64 bit </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjS9H3sT3syBosDp-Lh2vo9TR6KxZQPIr6S0qsOiYz1UMIdJuYgoFoDMJoH-DvcI-6bVObGEeUoZniLdTM7CcKoDxlFNusLMZjqDV6WZalTf9Y0xnwFO2kJHYci10r3FkcRRZHIp2EAZuLxLJ1P_iYiwFJSWvHfqc8CNleuHWCzunv7-4x5uw-qpbtZSOF2/s923/raspberrpi5-object-detection-OS.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="464" data-original-width="923" height="322" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjS9H3sT3syBosDp-Lh2vo9TR6KxZQPIr6S0qsOiYz1UMIdJuYgoFoDMJoH-DvcI-6bVObGEeUoZniLdTM7CcKoDxlFNusLMZjqDV6WZalTf9Y0xnwFO2kJHYci10r3FkcRRZHIp2EAZuLxLJ1P_iYiwFJSWvHfqc8CNleuHWCzunv7-4x5uw-qpbtZSOF2/w640-h322/raspberrpi5-object-detection-OS.png" width="640" /></a></div><h3 style="text-align: left;"><span style="background-color: white; color: #1f1f1f; font-family: "Google Sans", "Helvetica Neue", sans-serif; white-space-collapse: preserve;"><b><span style="font-size: medium;">tflite-support </span></b></span></h3><p><span style="background-color: white; color: #1f1f1f; font-family: "Google Sans", "Helvetica Neue", sans-serif; font-size: 16px; white-space-collapse: preserve;"></span></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhzBezb8zx5fhFDMscuiLUS8zr6qte_cZ82QQzRulz38MIBYX95W3i8KtSc1IFTM87V_ymvAb9OETk3vYeA_5NQCV4gWIy6eISN7mNnpWXTZRnJl33BmX1GzP70ce0vjT6ePZpxb1VErBgxNi2uln60KuzPXacdo1EF-7xdPLtNRl789PiyA9p3jTI9BwQ4" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="979" data-original-width="1203" height="520" src="https://blogger.googleusercontent.com/img/a/AVvXsEhzBezb8zx5fhFDMscuiLUS8zr6qte_cZ82QQzRulz38MIBYX95W3i8KtSc1IFTM87V_ymvAb9OETk3vYeA_5NQCV4gWIy6eISN7mNnpWXTZRnJl33BmX1GzP70ce0vjT6ePZpxb1VErBgxNi2uln60KuzPXacdo1EF-7xdPLtNRl789PiyA9p3jTI9BwQ4=w640-h520" width="640" /></a></div><br /><p></p><p><span style="background-color: white; color: #1f1f1f; font-family: "Google Sans", "Helvetica Neue", sans-serif; font-size: 16px; white-space-collapse: preserve;">The new Raspberry Pi OS uses Python 3.11 by default, but TensorFlow Lite currently only supports Python 3.9 on ARM aarch64 architecture. To resolve this, you can create a separate virtual environment with Python 3.8 or 3.9 using</span><span style="background-color: white; color: #1f1f1f; font-family: "Google Sans", "Helvetica Neue", sans-serif; font-size: 16px; font-weight: 700; white-space-collapse: preserve;"> </span></p><p><span style="background-color: white; color: #1f1f1f; font-family: "Google Sans", "Helvetica Neue", sans-serif; font-size: 16px; font-weight: 700; white-space-collapse: preserve;"><code style="background-color: var(--bard-color-surface-container-high); border-radius: 6px; color: var(--bard-color-on-surface-variant); font-family: "Google Sans Mono", monospace; font-size: 0.875rem; font-weight: 400; line-height: 1.25rem; padding: 1px 6px;">conda create -n name python=3.8</code> or <code style="background-color: var(--bard-color-surface-container-high); border-radius: 6px; color: var(--bard-color-on-surface-variant); font-family: "Google Sans Mono", monospace; font-size: 0.875rem; font-weight: 400; line-height: 1.25rem; padding: 1px 6px;">conda create -n name python=3.9</code></span></p><p><b><br /></b></p><p><b>Conda Python 3.8</b></p><p dir="ltr" style="line-height: 1.38; margin-bottom: 0pt; margin-top: 0pt;"><span face="Arial,sans-serif" style="background-color: transparent; color: black; font-size: 11pt; font-style: normal; font-variant: normal; font-weight: 400; text-decoration: none; vertical-align: baseline; white-space: pre;">Install mini conda</span></p><p dir="ltr" style="line-height: 1.38; margin-bottom: 0pt; margin-top: 0pt;"><a href="https://docs.conda.io/projects/miniconda/en/latest/miniconda-other-installer-links.html" style="text-decoration: none;"><span face="Arial,sans-serif" style="-webkit-text-decoration-skip: none; background-color: transparent; color: #1155cc; font-size: 11pt; font-style: normal; font-variant: normal; font-weight: 400; text-decoration-skip-ink: none; text-decoration: underline; vertical-align: baseline; white-space: pre;">https://docs.conda.io/projects/miniconda/en/latest/miniconda-other-installer-links.html</span></a></p><p dir="ltr" style="line-height: 1.38; margin-bottom: 0pt; margin-top: 0pt;"><br /></p><pre class="notranslate" style="background-color: #f6f8fa; border-radius: 6px; box-sizing: border-box; color: #1f2328; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px;"><span style="font-family: "Courier New", monospace; font-size: medium; text-wrap: wrap;">conda create -n tflite python=3.8.18</span></pre><pre class="notranslate" style="background-color: #f6f8fa; border-radius: 6px; box-sizing: border-box; color: #1f2328; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px;"><span style="font-family: "Courier New", monospace; font-size: medium; text-wrap: wrap;">conda activate tflite</span></pre><p dir="ltr" style="line-height: 1.74; margin-bottom: 0pt; margin-top: 0pt;"><span style="background-color: #f6f8fa; color: #1f2328; font-family: 'Courier New',monospace; font-size: 10pt; font-style: normal; font-variant: normal; font-weight: 400; text-decoration: none; vertical-align: baseline; white-space: pre;"><br /></span></p><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4dK3xgAnmljIn3sf4NoIuGZ6CFoSheyjWFDPGvp2tmsuUf3Z4FUO6VVyDQzrh8srIipHMeNNab3kNQ1KhBnfhWzamv5NxbMjiCR0AjbezQ5MIdtYlOkp08grpH-zkZiTSUitrMd1Vc8t731WF3Gu5cH1C7SONMRR_0Vfg4zSsT9gWu4rDMYQ5IlC3zvzF/s700/TensorFlow-Lite.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="525" data-original-width="700" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4dK3xgAnmljIn3sf4NoIuGZ6CFoSheyjWFDPGvp2tmsuUf3Z4FUO6VVyDQzrh8srIipHMeNNab3kNQ1KhBnfhWzamv5NxbMjiCR0AjbezQ5MIdtYlOkp08grpH-zkZiTSUitrMd1Vc8t731WF3Gu5cH1C7SONMRR_0Vfg4zSsT9gWu4rDMYQ5IlC3zvzF/s320/TensorFlow-Lite.jpg" width="320" /></a></div><h2 style="text-align: left;"><span style="color: #2b00fe;">TensorFlow-lite Example</span></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhi6pE5X7IxbnX2TmXTPQP6l4tJILeGqS0jFPA5_4PT7Ugs5799-iIfyOAQEz_hpWeIz8F74ptxu6vNjL9bZpfDzjf8o_lCi_ARo3_dE71V4ncu4n5QAAaLmXA8rA1SNs01tBPkqEp5NQXdP6od6MHekW3jUnWZNWZvV0nRyQSMuVwrAar-jpYzO978TNsO/s629/Raspberrypi5-tensorflow-lite-object-detection.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="438" data-original-width="629" height="279" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhi6pE5X7IxbnX2TmXTPQP6l4tJILeGqS0jFPA5_4PT7Ugs5799-iIfyOAQEz_hpWeIz8F74ptxu6vNjL9bZpfDzjf8o_lCi_ARo3_dE71V4ncu4n5QAAaLmXA8rA1SNs01tBPkqEp5NQXdP6od6MHekW3jUnWZNWZvV0nRyQSMuVwrAar-jpYzO978TNsO/w400-h279/Raspberrypi5-tensorflow-lite-object-detection.png" width="400" /></a></div><div><br /></div><h3 style="text-align: left;"><b>Install Code</b></h3><div><pre class="notranslate" style="background-color: #f6f8fa; border-radius: 6px; box-sizing: border-box; color: #1f2328; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: transparent; border-radius: 6px; border: 0px; box-sizing: border-box; display: inline; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">git clone https://github.com/tensorflow/examples --depth 1</code></pre><pre class="notranslate" style="background-color: #f6f8fa; border-radius: 6px; box-sizing: border-box; color: #1f2328; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: transparent; border-radius: 6px; border: 0px; box-sizing: border-box; display: inline; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">cd examples/lite/examples/object_detection/raspberry_pi
sh setup.sh</code></pre></div><div><br /></div><h2 style="text-align: left;"><span style="color: #2b00fe;">Run Image Object Detection</span></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgFZDLGUtj1WSW9SM_9D5V18WRwjXZ3U_iWJbUvSquJZMryHMUdwuUV_4X3TJe0zOXiBZ4k0tABOU0C6W3cWkxelTNhT8kMonifsJNp9zkfIE8srCe0wMy3PsD6va_HmRF_oWi_I3Tkn2Qq0ffaX_iJ90D81UCfoFrgS31MekDweFSa5ADnRjsEq9q4hUwu/s969/raspberrypi5-tensorflow-lite-object-detection-image-dog.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="685" data-original-width="969" height="453" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgFZDLGUtj1WSW9SM_9D5V18WRwjXZ3U_iWJbUvSquJZMryHMUdwuUV_4X3TJe0zOXiBZ4k0tABOU0C6W3cWkxelTNhT8kMonifsJNp9zkfIE8srCe0wMy3PsD6va_HmRF_oWi_I3Tkn2Qq0ffaX_iJ90D81UCfoFrgS31MekDweFSa5ADnRjsEq9q4hUwu/w640-h453/raspberrypi5-tensorflow-lite-object-detection-image-dog.jpg" width="640" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div><h2 style="text-align: left;"><b><span style="color: #2b00fe;">Run Video File Object Detection</span></b></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiVEYJwSnMDhXO4qjTOT7QqAhu4_Y4kyDNUcDCBOll6qPzK1Gn67zlNkmUcXCI81W1ZCA6UYUeZ7P1cIGLEQ-LhJ_8OjvKVSk86aRXzizBm4OK5jB6__OAu55Y5X6QElTBfG5r2CPYevZzBIRgOlk5vv-8oDrFxE5sTtdL-GmIL2fxRrg_6LJJCbkIyu5wO/s1920/raspberrypi5-tensorflow-lite-object-detection-video-1.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1080" data-original-width="1920" height="360" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiVEYJwSnMDhXO4qjTOT7QqAhu4_Y4kyDNUcDCBOll6qPzK1Gn67zlNkmUcXCI81W1ZCA6UYUeZ7P1cIGLEQ-LhJ_8OjvKVSk86aRXzizBm4OK5jB6__OAu55Y5X6QElTBfG5r2CPYevZzBIRgOlk5vv-8oDrFxE5sTtdL-GmIL2fxRrg_6LJJCbkIyu5wO/w640-h360/raspberrypi5-tensorflow-lite-object-detection-video-1.png" width="640" /></a></div><br /><h3 style="text-align: left;"><b>Source Code</b></h3><p style="text-align: left;"><a href="https://github.com/tensorflow/examples/tree/master/lite/examples/object_detection/raspberry_pi">https://github.com/tensorflow/examples/tree/master/lite/examples/object_detection/raspberry_pi</a></p><div><div class="separator" style="clear: both; color: #757575; font-family: Roboto, sans-serif; font-size: 15px; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; clear: left; color: #2196f3; float: left; margin-bottom: 1em; margin-left: 1em; text-decoration-line: none;"><br class="Apple-interchange-newline" /><br class="Apple-interchange-newline" /><br /></a></div></div><div style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;"><div class="separator" style="clear: both; color: #757575; font-family: Roboto, sans-serif; font-size: 15px; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; clear: left; color: #2196f3; float: left; margin-bottom: 1em; margin-left: 1em; text-decoration-line: none;"><br class="Apple-interchange-newline" /><br class="Apple-interchange-newline" /><img border="0" data-original-height="641" data-original-width="860" height="149" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/w200-h149/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; box-shadow: rgba(0, 0, 0, 0.1) 1px 1px 5px; height: inherit; max-width: 100%; padding: 5px; position: relative;" width="200" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; clear: left; color: #2196f3; float: left; margin-bottom: 1em; margin-left: 1em; text-decoration-line: none;"><br /></a></div><div style="color: #757575; font-family: Roboto, sans-serif; font-size: 15px;"><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Adun Nantakaew อดุลย์ นันทะแก้ว 081-6452400 </div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> LINE : adunnan</div><div><span style="font-family: arial;"><span style="color: #050505;"><span style="white-space-collapse: preserve;"> FaceBook : </span></span><span style="white-space-collapse: preserve;"><span style="color: #0000ee;"><a href="https://www.facebook.com/softpowergroup" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; color: #2196f3; text-decoration-line: none;">https://www.facebook.com/softpowergroup</a></span></span></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Youtube : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg?fbclid=IwAR0ZBdO15bxb1phy-1VQXXGYCpxEkwZKFvFOIOA0xs9YEpnBXzHCcypgb5E" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg</a></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Web Blog : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://raspberrypi4u.blogspot.com/?fbclid=IwAR2f4r8kFnbz_dheZrpr3drRRWD4R0PpL8uG7kKDNYRPR7Mvlg2V8mHg9dE" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">http://raspberrypi4u.blogspot.com/</a></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Website : <a href="https://softpower.tech/" style="color: #2288bb; text-decoration-line: none;">https://softpower.tech</a></div></div></div>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-23951936763315717162024-01-16T20:14:00.000-08:002024-01-16T20:19:53.221-08:00Raspberry pi5 Yolov8 Object Detection
<iframe width="560" height="315" src="https://www.youtube.com/embed/I3mmfxE7QTk?si=Avd07WbIFOxlRw56" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
<h1 style="text-align: left;"><span style="color: #ff00fe;"> Raspberry pi5 Yolov8 Object Detection</span></h1><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgAV8JPzi3cEzUuGt9lFTyB6XRLIPlWL8k_M6DRxdIiPMpCioNSRc6C63mod0i-pscLWQGJX-0beI_cfHpL_lkGUbDiXJ4DBWdlwfr8UtibBLEfHhje1J51HhNwLxKiFpj2KCfdj4UmAt2xGI7yHx945mG83rioKlpR7nN7LnAaTx-r17w25b7s5bfY7q4n/s2200/yolov8-logo.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="645" data-original-width="2200" height="94" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgAV8JPzi3cEzUuGt9lFTyB6XRLIPlWL8k_M6DRxdIiPMpCioNSRc6C63mod0i-pscLWQGJX-0beI_cfHpL_lkGUbDiXJ4DBWdlwfr8UtibBLEfHhje1J51HhNwLxKiFpj2KCfdj4UmAt2xGI7yHx945mG83rioKlpR7nN7LnAaTx-r17w25b7s5bfY7q4n/s320/yolov8-logo.png" width="320" /></a></div><div class="separator" style="clear: both; text-align: left;"><br /></div><h2 style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 22px; margin: 0px; position: relative; text-align: left;"><b>YOLOv8 from Ultralytics</b></h2><p style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"><a href="https://ultralytics.com/" rel="nofollow" style="box-sizing: border-box; color: #2288bb; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; text-align: -webkit-center; text-decoration-line: none;">Ultralytics</a><span face="-apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"" style="color: #1f2328; font-size: 16px; text-align: -webkit-center;"> </span><a href="https://github.com/ultralytics/ultralytics" style="box-sizing: border-box; color: #2288bb; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; text-align: -webkit-center; text-decoration-line: none;">YOLOv8</a><span face="-apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"" style="color: #1f2328; font-size: 16px; text-align: -webkit-center;"> is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.</span></p><p style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"></p><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg26pBRypJ7x-jZOd6srO8kbPI7riV9JgA7q6-higFvWPb8lNp6v7mLEE4QLhQWsA2TClqUo98-ObigHWXSAWAKlKOQlU5S8ShRj6-QyKaWXoREgkK5bXYi_ewxcN78zV9G38Bp43I49y2Vi-p2Vh3LJjBJqFIAyK1rgse4AoBffHC-G1gmRvt9cF_gENbl/s2000/Rpi5.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1518" data-original-width="2000" height="243" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg26pBRypJ7x-jZOd6srO8kbPI7riV9JgA7q6-higFvWPb8lNp6v7mLEE4QLhQWsA2TClqUo98-ObigHWXSAWAKlKOQlU5S8ShRj6-QyKaWXoREgkK5bXYi_ewxcN78zV9G38Bp43I49y2Vi-p2Vh3LJjBJqFIAyK1rgse4AoBffHC-G1gmRvt9cF_gENbl/s320/Rpi5.jpg" width="320" /></a></div><p></p><h2 style="background-color: white; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; text-align: left;"><span face="-apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"" style="color: #2b00fe; font-size: medium; text-align: -webkit-center;"><b>Raspberry pi 5</b></span></h2>Specification<br /><ul style="text-align: left;"><li>Broadcom BCM2712 2.4GHz quad-core 64-bit Arm Cortex-A76 CPU, with cryptography extensions, 512KB per-core L2 caches and a 2MB shared L3 cache</li><li>VideoCore VII GPU, supporting OpenGL ES 3.1, Vulkan 1.2</li><li>Dual 4Kp60 HDMI® display output with HDR support</li><li>4Kp60 HEVC decoder</li><li>LPDDR4X-4267 SDRAM (4GB and 8GB SKUs available at launch)</li><li>Dual-band 802.11ac Wi-Fi®</li><li>Bluetooth 5.0 / Bluetooth Low Energy (BLE)</li><li>microSD card slot, with support for high-speed SDR104 mode</li><li>2 × USB 3.0 ports, supporting simultaneous 5Gbps operation</li><li>2 × USB 2.0 ports</li><li>Gigabit Ethernet, with PoE+ support (requires separate PoE+ HAT)</li><li>2 × 4-lane MIPI camera/display transceivers</li><li>PCIe 2.0 x1 interface for fast peripherals (requires separate M.2 HAT or other adapter)</li><li>5V/5A DC power via USB-C, with Power Delivery support</li><li>Raspberry Pi standard 40-pin header</li><li>Real-time clock (RTC), powered from external battery</li><li>Power button</li></ul><div><br /></div><p style="background-color: white; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"><span face="-apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"" style="font-size: 16px; text-align: -webkit-center;"><span face="Roboto, -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif" style="color: #2b00fe; font-size: 17.6px; text-align: start;">Raspberry Pi 3, 4, and 5 compare</span></span></p><div class="md-typeset__scrollwrap" style="background-color: white; box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif; font-size: 17.6px; margin: 1em -0.8rem; overflow-x: auto; touch-action: auto;"><div class="md-typeset__table" style="box-sizing: inherit; display: inline-block; line-height: 1; margin-bottom: 0.5em; padding: 0px 0.8rem;"><table style="background-color: var(--md-default-bg-color); border-collapse: initial; border-radius: 0.1rem; border-right: none; border-spacing: 0px; box-sizing: inherit; display: inline-block; font-size: 0.74rem; margin: 0px; max-width: 100%; overflow: auto; touch-action: auto; width: 854.844px;"><thead style="box-sizing: inherit;"><tr style="box-sizing: inherit;"><th style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: none; box-sizing: inherit; min-width: 5rem; padding: 9px; text-align: left; vertical-align: top;">Feature</th><th style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: none; box-sizing: inherit; min-width: 5rem; padding: 9px; text-align: left; vertical-align: top;">Raspberry Pi 3</th><th style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: none; box-sizing: inherit; min-width: 5rem; padding: 9px; text-align: left; vertical-align: top;">Raspberry Pi 4</th><th style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: none; box-sizing: inherit; min-width: 5rem; padding: 9px; text-align: left; vertical-align: top;"><span style="color: #ff00fe;">Raspberry Pi 5</span></th></tr></thead><tbody style="box-sizing: inherit;"><tr style="box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">CPU</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">1.2GHz Quad-Core ARM Cortex-A53</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">1.5GHz Quad-core 64-bit ARM Cortex-A72</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">2.4GHz Quad-core 64-bit Arm Cortex-A76</td></tr><tr style="background-color: #f6f8fa; box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">RAM</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">1GB LPDDR2</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">2GB, 4GB or 8GB LPDDR4</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><em style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Details not yet available</em></td></tr><tr style="box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">USB Ports</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">4 x USB 2.0</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">2 x USB 2.0, 2 x USB 3.0</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">2 x USB 3.0, 2 x USB 2.0</td></tr><tr style="background-color: #f6f8fa; box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Network</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">Ethernet & Wi-Fi 802.11n</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">Gigabit Ethernet & Wi-Fi 802.11ac</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">Gigabit Ethernet with PoE+ support, Dual-band 802.11ac Wi-Fi®</td></tr><tr style="background-color: var(--md-typeset-table-color--light); box-shadow: 0 .05rem 0 var(--md-default-bg-color) inset; box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Performance</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">Slower, may require lighter YOLO models</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">Faster, can run complex YOLO models</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><em style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Details not yet available</em></td></tr><tr style="background-color: #f6f8fa; box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Power Requirement</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">2.5A power supply</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;">3.0A USB-C power supply</td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><em style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Details not yet available</em></td></tr><tr style="box-sizing: inherit; transition: background-color 125ms ease 0s;"><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><strong style="box-sizing: inherit; margin-bottom: 0px; margin-top: 0px;">Official Documentation</strong></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><a href="https://www.raspberrypi.org/documentation/hardware/raspberrypi/bcm2837/README.md" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; margin-bottom: 0px; margin-top: 0px; text-decoration-line: none; transition: color 125ms ease 0s; word-break: normal;">Link</a></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><a href="https://www.raspberrypi.org/documentation/hardware/raspberrypi/bcm2711/README.md" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; margin-bottom: 0px; margin-top: 0px; text-decoration-line: none; transition: color 125ms ease 0s; word-break: normal;">Link</a></td><td style="border-bottom: none; border-left: none; border-spacing: 0px; border-top: .05rem solid var(--md-typeset-table-color); box-sizing: inherit; padding: 9px; vertical-align: top;"><a href="https://www.raspberrypi.com/news/introducing-raspberry-pi-5/" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; margin-bottom: 0px; margin-top: 0px; text-decoration-line: none; transition: color 125ms ease 0s; word-break: normal;">Link</a></td></tr></tbody></table></div></div><p style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"><span face="-apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"" style="color: #1f2328; font-size: 16px; text-align: -webkit-center;"></span></p><h2 style="background-color: white; box-sizing: inherit; font-family: Roboto, -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif; font-size: 17.6px; text-align: left;"><span style="color: #2b00fe;">Raspberry pi OS</span></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgc6i-gTZDxYS-ORMHjPlpqzW2j4gVfbYlaHQT03fxGXO66aq4sL96lbXAwddeoYzQxyie_4LBiT-fCLEbGoj8iTVyrxJlH9GQL5iqwVfUZrxWk2DtF6dqhxv3MrnAAyZ7wnxTq6Y0jYtMeeZ_ANSW-J4aCURNKJZjBoM3uoSC12uEZd-khtHnmrxnw5SJ_/s1145/raspberrpi5-object-detection-Rpi-OS.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="402" data-original-width="1145" height="224" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgc6i-gTZDxYS-ORMHjPlpqzW2j4gVfbYlaHQT03fxGXO66aq4sL96lbXAwddeoYzQxyie_4LBiT-fCLEbGoj8iTVyrxJlH9GQL5iqwVfUZrxWk2DtF6dqhxv3MrnAAyZ7wnxTq6Y0jYtMeeZ_ANSW-J4aCURNKJZjBoM3uoSC12uEZd-khtHnmrxnw5SJ_/w640-h224/raspberrpi5-object-detection-Rpi-OS.png" width="640" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjplMpQ8wBC0VptZlXNUtvZ2geGCCNLdn9QM7QmfckX1cuZNDfWDPKr6u0tYWKOAv7A1N-hYsEjGgCoyM0ofDwBvS0eXG266Nsh17IfYjyrvArWf1Kmdlb9sK1TnZVPEmJIMfLt3Zvkk50H2bR1GL1dHc7uzb1nO-pIHiPsR2MIqhKXdACnu_0n3bnSvdxp/s923/raspberrpi5-object-detection-OS.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="464" data-original-width="923" height="322" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjplMpQ8wBC0VptZlXNUtvZ2geGCCNLdn9QM7QmfckX1cuZNDfWDPKr6u0tYWKOAv7A1N-hYsEjGgCoyM0ofDwBvS0eXG266Nsh17IfYjyrvArWf1Kmdlb9sK1TnZVPEmJIMfLt3Zvkk50H2bR1GL1dHc7uzb1nO-pIHiPsR2MIqhKXdACnu_0n3bnSvdxp/w640-h322/raspberrpi5-object-detection-OS.png" width="640" /></a></div><p style="background-color: white; box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif; font-size: 17.6px;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjegfjTQCp2a8gXIQL_ivrFg-Uoo029-ICQpQQ2LgChI3RsBB_k_TIiQqiQJ8hARRcq32zmOrFz7dpozvhxYJhRbvwRpJ1Kzp5ccQ9MvBG7fm2d8MCV5ji9mzwoB5xLlqqYj_fUiu36NgJO5riR9DGHzkw5Cfx2atKuyttu9rjxhjMOhH3hTYTOy8SJja6n/s1341/yolov8-banner.png" style="font-family: Times; font-size: medium; margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="429" data-original-width="1341" height="102" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjegfjTQCp2a8gXIQL_ivrFg-Uoo029-ICQpQQ2LgChI3RsBB_k_TIiQqiQJ8hARRcq32zmOrFz7dpozvhxYJhRbvwRpJ1Kzp5ccQ9MvBG7fm2d8MCV5ji9mzwoB5xLlqqYj_fUiu36NgJO5riR9DGHzkw5Cfx2atKuyttu9rjxhjMOhH3hTYTOy8SJja6n/s320/yolov8-banner.png" width="320" /></a></p><h2 style="background-color: white; box-sizing: inherit; font-family: Roboto, -apple-system, BlinkMacSystemFont, Helvetica, Arial, sans-serif; font-size: 17.6px; text-align: left;"><span style="color: #2b00fe;">Install Library</span></h2><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;">Pip install the ultralytics package including all <a href="https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml" style="background-color: transparent; box-sizing: border-box; text-underline-offset: 0.2rem;">requirements</a> in a <a href="https://www.python.org/" rel="nofollow" style="background-color: transparent; box-sizing: border-box; text-underline-offset: 0.2rem;"><span style="box-sizing: border-box; font-weight: var(--base-text-weight-semibold, 600);">Python>=3.8</span></a> environment with <a href="https://pytorch.org/get-started/locally/" rel="nofollow" style="background-color: transparent; box-sizing: border-box; text-underline-offset: 0.2rem;"><span style="box-sizing: border-box; font-weight: var(--base-text-weight-semibold, 600);">PyTorch>=1.8</span></a>.</p><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><a href="https://badge.fury.io/py/ultralytics" rel="nofollow" style="background-color: transparent; box-sizing: border-box; text-underline-offset: 0.2rem;"><img alt="PyPI version" data-canonical-src="https://badge.fury.io/py/ultralytics.svg" src="https://camo.githubusercontent.com/4c91d48324bb1a72eaebf67eb946680bf6ac202a6a423aec0a594877d02ff3f8/68747470733a2f2f62616467652e667572792e696f2f70792f756c7472616c79746963732e737667" style="background-color: var(--bgColor-default, var(--color-canvas-default)); border-style: none; box-sizing: content-box; max-width: 100%;" /></a> <a href="https://pepy.tech/project/ultralytics" rel="nofollow" style="background-color: transparent; box-sizing: border-box; text-underline-offset: 0.2rem;"><img alt="Downloads" data-canonical-src="https://static.pepy.tech/badge/ultralytics" src="https://camo.githubusercontent.com/19e3e80593e4f6a8cafb8dd061668d7d95aa8c33388563fc9bdd99ed16efcbc3/68747470733a2f2f7374617469632e706570792e746563682f62616467652f756c7472616c7974696373" style="background-color: var(--bgColor-default, var(--color-canvas-default)); border-style: none; box-sizing: content-box; max-width: 100%;" /></a></p><div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" style="box-sizing: border-box; color: #1f2328; display: flex; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; justify-content: space-between; margin-bottom: 16px; overflow: auto; position: relative;"><pre style="border-radius: 6px; box-sizing: border-box; color: var(--fgColor-default, var(--color-fg-default)); font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;"><span style="background-color: #fcff01;">pip install <b>ultralytics</b></span></pre></div><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"></p><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoPAF6pKglzetDqr6JMG_E_EenzSLKF9J4RoBQawcEPv_Fi17UMjhokL7HotdkT4i95EfRd0kpCGfQKcQc09PXDg6O4b_jhj4mifkYNPl3mgVGwjBBj05oF8P1QThUUXADknut8IPzKY_r6w8z3HX1_InJGWQ8pOuWu3lMwUJ9GO3m8uA46uqqI9XYY2ph/s653/raspberrpi5-object-detection-ultralytics-version.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="320" data-original-width="653" height="314" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoPAF6pKglzetDqr6JMG_E_EenzSLKF9J4RoBQawcEPv_Fi17UMjhokL7HotdkT4i95EfRd0kpCGfQKcQc09PXDg6O4b_jhj4mifkYNPl3mgVGwjBBj05oF8P1QThUUXADknut8IPzKY_r6w8z3HX1_InJGWQ8pOuWu3lMwUJ9GO3m8uA46uqqI9XYY2ph/w640-h314/raspberrpi5-object-detection-ultralytics-version.png" width="640" /></a></div><p></p><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><b>Run Test Image with Command Line</b></p><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;">YOLOv8 may be used directly in the Command Line Interface (CLI) with a <code style="background-color: var(--bgColor-neutral-muted, var(--color-neutral-muted)); border-radius: 6px; box-sizing: border-box; font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; font-size: 13.6px; margin: 0px; padding: 0.2em 0.4em; white-space-collapse: break-spaces;">yolo</code> command:</p><div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" style="box-sizing: border-box; color: #1f2328; display: flex; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; justify-content: space-between; margin-bottom: 16px; overflow: auto; position: relative;"><pre style="border-radius: 6px; box-sizing: border-box; color: var(--fgColor-default, var(--color-fg-default)); font-family: ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace; line-height: 1.45; margin-bottom: 0px; margin-top: 0px; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;"><span style="background-color: #fcff01;">yolo predict model=<b>yolov8n.pt</b> source=<span class="pl-s" color="var(--color-prettylights-syntax-string)" style="box-sizing: border-box;"><span class="pl-pds" color="var(--color-prettylights-syntax-string)" style="box-sizing: border-box;">'</span>https://ultralytics.com/images/bus.jpg<span class="pl-pds" color="var(--color-prettylights-syntax-string)" style="box-sizing: border-box;">'</span></span></span></pre><div class="zeroclipboard-container" style="animation: auto ease 0s 1 normal none running none; box-sizing: border-box;"><clipboard-copy aria-label="Copy" class="ClipboardButton btn btn-invisible js-clipboard-copy m-2 p-0 tooltipped-no-delay d-flex flex-justify-center flex-items-center" data-copy-feedback="Copied!" data-tooltip-direction="w" role="button" style="align-items: center; appearance: none; border-radius: 6px; border: 0px; box-shadow: none; box-sizing: border-box; color: var(--fgColor-accent, var(--color-accent-fg)); cursor: pointer; display: flex; font-weight: var(--base-text-weight-medium, 500); height: var(--control-small-size, 28px); justify-content: center; line-height: 20px; margin: var(--base-size-8, 8px) !important; padding: 0px; position: relative; text-wrap: nowrap; transition: color 80ms cubic-bezier(0.33, 1, 0.68, 1) 0s, background-color 0s ease 0s, box-shadow 0s ease 0s, border-color 0s ease 0s; user-select: none; vertical-align: middle; width: var(--control-small-size, 28px);" tabindex="0" value="yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg'"><svg aria-hidden="true" class="octicon octicon-copy js-clipboard-copy-icon" data-view-component="true" height="16" version="1.1" viewbox="0 0 16 16" width="16"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 0 1 0 1.5h-1.5a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-1.5a.75.75 0 0 1 1.5 0v1.5A1.75 1.75 0 0 1 9.25 16h-7.5A1.75 1.75 0 0 1 0 14.25Z"></path><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0 1 14.25 11h-7.5A1.75 1.75 0 0 1 5 9.25Zm1.75-.25a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-7.5a.25.25 0 0 0-.25-.25Z"></path></svg></clipboard-copy></div></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjcxc3VFySVwssvez01TnqGhktMHnTB1HSoJ0hUle1_LUUcCiF0iSqbCTBHASnh-CDhRqocCsDZjFiKFGxUNDyCcAaFRxV3aPTlkzbwPNOSF8qSj9eAB8jyYQxT35hn8AyVQiV6ckmitamuyDpz4Eh-dZhzZApUI8F9bk54caWFZwp7wynHiPjU4JAZ0qFC/s1323/raspberrpi5-object-detection-image.PNG" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="493" data-original-width="1323" height="238" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjcxc3VFySVwssvez01TnqGhktMHnTB1HSoJ0hUle1_LUUcCiF0iSqbCTBHASnh-CDhRqocCsDZjFiKFGxUNDyCcAaFRxV3aPTlkzbwPNOSF8qSj9eAB8jyYQxT35hn8AyVQiV6ckmitamuyDpz4Eh-dZhzZApUI8F9bk54caWFZwp7wynHiPjU4JAZ0qFC/w640-h238/raspberrpi5-object-detection-image.PNG" width="640" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5eFrFQFRz5jmIpHIyb98l6k-Qy4vJRHpG1-xqwJ6Lphgtm-iKrU7EzDxa5Y8nnP_qN06RTFIHgbGf4yT_Pxrr0oD99WcIkUcu9M9gS48xSWqEsNkuh4KoY8s4XMwQwRcPtO9A8DRJYkU5pB-1CE0hRBuw9qQhlcgxMfGPIGXMstfdUPKAnpYa0QVJ2JOa/s1080/bus.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1080" data-original-width="810" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5eFrFQFRz5jmIpHIyb98l6k-Qy4vJRHpG1-xqwJ6Lphgtm-iKrU7EzDxa5Y8nnP_qN06RTFIHgbGf4yT_Pxrr0oD99WcIkUcu9M9gS48xSWqEsNkuh4KoY8s4XMwQwRcPtO9A8DRJYkU5pB-1CE0hRBuw9qQhlcgxMfGPIGXMstfdUPKAnpYa0QVJ2JOa/w300-h400/bus.jpg" width="300" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><br /></div><b>Run Video File</b><div><b><br /></b><p dir="auto" style="box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><span face="ui-monospace, SFMono-Regular, "SF Mono", Menlo, Consolas, "Liberation Mono", monospace" style="background-color: #fcff01; font-size: medium; white-space: pre;">yolo predict model=yolov8n.pt <b>source=/home/pi/Video/your_video.mp4</b> show=True</span></p><div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" style="box-sizing: border-box; color: #1f2328; display: flex; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; justify-content: space-between; margin-bottom: 16px; overflow: auto; position: relative;"><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh1FNQra-hp2XqCgbN55yaRRPCGlpXatujtpEEkOZQaBGih1-MFZBo_jAatRESI1Pd0vLlt_sphl2rxg8ypKHs_9P2M-Lrjp-coKoYKGx2MVWGgoHZ24DN235xcuQW5Kd9xxRle9GGRAMITInox8JYOYWfjT9TeN_wZXFYiAtObrtr_aqEG4YmEXfzJCUj3/s1280/Raspberrypi5-yolov8-object-detection-run2.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="800" data-original-width="1280" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh1FNQra-hp2XqCgbN55yaRRPCGlpXatujtpEEkOZQaBGih1-MFZBo_jAatRESI1Pd0vLlt_sphl2rxg8ypKHs_9P2M-Lrjp-coKoYKGx2MVWGgoHZ24DN235xcuQW5Kd9xxRle9GGRAMITInox8JYOYWfjT9TeN_wZXFYiAtObrtr_aqEG4YmEXfzJCUj3/w640-h400/Raspberrypi5-yolov8-object-detection-run2.png" width="640" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><br /></div><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><br /></p><h2 style="margin: 0px; position: relative; text-align: left;"><span style="font-size: medium;">Reference</span></h2><div><span id="docs-internal-guid-743fbcbb-7fff-abcc-d970-af51dcb59ee2"><h1 dir="ltr" style="line-height: 1.38; margin-bottom: 6pt; margin-top: 20pt;"><span face="Arial, sans-serif" style="font-size: 12pt; font-variant-alternates: normal; font-variant-east-asian: normal; font-variant-numeric: normal; font-variant-position: normal; vertical-align: baseline; white-space-collapse: preserve;">Quick Start Guide: Raspberry Pi and Pi Camera with YOLOv5 and YOLOv8</span></h1><p dir="ltr" style="line-height: 1.38; margin-bottom: 0pt; margin-top: 0pt;"><a href="https://docs.ultralytics.com/guides/raspberry-pi/#choose-your-yolo-version-yolov5-or-yolov8" style="text-decoration-line: none;"><span face="Arial, sans-serif" style="color: #1155cc; font-size: 11pt; font-variant-alternates: normal; font-variant-east-asian: normal; font-variant-numeric: normal; font-variant-position: normal; text-decoration-line: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space-collapse: preserve;">https://docs.ultralytics.com/guides/raspberry-pi/#choose-your-yolo-version-yolov5-or-yolov8</span></a></p></span></div><div><br /></div><div><a href="https://github.com/ultralytics/ultralytics" style="color: #2288bb; text-decoration-line: none;">https://github.com/ultralytics/ultralytics</a></div><div><br /></div><div><div class="separator" style="clear: both; color: #757575; font-family: Roboto, sans-serif; font-size: 15px; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; clear: left; color: #2196f3; float: left; margin-bottom: 1em; margin-left: 1em; text-decoration-line: none;"><br class="Apple-interchange-newline" /><br class="Apple-interchange-newline" /><img border="0" data-original-height="641" data-original-width="860" height="149" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/w200-h149/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background: rgb(255, 255, 255); border: 0px; box-shadow: rgba(0, 0, 0, 0.1) 1px 1px 5px; height: inherit; max-width: 100%; padding: 5px; position: relative;" width="200" /></a></div><div style="color: #757575; font-family: Roboto, sans-serif; font-size: 15px;"><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"><br /></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Adun Nantakaew อดุลย์ นันทะแก้ว 081-6452400 </div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> LINE : adunnan</div><div><span style="font-family: arial;"><span style="color: #050505;"><span style="white-space-collapse: preserve;"> FaceBook : </span></span><span style="white-space-collapse: preserve;"><span style="color: #0000ee;"><a href="https://www.facebook.com/softpowergroup" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; color: #2196f3; text-decoration-line: none;">https://www.facebook.com/softpowergroup</a></span></span></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Youtube : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg?fbclid=IwAR0ZBdO15bxb1phy-1VQXXGYCpxEkwZKFvFOIOA0xs9YEpnBXzHCcypgb5E" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg</a></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> Web Blog : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://raspberrypi4u.blogspot.com/?fbclid=IwAR2f4r8kFnbz_dheZrpr3drRRWD4R0PpL8uG7kKDNYRPR7Mvlg2V8mHg9dE" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">http://raspberrypi4u.blogspot.com/</a></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space-collapse: preserve;"> <span style="background-color: white;">Website : </span><a href="https://softpower.tech/" style="color: #2288bb; text-decoration-line: none;">https://softpower.tech</a></div><div><br style="background-color: white;" /></div></div></div><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><br /></p><p dir="auto" style="background-color: white; box-sizing: border-box; color: #1f2328; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px; margin-top: 0px;"><br class="Apple-interchange-newline" /><br /></p><div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" style="box-sizing: border-box; color: #1f2328; display: flex; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; justify-content: space-between; margin-bottom: 16px; overflow: auto; position: relative;"></div></div>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-79382923992125871942022-09-04T08:04:00.010-07:002024-01-16T06:05:34.043-08:00Raspberry pi YOLOv4 Object Detection with Intel Neural compute stick and OpenVINO<h1 style="text-align: left;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh11s3ilGtCB7OQHtNW8W45-aFrlxK04CSu5-ZKfBb-SDcl4bg7sdxoip3nNcqpFLMJMTf4tJ9-v6xyVgwqo4sG4u7GQdOVBsLEsX63JpLOCj6s8uFjPtcfRIvybS4RdluWXmqzmFl6DWMSvlbOsi3k_UkM_fOihhubw6a3Ei1XuCHr60E9BCU0mXZC0w/s1280/raspberrypi-yolov4-object-detection.jpg" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="720" data-original-width="1280" height="360" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh11s3ilGtCB7OQHtNW8W45-aFrlxK04CSu5-ZKfBb-SDcl4bg7sdxoip3nNcqpFLMJMTf4tJ9-v6xyVgwqo4sG4u7GQdOVBsLEsX63JpLOCj6s8uFjPtcfRIvybS4RdluWXmqzmFl6DWMSvlbOsi3k_UkM_fOihhubw6a3Ei1XuCHr60E9BCU0mXZC0w/w640-h360/raspberrypi-yolov4-object-detection.jpg" width="640" /></a></div></h1><h1 style="text-align: left;"><span style="color: #ff00fe;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/p2JCyp8GH9s" title="YouTube video player" width="560"></iframe></span></h1><h1 style="text-align: left;"><span style="color: #ff00fe;">Raspberry pi </span><span style="color: #800180;">YOLOv4 Object Detection</span> </h1><h1 style="text-align: left;"><span style="font-weight: normal;"><span style="font-size: large;">with</span></span> <span style="color: #2b00fe;">Intel (<span style="font-size: large;">Neural compute stick)</span></span> <span style="font-weight: normal;"><span style="font-size: large;">and</span></span> <span style="color: #2b00fe;">OpenVINO</span></h1><div><span style="color: #2b00fe;"><br /></span></div><p class="p1" style="background-color: white; font-family: "Helvetica Neue Light"; font-size: 18px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px;"><span class="s1" style="color: #424448; font-kerning: none;">This is implementation of YOLOV4,YOLOV4-relu,YOLOV4-tiny ,YOLOV4-tiny-3l ,Scaled-YOLOv4 in </span><span class="s2" style="color: #444444; font-family: "Helvetica Neue"; font-kerning: none; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"><b>OpenVINO2021.3 on Raspberry pi.</b></span></p><h3 style="background-color: white; color: #424448; font-family: "Helvetica Neue Light"; font-size: 18px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px; text-align: left;"><span class="s1" style="font-kerning: none;">Last Article. </span>If you want to use YOLOv3</h3><p class="p1" style="background-color: white; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px;"><span class="s2" style="color: #444444; font-family: Helvetica Neue; font-kerning: none; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"><a href="http://raspberrypi4u.blogspot.com/2022/08/raspberrypi-yolo-objectdetection.html">http://raspberrypi4u.blogspot.com/2022/08/raspberrypi-yolo-objectdetection.html</a></span></p><p class="p1" style="background-color: white; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px;"><br /></p><p class="p1" style="background-color: white; color: #424448; font-family: "Helvetica Neue Light"; font-size: 18px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px;"><span class="s2" style="color: #fb02ff; font-family: "Helvetica Neue"; font-kerning: none; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"></span></p><div class="separator" style="clear: both; text-align: left;"><span class="s2" style="color: #fb02ff; font-family: "Helvetica Neue"; font-kerning: none; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgjvs08qBaGYm4df0Y4yttjZOvCOjNrzgIk10CJCdH3DcFOosiL0mvG2NK7NZnA0mKCeQwc73NqrWs3S4IzAKyvytAq3l02PiRJ1NNhm4Tv3N9szhp7BVxs8TX-A-0x_FDK-Hx22_dAS7gfAanrL2iSaiZlMLo8p0wt-e6vg5xSlUWP8eGspxBWGYAEwA/s1200/raspi4_intel_neural-compute_stick.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="900" data-original-width="1200" height="300" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgjvs08qBaGYm4df0Y4yttjZOvCOjNrzgIk10CJCdH3DcFOosiL0mvG2NK7NZnA0mKCeQwc73NqrWs3S4IzAKyvytAq3l02PiRJ1NNhm4Tv3N9szhp7BVxs8TX-A-0x_FDK-Hx22_dAS7gfAanrL2iSaiZlMLo8p0wt-e6vg5xSlUWP8eGspxBWGYAEwA/w400-h300/raspi4_intel_neural-compute_stick.jpg" width="400" /></a></span></div><p></p><p class="p1" style="background-color: white; color: #424448; font-family: "Helvetica Neue Light"; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px 0px 20px;"><span class="s2" style="color: #fb02ff; font-family: "Helvetica Neue"; font-kerning: none; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="color: #0d0d0d; font-size: 15px; white-space: pre-wrap;"><b>Hardware</b>
· Raspberry Pi Board (4B )
· Intel Neural Compute Stick 2
· SD Card 32GB
· 5V DC. 2A Power Supply
<b>Software</b>
· OS Raspbian 10 ( Buster )
· Python 3.7.3
· </span><b style="color: #0d0d0d; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 15px; white-space: pre-wrap;">OpenVINO Toolkit 2021.3 </b><span style="font-size: x-small;"><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;">( </span><span style="color: black; font-family: Times;">2021.3.0-2787-60059f2c755-releases/2021/3 )</span></span><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">
· OpenCV 4.0.0</span></span></p><h3 id="yolov4" style="box-sizing: inherit; font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 1.25em; letter-spacing: -0.01em; line-height: 1.5; margin: 1.6em 0px 0.8em;"><span style="background-color: white;"><span style="color: #38761d;">YOLOv4</span></span></h3><p style="background-color: white; box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 16px;">With the original authors work on YOLO coming to a standstill, YOLOv4 was released by Alexey Bochoknovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. The paper was titled <a href="https://arxiv.org/abs/2004.10934v1" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">YOLOv4: Optimal Speed and Accuracy of Object Detection</a></p><p style="background-color: white; box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 16px;"><strong style="box-sizing: inherit;">Author:</strong> <a href="https://ru.linkedin.com/in/alexey-bochkovskiy-1213b542" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">Alexey Bochoknovskiy</a>, <a href="https://www.researchgate.net/profile/Chien-Yao-Wang" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">Chien-Yao Wang</a>, and <a href="https://en.wikipedia.org/wiki/Mark_Liao" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">Hong-Yuan Mark Liao</a><br style="box-sizing: inherit;" /><strong style="box-sizing: inherit;">Released:</strong> 23 April 2020</p><p><br /></p><h3 style="text-align: left;">Run Python Code on <span style="color: #2b00fe;">YOLOv4</span></h3><p><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/qmJP2Ub63s0" title="YouTube video player" width="560"></iframe></p><p><br /></p><h3 style="text-align: left;">Run Python Code on <span style="color: red;">YOLOv4-tiny</span></h3><p><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/i4j0vzE6Zbw" title="YouTube video player" width="560"></iframe></p><h3 style="text-align: left;"><br /></h3><h3 style="text-align: left;">Compare Performance ( <span style="color: #2b00fe;">YOLOv4 vs. YOLOv4-tiny</span> )</h3><h2 style="color: #0c0c0c; font-family: Helvetica; font-size: 22px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; position: relative;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/p2JCyp8GH9s" title="YouTube video player" width="560"></iframe></h2><div><br /></div><div><br /></div><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEjmX2BXlpLiTqnN8Hu8R1goBJOFyklTpRkvnlsd9o80G2TQh-EuLEJqC1Uq-zmlgmCZMMulvPWE5RJDs5Fv9FlLSuC3bsJ3kG7joRX2b5o7y3oW98n3pNtG4cb_r_zQg5pW1OPjm2IPStlm35Sks55NhI0LmJ3_2kuJWyq1G5ASBj7UgMH-7j8QGpqbSw" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="792" data-original-width="1329" height="239" src="https://blogger.googleusercontent.com/img/a/AVvXsEjmX2BXlpLiTqnN8Hu8R1goBJOFyklTpRkvnlsd9o80G2TQh-EuLEJqC1Uq-zmlgmCZMMulvPWE5RJDs5Fv9FlLSuC3bsJ3kG7joRX2b5o7y3oW98n3pNtG4cb_r_zQg5pW1OPjm2IPStlm35Sks55NhI0LmJ3_2kuJWyq1G5ASBj7UgMH-7j8QGpqbSw=w400-h239" width="400" /></a></div><div class="separator" style="clear: both; text-align: left;"><br /><a href="https://blogger.googleusercontent.com/img/a/AVvXsEglXFZ385AAPkFxusFT1Epml3YNQdcCjW1CPlRNxbccjOEmW8ctRxtt57zir_-iXcJPXOxkYLGPZNXwJ6WW0WLRPyuHpuu2pdWRD_roliF8I1ZEzyIp3lxuHcdYuIR_QSgnBowxFqJP0ulTeg1MSQ0um1mLwcO6Bymw-iboUbyoXfVrEEfX7Sc-VVx7ww" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="793" data-original-width="1333" height="238" src="https://blogger.googleusercontent.com/img/a/AVvXsEglXFZ385AAPkFxusFT1Epml3YNQdcCjW1CPlRNxbccjOEmW8ctRxtt57zir_-iXcJPXOxkYLGPZNXwJ6WW0WLRPyuHpuu2pdWRD_roliF8I1ZEzyIp3lxuHcdYuIR_QSgnBowxFqJP0ulTeg1MSQ0um1mLwcO6Bymw-iboUbyoXfVrEEfX7Sc-VVx7ww=w400-h238" width="400" /></a> </div><br /><br /><p></p><p></p><div class="separator" style="clear: both; text-align: left;"><div class="separator" style="clear: both; text-align: left;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEi__Gu6DeNxNXCNTWztcaiYCEGfInm41Ss74vxcWJeaZICWGilvzpxyu7ghuuxz2BOdBBPUNv8M0Z9RzvoqN25nI1QVC_xA0wulz4KfY0gjrLS9ORqmIIMge0pp25cKqh9qraU9lQe4Ug4BdkGcsLNas1_z67C5oIzr1asPL-9MOYMg6oECrLPVFSGmww" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="291" data-original-width="788" height="236" src="https://blogger.googleusercontent.com/img/a/AVvXsEi__Gu6DeNxNXCNTWztcaiYCEGfInm41Ss74vxcWJeaZICWGilvzpxyu7ghuuxz2BOdBBPUNv8M0Z9RzvoqN25nI1QVC_xA0wulz4KfY0gjrLS9ORqmIIMge0pp25cKqh9qraU9lQe4Ug4BdkGcsLNas1_z67C5oIzr1asPL-9MOYMg6oECrLPVFSGmww=w640-h236" width="640" /></a></div></div><div><br /></div><div style="background-color: white; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif;"><div style="color: #222222;"><br /></div><div style="color: #222222;"><br /></div><h3 style="text-align: left;"><span style="color: #222222;">Compare YOLOv4-tiny with </span><span style="color: #ff00fe;">Raspberry pi + Intel NCS</span><span style="color: #222222;"> vs. </span><span style="color: #38761d;">NVIDIA Jetson Nano</span></h3><div style="color: #222222;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/jFpOnd23-_I" title="YouTube video player" width="560"></iframe></div><div style="color: #222222;"><br /></div><div style="color: #222222;"><br /></div><div style="color: #222222;"><b>Performance Compare</b></div><div style="color: #222222;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEgYYbmCA08IjArTO2gDbORFq8kMFK1mAnVmiTkMay1yB7EENmKYYcOaERqD84kZPY04CCYduMa5XmuITl-UicAHUKaNRvY75o3EpqHoD5qa7BN9d2_esKGXRiM3NYD_cy3HkRUFKYxd2YVgadWSHu8x2nz9aEJvDOv5MwQCMNJ_lrYOFHaINgptJ3TjYQ" style="margin-left: 1em; margin-right: 1em; text-align: left;"><img data-original-height="336" data-original-width="1200" height="180" src="https://blogger.googleusercontent.com/img/a/AVvXsEgYYbmCA08IjArTO2gDbORFq8kMFK1mAnVmiTkMay1yB7EENmKYYcOaERqD84kZPY04CCYduMa5XmuITl-UicAHUKaNRvY75o3EpqHoD5qa7BN9d2_esKGXRiM3NYD_cy3HkRUFKYxd2YVgadWSHu8x2nz9aEJvDOv5MwQCMNJ_lrYOFHaINgptJ3TjYQ=w640-h180" width="640" /></a></div><br /></div><div style="color: #222222;"><br /></div><div style="color: #222222;"><br /></div><h2 style="color: #0c0c0c; font-family: Helvetica; font-size: 22px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; position: relative;"><span style="color: black; font-family: Times;">Reference</span></h2><div style="color: #222222; font-size: 13.2px;"><span style="color: black; font-family: Times;"><br /></span></div><div style="color: #222222;"><span style="color: black; font-family: Times;"><b>Source Code</b></span></div><div style="color: #222222; font-size: 13.2px;"><span style="color: black; font-family: Times; font-size: medium;"><a href="https://github.com/TNTWEN/OpenVINO-YOLOV4">https://github.com/TNTWEN/OpenVINO-YOLOV4</a></span></div><div style="color: #222222; font-size: 13.2px;"><h3 class="post-title entry-title" itemprop="name" style="color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 22px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; font-weight: normal; line-height: normal; margin: 0.75em 0px 0px; position: relative;">Raspberry pi YOLOv3 Object detection </h3></div><div style="color: #222222; font-size: 13.2px;"><a href="http://raspberrypi4u.blogspot.com/2022/08/raspberrypi-yolo-objectdetection.html" style="font-family: "Helvetica Neue"; font-size: medium;">http://raspberrypi4u.blogspot.com/2022/08/raspberrypi-yolo-objectdetection.html</a></div></div><div style="background-color: white;"><p style="color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0.75em 0px 0px; position: relative;"><span style="font-size: small;"><b>Raspberry pi OpenVINO with Intel Movidius ( Neural Compute Stick )</b></span></p></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); background-color: white; color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"></span></p><div style="background-color: white;"><a href="http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html" style="color: #2288bb; text-decoration-line: none;" target="_blank">http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html</a></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); background-color: white; color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); background-color: white; color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;">Install OpenVINO™ toolkit for Raspbian* OS</span><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;">
</span><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;"><a href="https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html" style="color: #2288bb; text-decoration-line: none;">https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html</a></span></span></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); background-color: white; color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><br /></span></p><div style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background: transparent; clear: left; color: #2196f3; font-family: Roboto, sans-serif; margin-bottom: 1em; margin-left: 1em; text-align: center; text-decoration-line: none;"><img border="0" data-original-height="641" data-original-width="860" height="149" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/w200-h149/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; box-shadow: rgba(0, 0, 0, 0.1) 1px 1px 5px; height: inherit; max-width: 100%; padding: 5px; position: relative;" width="200" /></a> </div><div style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Adun Nantakaew อดุลย์ นันทะแก้ว 081-6452400 </div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> LINE : adunnan</div><div style="background-color: white; color: #757575; font-family: Roboto, sans-serif; font-size: 15px;"><span style="font-family: arial;"><span style="color: #050505;"><span style="white-space: pre-wrap;"> FaceBook : <a href="https://www.facebook.com/adun.nantakaew/" style="color: #2288bb; text-decoration-line: none;">https://www.facebook.com/adun.nantakaew/</a></span></span></span></div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Youtube : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg?fbclid=IwAR0ZBdO15bxb1phy-1VQXXGYCpxEkwZKFvFOIOA0xs9YEpnBXzHCcypgb5E" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg</a></span></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); background-color: white; color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"></span></p><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Web Blog : <a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://raspberrypi4u.blogspot.com/?fbclid=IwAR2f4r8kFnbz_dheZrpr3drRRWD4R0PpL8uG7kKDNYRPR7Mvlg2V8mHg9dE" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">http://raspberrypi4u.blogspot.com/</a></div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Website : <a href="https://softpower.tech">https://softpower.tech</a></div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"><br /></div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"><br /></div><div dir="auto" style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"><br /></div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-59141669027429132342022-08-02T21:18:00.005-07:002023-05-09T02:41:52.693-07:00Raspberry pi YOLO Object detection with Intel Neural compute stick and OpenVINO<h1 style="text-align: center;"><span style="color: #ff00fe;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/ehb55UM2f1I" title="YouTube video player" width="560"></iframe></span></h1><h1 style="text-align: left;"><span style="color: #ff00fe;">Raspberry pi YOLO Object detection </span><span style="color: #666666;">with</span><span style="color: #ff00fe;"> </span><span style="color: #2b00fe;">Intel Neural compute stick and OpenVINO </span></h1><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjhW71vV-gCYX-2waqJyVdVIoJSG0LYnkbLSt5DEu8Vikd8x509KKyjZgQSMnvtNuTpsfxaIp7iarqLHc6eOz-t9LRriR8He6pu9BpsRnSGlin0iHYJD_osgdys94QeBohpcQlUHD0K_kmRNFn7h_BTMRgKST680WV88GbcsfbnEXUsWL5uNQwDG7nJyA/s1200/raspi4_intel_neural-compute_stick.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="900" data-original-width="1200" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjhW71vV-gCYX-2waqJyVdVIoJSG0LYnkbLSt5DEu8Vikd8x509KKyjZgQSMnvtNuTpsfxaIp7iarqLHc6eOz-t9LRriR8He6pu9BpsRnSGlin0iHYJD_osgdys94QeBohpcQlUHD0K_kmRNFn7h_BTMRgKST680WV88GbcsfbnEXUsWL5uNQwDG7nJyA/s320/raspi4_intel_neural-compute_stick.jpg" width="320" /></a></div><p><span style="background-color: white;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d;"><span style="font-size: 15px; white-space: pre-wrap;">Hardware
· Raspberry Pi Board (4B )
· Intel Neural Compute Stick 2
· SD Card 32GB
· 5V DC. 2A Power Supply
Software
· OS Raspbian 10 ( Buster )
· Python 3.7.3
· <b>OpenVINO Toolkit 2020.3</b>
· OpenCV 4.0.0</span></span></span></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgZ2eQKWjlPb-gd3govmHoK1SEeyh9X1WQX_b-aC2JQXv01ShF7bZ_Q82us8x5hNDxZQgyGWsvLpuPK6N_bw6_h6yY8hM7b2rUb4u2i8xW7PsdmV_V5bvlLJ1qNFWdpta1xHctmvEJqJXz2qb-fYqa_9_QnmGjAtWvhoTWUtTowhXA64puALWqUxrEMJw/s830/yolo-object-detction.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="289" data-original-width="830" height="222" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgZ2eQKWjlPb-gd3govmHoK1SEeyh9X1WQX_b-aC2JQXv01ShF7bZ_Q82us8x5hNDxZQgyGWsvLpuPK6N_bw6_h6yY8hM7b2rUb4u2i8xW7PsdmV_V5bvlLJ1qNFWdpta1xHctmvEJqJXz2qb-fYqa_9_QnmGjAtWvhoTWUtTowhXA64puALWqUxrEMJw/w640-h222/yolo-object-detction.png" width="640" /></a></div><h2 style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 22px; margin: 0px; position: relative;"><span style="color: #2b00fe;">What is a YOLO object detector?</span></h2><p style="background-color: white; box-sizing: inherit; color: #051e50; font-family: proxima-nova, sans-serif; font-size: 13.2px; margin: 24px 0px; max-width: 100%; padding: 0px;">When it comes to deep learning-based object detection, there are three primary object detectors you’ll encounter:</p><ul style="background-color: white; box-sizing: inherit; color: #051e50; font-family: proxima-nova, sans-serif; font-size: 13.2px; line-height: 1.4; margin: 24px 0px 30px 24px; max-width: 100%; padding: 0px;"><li style="box-sizing: inherit; list-style-type: disc; margin: 0px 0px 15px; padding: 0px;">R-CNN and their variants, including the original R-CNN, Fast R- CNN, and Faster R-CNN</li><li style="box-sizing: inherit; list-style-type: disc; margin: 0px 0px 15px; padding: 0px;">Single Shot Detector (SSDs)</li><li style="box-sizing: inherit; list-style-type: disc; margin: 0px 0px 15px; padding: 0px;">YOLO</li></ul><div style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"><span face="proxima-nova, sans-serif" style="color: #051e50;">First introduced in 2015 by Redmon et al., their paper, </span><a href="https://arxiv.org/abs/1506.02640" rel="noopener noreferrer" style="border-bottom: 1px solid rgb(22, 159, 230); box-sizing: inherit; color: #169fe6; font-family: proxima-nova, sans-serif; font-weight: 700; text-decoration-line: none; transition: all 0.2s ease-in-out 0s;" target="_blank"><em style="box-sizing: inherit;">You Only Look Once: Unified, Real-Time Object Detection</em></a><span face="proxima-nova, sans-serif" style="color: #051e50;">, details an object detector capable of super real-time object detection, obtaining </span><span face="proxima-nova, sans-serif" style="box-sizing: inherit; color: #051e50; font-weight: bolder;">45 FPS</span><span face="proxima-nova, sans-serif" style="color: #051e50;"> on a GPU.</span></div><div style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"><span face="proxima-nova, sans-serif" style="color: #051e50;"><br /></span></div><div style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif;"><p class="p2" style="font-size: 13.2px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><b>You Only Look Once: Unified, Real-Time Object Detection</b></p><p class="p2" style="font-size: 13.2px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><a href="https://arxiv.org/pdf/1506.02640v3.pdf" style="color: #2288bb; text-decoration-line: none;">https://arxiv.org/pdf/1506.02640v3.pdf</a></p><p class="p2" style="font-size: 13.2px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><div style="font-size: 13.2px;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEisYYMgdQX01zdDQJ23jqFVZ_Hzjtors-bDEbcxnz2rf8A5bB2wvPPJbuy7O0CvmDR4d1tv7bR3gllWxDw1rKUmBidajH1jGScu7J-WgGqh8NVUf_BbO4QMdjGyn0-PFk1-aqwOXPp4dgBpw7f1U9B6xrRRyylQ0Jn5l-EQpvfStK1Ak3K2r3OpboEsrg/s735/yolov3-compare.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="452" data-original-width="735" height="394" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEisYYMgdQX01zdDQJ23jqFVZ_Hzjtors-bDEbcxnz2rf8A5bB2wvPPJbuy7O0CvmDR4d1tv7bR3gllWxDw1rKUmBidajH1jGScu7J-WgGqh8NVUf_BbO4QMdjGyn0-PFk1-aqwOXPp4dgBpw7f1U9B6xrRRyylQ0Jn5l-EQpvfStK1Ak3K2r3OpboEsrg/w640-h394/yolov3-compare.png" width="640" /></a></div><p style="box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 16px;">YOLOv3 improved on the YOLOv2 paper and both Joseph Redmon and Ali Farhadi, the original authors, contributed.<br style="box-sizing: inherit;" />Together they published <a href="https://arxiv.org/abs/1804.02767v1" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; color: #2288bb; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">YOLOv3: An Incremental Improvement</a></p><p style="box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 16px;">The original YOLO papers were are hosted <a href="https://pjreddie.com/darknet/yolo/" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; color: #2288bb; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">here</a></p><p style="box-sizing: inherit; color: rgba(0, 0, 0, 0.87); font-family: Roboto, -apple-system, "system-ui", Helvetica, Arial, sans-serif; font-size: 16px;"><strong style="box-sizing: inherit;">Author:</strong> <a href="https://pjreddie.com/" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; color: #2288bb; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">Joseph Redmon</a> and <a href="https://www.cs.washington.edu/people/faculty/ali" style="-webkit-tap-highlight-color: transparent; box-sizing: inherit; color: #2288bb; text-decoration-line: none; transition: color 125ms ease 0s; word-break: break-word;">Ali Farhadi</a><br style="box-sizing: inherit;" /><strong style="box-sizing: inherit;">Released:</strong> 8 Apr 2018</p></div><div><p style="box-sizing: inherit; color: #051e50; font-family: proxima-nova, sans-serif; font-size: 13.2px; margin: 24px 0px; max-width: 100%; padding: 0px;">We’ll be using YOLOv3 in this blog post, in particular, YOLO trained on the COCO dataset.</p><p style="box-sizing: inherit; color: #051e50; font-family: proxima-nova, sans-serif; font-size: 13.2px; margin: 24px 0px; max-width: 100%; padding: 0px;">The COCO dataset consists of 80 labels.</p><h2 style="font-size: 22px; margin: 0px; position: relative;">YOLOv3-416</h2><div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;">Video Inference Performance</span><span class="Apple-converted-space"> </span>: <span class="Apple-converted-space"> 3</span> FPS.</p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><br /></span></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/WEG9I5ImCf0" title="YouTube video player" width="560"></iframe></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><br /></span></p><h2 style="font-size: 22px; margin: 0px; position: relative;">YOLOv3-tiny-416</h2><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"></span></p><div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;">Video Inference Performance</span><span class="Apple-converted-space"> </span>: <span class="Apple-converted-space"> 7</span> FPS.</p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/ehb55UM2f1I" title="YouTube video player" width="560"></iframe></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><h2 style="color: #0c0c0c; font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: left;"><span style="font-size: large;">Compare Performance</span></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjVVU9ND68wWoSb0JsneLm_ZFVJKjMhuJ8_Wy7ikcNoBibTSY_kt1phcwWgfDrvBOag6g3hZkQRLUoD0HZwHUW5X3oBEENx-RfYTHvfZhJVyFBKRlcxLcr-wC0z-Dn8eeVLS_Xzr5kTcS6U6FaJtELekMTxQqGj0bliRPOShKxZgF-6Je2wvrjr5fg-pw/s915/raspberrypi-yolo.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="290" data-original-width="915" height="202" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjVVU9ND68wWoSb0JsneLm_ZFVJKjMhuJ8_Wy7ikcNoBibTSY_kt1phcwWgfDrvBOag6g3hZkQRLUoD0HZwHUW5X3oBEENx-RfYTHvfZhJVyFBKRlcxLcr-wC0z-Dn8eeVLS_Xzr5kTcS6U6FaJtELekMTxQqGj0bliRPOShKxZgF-6Je2wvrjr5fg-pw/w640-h202/raspberrypi-yolo.png" width="640" /></a></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"></p><div class="separator" style="clear: both; text-align: center;"><br /></div><p></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span style="color: black; font-family: Times; font-size: 13.2px;"><br /></span></p><h2 style="color: #0c0c0c; font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: left;"><span style="color: black; font-family: Times;">Reference</span></h2></div><div style="color: black; font-family: Times; font-size: medium;"><p style="color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0.75em 0px 0px; position: relative;"><span style="font-size: small;"><b>Raspberry pi OpenVINO with Intel Movidius ( Neural Compute Stick )</b></span></p></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"></span></p><div style="color: black; font-family: Times; font-size: medium;"><a href="http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html" target="_blank">http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html</a></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;">Install OpenVINO™ toolkit for Raspbian* OS</span><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;">
</span><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d; white-space: pre-wrap;"><a href="https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html">https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html</a></span></span></p><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"><br /></span></p><div style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background: transparent; clear: left; color: #2196f3; font-family: Roboto, sans-serif; margin-bottom: 1em; margin-left: 1em; text-align: center; text-decoration-line: none;"><img border="0" data-original-height="641" data-original-width="860" height="149" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/w200-h149/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; box-shadow: rgba(0, 0, 0, 0.1) 1px 1px 5px; height: inherit; max-width: 100%; padding: 5px; position: relative;" width="200" /></a> </div><div style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Adun Nantakaew อดุลย์ นันทะแก้ว 081-6452400 </div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> LINE : adunnan</div><div style="color: #757575; font-family: Roboto, sans-serif; font-size: 15px;"><span style="font-family: arial;"><span style="color: #050505;"><span style="white-space: pre-wrap;"> FaceBook : <a href="https://www.facebook.com/adun.nantakaew/">https://www.facebook.com/adun.nantakaew/</a></span></span></span></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Youtube : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg?fbclid=IwAR0ZBdO15bxb1phy-1VQXXGYCpxEkwZKFvFOIOA0xs9YEpnBXzHCcypgb5E" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg</a></span></div><p class="p1" style="-webkit-text-stroke-color: rgb(12, 12, 12); color: #0c0c0c; font-family: Helvetica; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span class="s1" style="font-kerning: none;"></span></p><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Web Blog : <span><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://raspberrypi4u.blogspot.com/?fbclid=IwAR2f4r8kFnbz_dheZrpr3drRRWD4R0PpL8uG7kKDNYRPR7Mvlg2V8mHg9dE" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">http://raspberrypi4u.blogspot.com/</a></span></div></div></div><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;"> Website : <a href="https://softpower.tech">https://softpower.tech</a></div></div>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-11092301347719087112022-07-15T06:30:00.015-07:002023-05-09T02:42:15.104-07:00Raspberry pi 4B Object Detection with Intel Neural Compute Stick and OpenVINO<div style="text-align: center;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/kHG156Ga_Xc" title="YouTube video player" width="560"></iframe></div><h1 style="text-align: left;"><span style="color: #ff00fe;">Raspberry pi Object Detection with Intel Neural Compute Stick and OpenVINO</span></h1><p><span face="roboto, helvetica, sans-serif" style="background-color: white; color: #4a4a4a; font-size: 15px;">This project showcases Object Detection on edge device.</span></p><p><span face="roboto, helvetica, sans-serif" style="background-color: white; color: #4a4a4a; font-size: 15px;">We use Raspberry pi 4B board with Intel NCS ( Neural Compute Stick ) and OpenVINO Library and Source code from Intel AI.</span></p><p><span face="roboto, helvetica, sans-serif" style="background-color: white; color: #4a4a4a; font-size: 15px;"></span></p><div class="separator" style="clear: both; text-align: center;"><span face="roboto, helvetica, sans-serif" style="background-color: white; color: #4a4a4a; font-size: 15px;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEh7HTAzoGtehYt7LWWLxUL6vHtoJAFhNyCVfeyWocFKdYaOtXSG7MVCb3C0DClYiJ940dkgFC1eFrQSi0viy4sHcm3pnqtQN5Lt4lCl2DIfBoswAo6Z7-TCvX733dD523Q80w01utvMp5f5RkexO3oIDpiJshCl36jiBEa3Qex0ZUW8gJFbMWeA-VNkIw" style="margin-left: 1em; margin-right: 1em;"><img alt="" data-original-height="500" data-original-width="500" height="240" src="https://blogger.googleusercontent.com/img/a/AVvXsEh7HTAzoGtehYt7LWWLxUL6vHtoJAFhNyCVfeyWocFKdYaOtXSG7MVCb3C0DClYiJ940dkgFC1eFrQSi0viy4sHcm3pnqtQN5Lt4lCl2DIfBoswAo6Z7-TCvX733dD523Q80w01utvMp5f5RkexO3oIDpiJshCl36jiBEa3Qex0ZUW8gJFbMWeA-VNkIw" width="240" /></a> <a href="https://blogger.googleusercontent.com/img/a/AVvXsEjFcYEHRLBiXetL8ZR03_AR9cuzhIbpQOagfD7s9PoevUQBzJlt3H1YuFSdNNPNxCGWVVSh3Jgu41kqKmv0nH0Xm47Krgxl7gT8OtUheMYCoSR7MldKlWPYzIXQAdCDHMSmZ_yKIf6Ba0Tgm26Ao5HKIeNiYIOHACgL334Ih9NhhxhT7oAgmjZX2eaeQA" style="margin-left: 1em; margin-right: 1em;"><img alt="" data-original-height="726" data-original-width="1130" height="206" src="https://blogger.googleusercontent.com/img/a/AVvXsEjFcYEHRLBiXetL8ZR03_AR9cuzhIbpQOagfD7s9PoevUQBzJlt3H1YuFSdNNPNxCGWVVSh3Jgu41kqKmv0nH0Xm47Krgxl7gT8OtUheMYCoSR7MldKlWPYzIXQAdCDHMSmZ_yKIf6Ba0Tgm26Ao5HKIeNiYIOHACgL334Ih9NhhxhT7oAgmjZX2eaeQA" width="320" /></a><br /></span></div><p></p><h4 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px; margin: 0px; position: relative;"><b>Hardware</b></h4><p><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· Raspberry Pi Board (4B )</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· Intel Neural Compute Stick 2</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· SD Card 32GB</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· 5V DC. 2A Power Supply</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /></p><h4 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px; margin: 0px; position: relative;"><b>Software</b></h4><p><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· OS Raspbien 10 ( Buster )</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· Python 3.7.3</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· OpenVINO Toolkit 2019.R3</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">· OpenCV 4.0.0</span><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /><span face=""Trebuchet MS", Trebuchet, Verdana, sans-serif" style="background-color: white; color: #666666; font-size: 13.2px;">Machine Learning Object Detection Model : <b>Mobilenet SSD V2</b></span></p><h2 style="text-align: left;"><span style="color: #ff00fe;">Run Python Code </span><span style="font-weight: normal;"><span style="color: #444444;">( Async Mode )</span></span></h2><div><span face="sans-serif" style="background-color: white; color: #333333; font-size: 16px;">Async API usage can improve overall frame-rate of the application, because rather than wait for inference to complete, the app can continue doing things on the host, while accelerator is busy.</span></div><div><p style="background-color: white; box-sizing: border-box; color: #333333; font-family: sans-serif; font-size: 16px; margin-bottom: 1.15rem; margin-top: 0px;">This and other performance implications and tips for the Async API are covered in the <a class="reference external" href="https://docs.openvino.ai/latest/_docs_optimization_guide_dldt_optimization_guide.html" style="background-color: transparent; box-sizing: border-box; text-decoration-line: none;">Optimization Guide</a>.</p><p style="background-color: white; box-sizing: border-box; color: #333333; font-family: sans-serif; font-size: 16px; margin-bottom: 1.15rem; margin-top: 0px;">Other demo objectives are:</p><ul class="simple" style="background-color: white; box-sizing: border-box; color: #333333; font-family: sans-serif; font-size: 16px; margin-bottom: 1rem; margin-top: 0px;"><li style="box-sizing: border-box;"><p style="box-sizing: border-box; color: rgba(var(--pst-color-paragraph),1); font-size: 1em; margin-bottom: 0px; margin-top: 0px;">Video as input support via OpenCV*</p></li><li style="box-sizing: border-box;"><p style="box-sizing: border-box; color: rgba(var(--pst-color-paragraph),1); font-size: 1em; margin-bottom: 0px; margin-top: 0px;">Visualization of the resulting bounding boxes and text labels (from the <code class="docutils literal notranslate" style="box-sizing: border-box; color: rgb(var(--ost-color-primary)); font-family: var(--pst-font-family-monospace); font-size: 14px; overflow-wrap: break-word;"><span class="pre" style="box-sizing: border-box; hyphens: none;">.labels</span></code> file) or class number (if no file is provided)</p></li></ul></div><p></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEinC8GED7JmQjAWX0eUyfY1cwJq0NyMpYISsGKC9_CTaZdlwknQOlfr48x522yVv__BCakIZ6VUn3x6Hp9FFtMBChjSHykQZuT8vqmE1r0KfSmhiKfBZ_0p2_8jJiV0R8N32NqQB-jOaNptqGBNXVE7Z4AWYeFpMZN4ExD4f9JQwszyI3BKioDjc1nMtQ" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="693" data-original-width="927" height="478" src="https://blogger.googleusercontent.com/img/a/AVvXsEinC8GED7JmQjAWX0eUyfY1cwJq0NyMpYISsGKC9_CTaZdlwknQOlfr48x522yVv__BCakIZ6VUn3x6Hp9FFtMBChjSHykQZuT8vqmE1r0KfSmhiKfBZ_0p2_8jJiV0R8N32NqQB-jOaNptqGBNXVE7Z4AWYeFpMZN4ExD4f9JQwszyI3BKioDjc1nMtQ=w640-h478" width="640" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhIla9s-qgT4LXeMQmcWQSfzfx8wV95rSB5C4xMusUaV_oRSEfkEZtttRNto5Q1SGksZe2ELurVWP7axVpBzsIu3zpyMzoU35KO8qsNsI3pA9zSbgiZvqnYjIYKRX5FcBQXbg5Ap13XWvGIM5VSyErYSWDtIvm3lFgkkxCWfnsu-Ekb5QuX-gPzn8Xsmg" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="711" data-original-width="953" height="478" src="https://blogger.googleusercontent.com/img/a/AVvXsEhIla9s-qgT4LXeMQmcWQSfzfx8wV95rSB5C4xMusUaV_oRSEfkEZtttRNto5Q1SGksZe2ELurVWP7axVpBzsIu3zpyMzoU35KO8qsNsI3pA9zSbgiZvqnYjIYKRX5FcBQXbg5Ap13XWvGIM5VSyErYSWDtIvm3lFgkkxCWfnsu-Ekb5QuX-gPzn8Xsmg=w640-h478" width="640" /></a></div><br />Video Test : 960x540 pixels<p></p><p><b>Total frame : 301 frames</b></p><p><b>Total Inference time : 12.44 sec</b></p><p><b>Average performance : <span style="color: #ff00fe; font-size: medium;">24.20 fps</span></b></p>
<h2><span style="color: #ff00fe;">Run Python Code </span><span style="font-weight: normal;"><span style="color: #444444;">( Sync Mode )</span></span></h2>
<div style="text-align: center;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/Sd4r9YmxSPs" title="YouTube video player" width="560"></iframe></div><div style="text-align: center;"><br /></div>
<div><span style="color: #ff00fe;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEj38nOg5ZimkhYVP8Hk7pR-useohw-SBUGt8I-3jo339yDP8HobkuNwkMk4enmk23lWxSLBLzwy2JTEsu-LFVpVZfQM8RAY6TG6TiJ15mH2dBb-XjIF1jP7JXiY-dEe-PSaNogFDMTsg9-YsfczGHA7_V1ALFSy8lrxG_rtUekjGWDZFMgqd_Mna5I6hw" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="873" data-original-width="1413" height="248" src="https://blogger.googleusercontent.com/img/a/AVvXsEj38nOg5ZimkhYVP8Hk7pR-useohw-SBUGt8I-3jo339yDP8HobkuNwkMk4enmk23lWxSLBLzwy2JTEsu-LFVpVZfQM8RAY6TG6TiJ15mH2dBb-XjIF1jP7JXiY-dEe-PSaNogFDMTsg9-YsfczGHA7_V1ALFSy8lrxG_rtUekjGWDZFMgqd_Mna5I6hw=w400-h248" width="400" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEisPKuoFhgm_LWy0gh3Yc37tqRW3Xza3ne1xJpUyXqTDJj1Zg5eYAGLY--y-W6hACOARJzANZiGWdR6W-ztTMB6L-5VrBIwbKqbM56pDXiyL4aQj9Q83VqzRJLXfCdFS9iOux3nWnTvOc12pOzVchj672dkOoF-RDngJ0NS_DEOngS3KSr6tFiwgPXjGQ" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="869" data-original-width="1241" height="280" src="https://blogger.googleusercontent.com/img/a/AVvXsEisPKuoFhgm_LWy0gh3Yc37tqRW3Xza3ne1xJpUyXqTDJj1Zg5eYAGLY--y-W6hACOARJzANZiGWdR6W-ztTMB6L-5VrBIwbKqbM56pDXiyL4aQj9Q83VqzRJLXfCdFS9iOux3nWnTvOc12pOzVchj672dkOoF-RDngJ0NS_DEOngS3KSr6tFiwgPXjGQ=w400-h280" width="400" /></a></div><br /></div><br /></span></div><div>Video Test : 960x540 pixels<p></p><p><b>Total frame : 301 frames</b></p><p><b>Total Inference time : 24.96 sec</b></p><p><b>Average performance : <span style="color: #ff00fe; font-size: medium;">12<span>.06 fps</span></span></b></p></div><h2 style="text-align: left;"><span style="font-size: small;"><br /></span></h2><h2 style="text-align: left;"><span style="font-size: small;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEgNv1wdmEaCRoiS17m4iVY-IOz0g_gVd4m1Px2jpX8j2AaGgggrcfP2XPRAdfe31eHUFsJrUGbSqQHtYtTXhvTg3wHN0PeiR5sB9m0Mlyp1EIT8WZun7MlQAL67ixvKK7bOJkvSQg5IeVrVt8jX2frTvcPcwvcLAGPrwznbjJKJ_3J0j9eKLlFCtz5HGg" style="margin-left: 1em; margin-right: 1em;"><img alt="" data-original-height="119" data-original-width="584" height="65" src="https://blogger.googleusercontent.com/img/a/AVvXsEgNv1wdmEaCRoiS17m4iVY-IOz0g_gVd4m1Px2jpX8j2AaGgggrcfP2XPRAdfe31eHUFsJrUGbSqQHtYtTXhvTg3wHN0PeiR5sB9m0Mlyp1EIT8WZun7MlQAL67ixvKK7bOJkvSQg5IeVrVt8jX2frTvcPcwvcLAGPrwznbjJKJ_3J0j9eKLlFCtz5HGg" width="320" /></a></div></span></h2><h2 style="text-align: left;"><span style="font-size: small;">OpenVINO Toolkit</span></h2><div><span style="font-size: small;">Now We try to use OpenVINO 2020.3 compare with OpenVINO 2019 R3.</span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;">OpenVINO 2020.3 frame rate is a little bit lower than OpenVINO 2019 R3.</span></div><div><span style="font-size: small;"><br /></span></div><div style="text-align: center;">
<iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/1vabCtxp298" title="YouTube video player" width="560"></iframe>
<span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><h2 style="text-align: left;">Comparison</h2><div><b><span style="font-size: medium;">Async vs Sync Mode</span></b></div><div style="text-align: center;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/qhmE80dR-dQ" title="YouTube video player" width="560"></iframe></div><div><span style="font-size: small;"><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjSSnjo0U8oIGNTjSZ29wgs8z3BK64KKkeXwYuMqYd_mj7J9hhm6zPNDriRBDegUsWPvvSkSZeN4vX5WSDSGDHbKvrvhQbfN1FC1R6n-Iu6AbC7U4Lx_zd6Ddzt07gLxN5zx6oY6hlyfS010lbLAkRYRkJNFRIWlwu6qkql_Ie3FdARlG4zmuUXNCMDVQ/s1016/Raspberrypi-object-detection-intel-neuralcomputestick-compare.png" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="262" data-original-width="1016" height="166" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjSSnjo0U8oIGNTjSZ29wgs8z3BK64KKkeXwYuMqYd_mj7J9hhm6zPNDriRBDegUsWPvvSkSZeN4vX5WSDSGDHbKvrvhQbfN1FC1R6n-Iu6AbC7U4Lx_zd6Ddzt07gLxN5zx6oY6hlyfS010lbLAkRYRkJNFRIWlwu6qkql_Ie3FdARlG4zmuUXNCMDVQ/w640-h166/Raspberrypi-object-detection-intel-neuralcomputestick-compare.png" width="640" /></a></div><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;"><br /></span></div><div><span style="font-size: small;">This is my experiment may something was wrong.</span></div><div><span style="font-size: small;"><br /></span></div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjgJijuUYKHm7zyj5Ws65BWXVe12BnggEH8xJE7nN2hqPTDDo9JEyzcvBb4Uf6vCeICBrpdhNZNU1ZVOj06-haZBZ6BuTh4eYwGm2uoiCt3sSQu9fe-BsrndaPElD-wd2YUW6HGSAtMj9iNWLLjqjHp6N3SD6qTCzuagnLLcwmXlv-hC8LOBKzZ2hUq7w/s406/youtube.png" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="124" data-original-width="406" height="98" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjgJijuUYKHm7zyj5Ws65BWXVe12BnggEH8xJE7nN2hqPTDDo9JEyzcvBb4Uf6vCeICBrpdhNZNU1ZVOj06-haZBZ6BuTh4eYwGm2uoiCt3sSQu9fe-BsrndaPElD-wd2YUW6HGSAtMj9iNWLLjqjHp6N3SD6qTCzuagnLLcwmXlv-hC8LOBKzZ2hUq7w/s320/youtube.png" width="320" /></a></div><div><br /></div><h3 style="text-align: left;"><b><br /></b></h3><div><b><br /></b></div><h3 style="text-align: left;"><b><br /></b></h3><div><b><br /></b></div><h3 style="text-align: left;"><b><br /></b></h3><h3 style="text-align: left;"><b><br /></b></h3><h3 style="text-align: left;"><b>YouTube Video</b></h3><div><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Raspberry pi Object Detection with Intel Neural Compute Stick and <b>OpenVINO ( 2020.3 )</b></span></div><div><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d;"><a href="https://youtu.be/1vabCtxp298">https://youtu.be/1vabCtxp298</a></span></span></div><div><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><br /></span></div><div><b><span style="color: #ff00fe;">Compare Raspberry pi Object Detection Intel NCS</span></b> <b><span style="color: #0b5394;">( Async vs. Sync mode )</span></b></div><div><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><a href="https://youtu.be/qhmE80dR-dQ">https://youtu.be/qhmE80dR-dQ</a></span></div><div><b><br /></b></div><div><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Raspberry pi Object Detection with Intel Neural Compute Stick ( Sync mode )</span></div><div><a href="https://youtu.be/Sd4r9YmxSPs">https://youtu.be/Sd4r9YmxSPs</a></div><div><b><br /></b></div><div><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Raspberry pi Object Detection with Intel Neural Compute Stick ( Async mode )</span></div><div><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d;"><a href="https://youtu.be/kHG156Ga_Xc">https://youtu.be/kHG156Ga_Xc</a></span></span></div><div><b><br /></b></div><div><b><span style="color: #ff00fe;">Compare Raspberry pi Object Detection</span></b> <b><span style="color: #ffa400;">( TensorFlow vs. TensorFlow-lite ) </span></b></div><div><a href="https://youtu.be/qCYngmeAkqQ">https://youtu.be/qCYngmeAkqQ</a></div><div><b><br /></b></div><div><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Raspberry pi Object Detection with TensorFlow-lite ( INT8 )</span></div><div><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d;"><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><a href="https://youtu.be/7TLjkfXVwoI">https://youtu.be/7TLjkfXVwoI</a></span></span></div><div><br /></div><div><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Raspberry pi Object Detection with TensorFlow ( FP32 )</span></div><div><span style="background-color: white; font-size: 15px; white-space: pre-wrap;"><span face="Roboto, Noto, sans-serif" style="color: #0d0d0d;"><a href="https://youtu.be/m3ffxON6qlo">https://youtu.be/m3ffxON6qlo</a></span></span></div><div><br /></div><h2 style="text-align: left;">Reference</h2><div><p style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0.75em 0px 0px; position: relative; text-align: left;"><span style="font-size: small;"><b>Raspberry pi OpenVINO with Intel Movidius ( Neural Compute Stick )</b></span></p></div><div><a href="http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html" target="_blank">http://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html</a></div><div><span style="font-size: xx-small;"> </span></div><p><span face="roboto, helvetica, sans-serif" style="background-color: white; color: #2171b8;"><b>Install OpenVINO™ toolkit for Raspbian* OS</b></span></p><p><a href="https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html" target="_blank">https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_raspbian.html</a></p><p style="background-color: white; box-sizing: border-box; font-family: sans-serif; font-weight: 400; line-height: 1.15; margin: 0px 0px 1.05rem; text-align: left;">Object Detection Python* Demo</p><p><a href="https://docs.openvino.ai/latest/omz_demos_object_detection_demo_python.html" target="_blank">https://docs.openvino.ai/latest/omz_demos_object_detection_demo_python.html</a></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><b>Model</b><span class="Apple-converted-space"><b> </b>( SSD MobileNet )</span></p><p class="p2" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; min-height: 14px;"><br /></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><a href="https://docs.openvino.ai/latest/omz_models_model_ssd_mobilenet_v1_coco.html">https://docs.openvino.ai/latest/omz_models_model_ssd_mobilenet_v1_coco.html</a></p><p class="p2" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; min-height: 14px;"><br /></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><a href="https://docs.openvino.ai/latest/omz_models_model_ssdlite_mobilenet_v2.html">https://docs.openvino.ai/latest/omz_models_model_ssdlite_mobilenet_v2.html</a></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><b>OpenVINO Optimization</b></p><p class="p1" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><br /></p><p class="p1" style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span style="font-family: Helvetica;"><span style="font-size: 12px;"><a href="https://docs.openvino.ai/latest/openvino_docs_optimization_guide_dldt_optimization_guide.html">https://docs.openvino.ai/latest/openvino_docs_optimization_guide_dldt_optimization_guide.html</a></span></span></p><p class="p1" style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span style="font-family: Helvetica;"><br /></span></p><p class="p1" style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span style="font-family: Helvetica;"><br /></span></p><div style="background-color: white; color: #757575; font-family: Roboto, sans-serif; font-size: 15px;"><div dir="auto" style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space: pre-wrap;"><div style="text-align: left;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/s860/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background: transparent; clear: left; color: #2196f3; font-family: Roboto, sans-serif; margin-bottom: 1em; margin-left: 1em; text-align: center; text-decoration-line: none;"><img border="0" data-original-height="641" data-original-width="860" height="149" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilX9Gd83Sm5mjudpuAaPIJS5KKi7qvj30ugjeSZSSne8czhvYspous7J3Fenf6cSsnWulOdNI4YzjK6Q60BBcVBMdlLVfDIbMIVHPAYmw-FTlYOk3Vdp2IuWnC_RHaVK7SQN0QNWCj9FZf/w200-h149/269-2697881_computer-icons-user-clip-art-transparent-png-icon.png" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; box-shadow: rgba(0, 0, 0, 0.1) 1px 1px 5px; height: inherit; max-width: 100%; padding: 5px; position: relative;" width="200" /></a> </div><div style="text-align: left;"> Adun Nantakaew อดุลย์ นันทะแก้ว 081-6452400 </div><div dir="auto"> LINE : adunnan</div><div style="color: #757575; font-family: Roboto, sans-serif; white-space: normal;"><span style="font-family: arial;"><span style="color: #050505;"><span style="white-space: pre-wrap;"> FaceBook : <a href="https://www.facebook.com/adun.nantakaew/">https://www.facebook.com/adun.nantakaew/</a></span></span></span></div><div dir="auto"> Youtube : <span style="font-family: inherit;"><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg?fbclid=IwAR0ZBdO15bxb1phy-1VQXXGYCpxEkwZKFvFOIOA0xs9YEpnBXzHCcypgb5E" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">https://www.youtube.com/channel/UCw3VVy4wOsb8a0a1YYqJAPg</a></span></div><div dir="auto"> Web Blog : <span><a class="oajrlxb2 g5ia77u1 qu0x051f esr5mh6w e9989ue4 r7d6kgcz rq0escxv nhd2j8a9 nc684nl6 p7hjln8o kvgmc6g5 cxmmr5t8 oygrvhab hcukyx3x jb3vyjys rz4wbd8a qt6c0cv9 a8nywdso i1ao9s8h esuyzwwr f1sip0of lzcic4wl py34i1dx gpro0wi8" href="https://raspberrypi4u.blogspot.com/?fbclid=IwAR2f4r8kFnbz_dheZrpr3drRRWD4R0PpL8uG7kKDNYRPR7Mvlg2V8mHg9dE" rel="nofollow noopener" role="link" style="-webkit-tap-highlight-color: transparent; background: transparent; border-color: initial; border-style: initial; border-width: 0px; box-sizing: border-box; color: #2196f3; cursor: pointer; display: inline; font-family: inherit; list-style: none; margin: 0px; outline: none; padding: 0px; text-align: inherit; text-decoration-line: none; touch-action: manipulation;" tabindex="0" target="_blank">http://raspberrypi4u.blogspot.com/</a></span></div><div dir="auto"> Website : <a href="https://softpower.tech">https://softpower.tech</a></div></div></div><p class="p1" style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;"><span style="font-family: Helvetica;"></span></p><p style="background-color: white; color: #222222; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13.2px;"> </p>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-22584935059533011472022-07-13T02:26:00.011-07:002023-05-09T02:42:50.632-07:00Raspberry pi 4 Object Detection with TensorFlow and TensorFlow lite<div style="text-align: center;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/qCYngmeAkqQ" title="YouTube video player" width="560"></iframe></div>
<h1 style="text-align: left;"><span style="color: #2b00fe; font-size: x-large;">Raspberry pi 4B Object Detection with TensorFlow and Tensorflow Lite Comparison</span></h1><h2 style="text-align: left;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhndjLZ31rKL_QB9kVF8FVFoae4FzMBj-R2iMK63PHh1R6uChO1B4f0vKRMVnHcrQAFtzZBxwwqQ35qNl6_z-hIMb1lluZY9GNV0jCgFWDgJevNYEx0uWM79iKUlxe2PfoMvsvZxryTiHliWMYTDiSDuQryXisCYn7kmr7nY-fvPOBpi418wh31bKUlhg" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img data-original-height="582" data-original-width="1400" height="266" src="https://blogger.googleusercontent.com/img/a/AVvXsEhndjLZ31rKL_QB9kVF8FVFoae4FzMBj-R2iMK63PHh1R6uChO1B4f0vKRMVnHcrQAFtzZBxwwqQ35qNl6_z-hIMb1lluZY9GNV0jCgFWDgJevNYEx0uWM79iKUlxe2PfoMvsvZxryTiHliWMYTDiSDuQryXisCYn7kmr7nY-fvPOBpi418wh31bKUlhg=w640-h266" width="640" /></a></div><br /><br /></h2><h2 style="text-align: left;"><span style="color: #2b00fe;"><br /></span></h2><h2 style="text-align: left;"><span style="color: #2b00fe;"><br /></span></h2><h2 style="text-align: left;"><span style="color: #2b00fe;"><br /></span></h2><h2 style="text-align: left;"><span style="color: #2b00fe;"><br /></span></h2><h2 style="text-align: left;"><span style="color: #2b00fe;"><br /></span></h2><div><span style="color: #2b00fe;"><br /></span></div><div><span style="color: #2b00fe;"><br /></span></div><div><br /></div><div><br /></div><div><br /></div><h2 style="text-align: left;"><span style="color: #2b00fe;">What is object detection?</span></h2><p><span face="Roboto, "Noto Sans", "Noto Sans JP", "Noto Sans KR", "Noto Naskh Arabic", "Noto Sans Thai", "Noto Sans Hebrew", "Noto Sans Bengali", sans-serif" style="background-color: white; color: #202124; font-size: 16px;">Given an image or a video stream, an object detection model can identify which of a known set of objects might be present and provide information about their positions within the image.</span></p><p style="background-color: white; box-sizing: inherit; color: #202124; font-family: Roboto, "Noto Sans", "Noto Sans JP", "Noto Sans KR", "Noto Naskh Arabic", "Noto Sans Thai", "Noto Sans Hebrew", "Noto Sans Bengali", sans-serif; font-size: 16px; margin: 16px 0px; padding: 0px;">An object detection model is trained to detect the presence and location of multiple classes of objects. For example, a model might be trained with images that contain various pieces of fruit, along with a <em style="box-sizing: inherit;">label</em> that specifies the class of fruit they represent (e.g. an apple, a banana, or a strawberry), and data specifying where each object appears in the image.</p><p style="background-color: white; box-sizing: inherit; color: #202124; font-family: Roboto, "Noto Sans", "Noto Sans JP", "Noto Sans KR", "Noto Naskh Arabic", "Noto Sans Thai", "Noto Sans Hebrew", "Noto Sans Bengali", sans-serif; font-size: 16px; margin: 16px 0px; padding: 0px;">When we subsequently provide an image to the model, it will output a list of the objects it detects, the location of a bounding box that contains each object, and a score that indicates the confidence that detection was correct.</p><h2 style="text-align: left;"><span style="color: #2b00fe;">Object Detection Models</span></h2><div>We use MobileNet-v2 Model.</div><div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEi5-SoYmiQNGbSMZECtuO-z2cq92K3VF1j78Y2nLnkUAdOnB8feNA7s6UbqyPmou5fiZxehWyskjUFFPzRqVRF0IIF4rTBWk-CNUXgxNKF99HWqoMVoRX6J1spuA97_MXFom6Sf0LZMwnp8zWBgyPyOrJuum6h3NVCpvL7MwGF1ympLoY870rrtEKsPcQ" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="540" data-original-width="573" height="602" src="https://blogger.googleusercontent.com/img/a/AVvXsEi5-SoYmiQNGbSMZECtuO-z2cq92K3VF1j78Y2nLnkUAdOnB8feNA7s6UbqyPmou5fiZxehWyskjUFFPzRqVRF0IIF4rTBWk-CNUXgxNKF99HWqoMVoRX6J1spuA97_MXFom6Sf0LZMwnp8zWBgyPyOrJuum6h3NVCpvL7MwGF1ympLoY870rrtEKsPcQ=w640-h602" width="640" /></a></div><br /><h2 style="text-align: left;"><span style="color: #2b00fe;">Run Object Detection Model on Raspberry pi 4B</span></h2></div><div><br /></div><div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEgbdopNl3UOM-AegmyODzgXA_s8dX8iCmW_KW9pn6zXSMKTLnhkpOKWc8R7FEEFvPANnJjKR_XNELcMTzvE0UIElOxsDr9vc_8Cj0AEjAHY22J6ejsoEJvrW60BhDSY2nePIFtJVFx5ANnT8tFkMDpQPilUisPcVCJYxFkTQzljxdTqtjlvOTSuxrwUjg" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="203" data-original-width="300" height="136" src="https://blogger.googleusercontent.com/img/a/AVvXsEgbdopNl3UOM-AegmyODzgXA_s8dX8iCmW_KW9pn6zXSMKTLnhkpOKWc8R7FEEFvPANnJjKR_XNELcMTzvE0UIElOxsDr9vc_8Cj0AEjAHY22J6ejsoEJvrW60BhDSY2nePIFtJVFx5ANnT8tFkMDpQPilUisPcVCJYxFkTQzljxdTqtjlvOTSuxrwUjg=w200-h136" width="200" /></a><a href="https://blogger.googleusercontent.com/img/a/AVvXsEjdX9J0qwKo3aYu9a35bZxcDmzmr57w174cixrGipY97P2EjgBCahFEKJtc8NXeLLG0p5-TiMQrB9TeltDD5CE2E3jr6ld-lY2k5cUCNu7x8JprBPd4tgzVnrpDfG8y9x_e17O8nYHKwTy0XHcgEa09xnx3QXFqgUMa4Mo0_xCM3RgmOn5TR2GGtpVXJA" style="clear: left; display: inline; margin-bottom: 1em; margin-right: 1em;"><img data-original-height="800" data-original-width="1170" height="137" src="https://blogger.googleusercontent.com/img/a/AVvXsEjdX9J0qwKo3aYu9a35bZxcDmzmr57w174cixrGipY97P2EjgBCahFEKJtc8NXeLLG0p5-TiMQrB9TeltDD5CE2E3jr6ld-lY2k5cUCNu7x8JprBPd4tgzVnrpDfG8y9x_e17O8nYHKwTy0XHcgEa09xnx3QXFqgUMa4Mo0_xCM3RgmOn5TR2GGtpVXJA=w200-h137" width="200" /></a></div></div><h3 style="text-align: left;"><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;"><b>TensorFlow</b></span></h3><p><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Software
• Raspberry pi Legacy OS ( Raspbian 10 , 32 bit version )
• Tensorflow 1.14.0
• OpenCV 4.0
• Python 3.7.3
Machine Learning Model : SSD Mobilenet V2 ( FP32 )</span></p><p><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Image JPG 1024x636 pixels</span></p><span face="Roboto, Noto, sans-serif" style="background-color: white; color: #0d0d0d; font-size: 15px; white-space: pre-wrap;">Video MP4 960x540 pixels</span><div><span style="color: #0d0d0d;"><span style="font-size: 15px; white-space: pre-wrap;"><br /></span></span><p></p><p><b>Result ( Image )</b></p><p></p><div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEiE41_6fbpT9MMIiaJVzKGdAAtZmxam6UlEM_KdSDaJCePBkO45JhME4G0ATqJCdW8m7qETXQdun7smgAVMY5XEp7sJFUhBD0mDzzgh1YqNYOpm5zvkaBAjEvvZ_kU5-aBndW_KOjOm097-5K8BJxzWubk3d-RDJVw6DwuEcNwZpIpml0hrNjEtfP2FxA" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="1061" data-original-width="1412" height="301" src="https://blogger.googleusercontent.com/img/a/AVvXsEiE41_6fbpT9MMIiaJVzKGdAAtZmxam6UlEM_KdSDaJCePBkO45JhME4G0ATqJCdW8m7qETXQdun7smgAVMY5XEp7sJFUhBD0mDzzgh1YqNYOpm5zvkaBAjEvvZ_kU5-aBndW_KOjOm097-5K8BJxzWubk3d-RDJVw6DwuEcNwZpIpml0hrNjEtfP2FxA=w400-h301" width="400" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEh5gHJ3YgsKQD7nxTUcjPr5gTTWqMDrgoL4Y5CN60Krq08JdbQRw8dG0Qn5gigrlauefFNvOVXgWpM7ujFtftzNe4clpjv2zOVvlKYUWjHHwSraYVA-Kby4FsN48A7jvpV6dELxRSJJpSJcJ-szXIqgSZgNeTzqQyiiTYlRSShnThHu2vHQXCXpYvJa2Q" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="654" data-original-width="922" height="284" src="https://blogger.googleusercontent.com/img/a/AVvXsEh5gHJ3YgsKQD7nxTUcjPr5gTTWqMDrgoL4Y5CN60Krq08JdbQRw8dG0Qn5gigrlauefFNvOVXgWpM7ujFtftzNe4clpjv2zOVvlKYUWjHHwSraYVA-Kby4FsN48A7jvpV6dELxRSJJpSJcJ-szXIqgSZgNeTzqQyiiTYlRSShnThHu2vHQXCXpYvJa2Q=w400-h284" width="400" /></a></div></div></div></div><p></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;">Loading time 8327.86 ms<span> </span><span> </span><span> @ test1</span></p><div class="separator" style="clear: both; text-align: center;"><div class="separator" style="clear: both;"><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Inference time 10245.02 ms</p><p class="p2" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; min-height: 14px; text-align: start;"><br /></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Loading time: 7910.86 ms<span> </span><span> </span><span> @ test2</span></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Inference time: 9650.78 ms</p><p class="p2" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; min-height: 14px; text-align: start;"><br /></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Loading time: 7917.60 ms<span> </span><span> </span><span> @ test3</span></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Inference time: 9642.02 ms</p></div><br /></div><p style="text-align: left;"><b>Result ( Video ) <span style="color: red; font-size: medium;">~ 2 fps</span></b></p><p style="text-align: center;"><b><span style="color: red; font-size: medium;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/m3ffxON6qlo" title="YouTube video player" width="560"></iframe></span></b></p><p></p><div class="separator" style="clear: both; text-align: center;"><br /></div><p></p><p><b></b></p><div class="separator" style="clear: both; text-align: center;"><b><a href="https://blogger.googleusercontent.com/img/a/AVvXsEg2MxKyR26DlKrK7Bg2N9NzA2zaug6-4JLyDBR13JVnI6JAe-Nild3OBhmJQBfKhWxVMZPvlTvl0Dn2xo2GKZ3TihR10ax_JO0CqF9LCgQUAcyLy6pPC44oAg0k8HA3Knbu1aLL-pQiL0ptcesVP8eY2eVFXJa4XUhDCvDpxmuuovmRDWjOs3fTsnRyYQ" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="649" data-original-width="923" height="281" src="https://blogger.googleusercontent.com/img/a/AVvXsEg2MxKyR26DlKrK7Bg2N9NzA2zaug6-4JLyDBR13JVnI6JAe-Nild3OBhmJQBfKhWxVMZPvlTvl0Dn2xo2GKZ3TihR10ax_JO0CqF9LCgQUAcyLy6pPC44oAg0k8HA3Knbu1aLL-pQiL0ptcesVP8eY2eVFXJa4XUhDCvDpxmuuovmRDWjOs3fTsnRyYQ=w400-h281" width="400" /></a></b></div><div class="separator" style="clear: both; text-align: center;"><b><br /></b></div><h3 style="text-align: left;"><b>TensorFlow-lite</b></h3><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEh0JAVUHRgy3360fg_MFnPjTIzM9kcPVnOy1zsYoQaw8yM_RTwzrwoPkFHff16EpluodCgTaSi7nL4aEuhK0n1ZtTrwOEPNqdFNdgEmzU2biiuCE6F34hEz0yAUXvHq24fWWeDiNpMavpACGH3uHen2xRjoCLCG1iHejklkt4MH0Ti8bt8K7vwEit0P4A" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="525" data-original-width="700" height="150" src="https://blogger.googleusercontent.com/img/a/AVvXsEh0JAVUHRgy3360fg_MFnPjTIzM9kcPVnOy1zsYoQaw8yM_RTwzrwoPkFHff16EpluodCgTaSi7nL4aEuhK0n1ZtTrwOEPNqdFNdgEmzU2biiuCE6F34hEz0yAUXvHq24fWWeDiNpMavpACGH3uHen2xRjoCLCG1iHejklkt4MH0Ti8bt8K7vwEit0P4A=w200-h150" width="200" /></a><a href="https://blogger.googleusercontent.com/img/a/AVvXsEjdX9J0qwKo3aYu9a35bZxcDmzmr57w174cixrGipY97P2EjgBCahFEKJtc8NXeLLG0p5-TiMQrB9TeltDD5CE2E3jr6ld-lY2k5cUCNu7x8JprBPd4tgzVnrpDfG8y9x_e17O8nYHKwTy0XHcgEa09xnx3QXFqgUMa4Mo0_xCM3RgmOn5TR2GGtpVXJA" style="clear: left; display: inline; margin-bottom: 1em; margin-right: 1em;"><img data-original-height="800" data-original-width="1170" height="137" src="https://blogger.googleusercontent.com/img/a/AVvXsEjdX9J0qwKo3aYu9a35bZxcDmzmr57w174cixrGipY97P2EjgBCahFEKJtc8NXeLLG0p5-TiMQrB9TeltDD5CE2E3jr6ld-lY2k5cUCNu7x8JprBPd4tgzVnrpDfG8y9x_e17O8nYHKwTy0XHcgEa09xnx3QXFqgUMa4Mo0_xCM3RgmOn5TR2GGtpVXJA=w200-h137" width="200" /></a> </div><b>Result ( image )</b><div><b><br /></b></div><div><b><br /></b><p></p><p></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhXHvRsbTF5nyAh-EubZeJHfhEXx5rBjFQUlkQLBinlgkumELIbSjKlTDyCxem_bpNFRjA5bSWf4wJJUtEziAlhJfdWszmQTq2aHo4vljrDlusA71r4R_bs3beg8XoQa6GL0X5GbnhvSnSZ0D2tCJmpoyaeyxYyGy9IJ0BjdAjBO0oH5vMaidu7p1vqHg" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="695" data-original-width="925" height="301" src="https://blogger.googleusercontent.com/img/a/AVvXsEhXHvRsbTF5nyAh-EubZeJHfhEXx5rBjFQUlkQLBinlgkumELIbSjKlTDyCxem_bpNFRjA5bSWf4wJJUtEziAlhJfdWszmQTq2aHo4vljrDlusA71r4R_bs3beg8XoQa6GL0X5GbnhvSnSZ0D2tCJmpoyaeyxYyGy9IJ0BjdAjBO0oH5vMaidu7p1vqHg=w400-h301" width="400" /></a></div><p></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px;">Loading time: 4.13 ms<span> </span><span> </span><span> @ test1</span></p><div class="separator" style="clear: both; text-align: center;"><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Inference time: 229.85 ms</p><p class="p2" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; min-height: 14px; text-align: start;"><br /></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Loading time: 4.38 ms<span> </span><span> </span><span> @ test2</span></p><p class="p1" style="font-family: Helvetica; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; margin: 0px; text-align: start;">Inference time: 231.55 ms</p></div><p><br /><b>Result ( Video ) ~ 4-5 fps</b></p><p><b></b></p>
<div style="text-align: center;"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/7TLjkfXVwoI" title="YouTube video player" width="560"></iframe></div><div class="separator" style="clear: both; text-align: center;"><b><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhfgf8n5zWPj7VJGxdSpKEIC-pGekYQWD8gFcJfJlSNnNUuAjYtJBxGP4e23xO67ksj6jNoHytfiKnjxd26sSlH2D5mFZdfmGzb_1ktIUjXysQhqdHlL07o3BFyk_bgmqI4nWo2DiYL_bbeDS2JgyIJq2v0e095K2Ns6z2KGx4OS33csNJaZk31EqXrzw" style="margin-left: 1em; margin-right: 1em;"><img data-original-height="696" data-original-width="922" height="302" src="https://blogger.googleusercontent.com/img/a/AVvXsEhfgf8n5zWPj7VJGxdSpKEIC-pGekYQWD8gFcJfJlSNnNUuAjYtJBxGP4e23xO67ksj6jNoHytfiKnjxd26sSlH2D5mFZdfmGzb_1ktIUjXysQhqdHlL07o3BFyk_bgmqI4nWo2DiYL_bbeDS2JgyIJq2v0e095K2Ns6z2KGx4OS33csNJaZk31EqXrzw=w400-h302" width="400" /></a></b></div><b><br /><br /></b><p></p><h2 style="text-align: left;"><span style="color: #2b00fe;">TensorFlow and TensorFlow-lite Comparison</span></h2><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEige2yJYhFHJ7QjSa9X8QHnjpJT64biZRBkk-cyU8yzyE0JyWK2lwt3aFvXuv5HtfqKIPZ1jYNA4f0pftYqs5Itd99OeNVF9Y_ENE1BTQ8n3DbqJndSIrQsBfjwZ2aXT-rdp6JxwtLRps17MhMgocswfv2AQUFB5tS3niOZwg-vB4MgxmspC1YZ33wmeA/s930/Raspberrypi-objectdetction-comapre-tensorflow-vs-tensorflow-lite.png" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="305" data-original-width="930" height="210" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEige2yJYhFHJ7QjSa9X8QHnjpJT64biZRBkk-cyU8yzyE0JyWK2lwt3aFvXuv5HtfqKIPZ1jYNA4f0pftYqs5Itd99OeNVF9Y_ENE1BTQ8n3DbqJndSIrQsBfjwZ2aXT-rdp6JxwtLRps17MhMgocswfv2AQUFB5tS3niOZwg-vB4MgxmspC1YZ33wmeA/w640-h210/Raspberrypi-objectdetction-comapre-tensorflow-vs-tensorflow-lite.png" width="640" /></a></div><br /><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><div><br /></div><h3 style="text-align: left;"><span style="color: #2b00fe;">Reference</span></h3><p><b>TensorFlow</b></p><p><a href="https://www.tensorflow.org/">https://www.tensorflow.org/</a></p><p><a href="https://github.com/tensorflow/models">https://github.com/tensorflow/models</a></p><p><br /></p><p><b>TensorFlow-lite</b></p><p><a href="https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi">https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi</a></p><p><br /></p><p><span style="background-color: white; color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;">Website : </span><a href="https://softpower.tech" style="font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;">https://softpower.tech</a></p></div></div>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-14302164531610816622020-05-15T06:58:00.001-07:002023-05-09T02:43:07.947-07:00Raspberry pi Pytorch Object Detection<h2>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg-wnT0CEadyEszZdgT1rDeMinjesFK8t8z9jMRmHUDKMEvl6C1fP5g5_TUBZmvdzoBBdX_xpbte1WudtOlxfE8EN8fXgZD9yL2LQL4mknw9L5YX-rIrdoIhYQ-iuZaGyzJJdH_3gEFaI4A/s1600/raspberrypi-pytorch-objectdetection.jpg"><img border="0" height="312" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg-wnT0CEadyEszZdgT1rDeMinjesFK8t8z9jMRmHUDKMEvl6C1fP5g5_TUBZmvdzoBBdX_xpbte1WudtOlxfE8EN8fXgZD9yL2LQL4mknw9L5YX-rIrdoIhYQ-iuZaGyzJJdH_3gEFaI4A/s640/raspberrypi-pytorch-objectdetection.jpg" width="640" /></a></h2>
<h2>
<span style="color: magenta; font-size: x-large;"><b>Raspberry pi Pytorch Object Detection</b></span></h2>
<h1 style="background-color: white; border-bottom: 1px solid rgb(234, 236, 239); box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; line-height: 1.25; margin-bottom: 16px; margin-left: 0px; margin-right: 0px; margin-top: 0px !important; margin: 0px 0px 16px; padding-bottom: 0.3em;">
<span style="font-size: small; font-weight: normal;">Single Shot MultiBox Detector Implementation in Pytorch.</span></h1>
<div style="background-color: white; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 14px; margin-bottom: 6px; margin-top: 6px;">
</div>
<h3>
<b><span style="color: orange;">Software</span></b></h3>
<ul style="color: #1c1e21;">
<li>Raspbien 10</li>
<li><span class="text_exposed_show" style="display: inline; font-family: inherit;">Python 3.7.3</span></li>
<li><span class="text_exposed_show" style="display: inline; font-family: inherit;">Torch 1.4.0</span></li>
<li><span class="text_exposed_show" style="display: inline; font-family: inherit;">Torchvision 0.5</span></li>
</ul>
<br />
<div class="text_exposed_show" style="background-color: white; display: inline;">
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
Pre-trained Model : MobileNetV2 SSD-Lite</div>
<div class="separator" style="clear: both; color: #1c1e21; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWpRIxc8lOrP3SatObAzZVf1yqo34okAR0eDCdY1BQ1Y5yNsy444NO4SHRPYz4Vdh94cAnRy4r-rBCuvV-wVutGkiwn1F3Dq17HYNtE39C6Zfv0EBXj0FivNZoERorILlZGnLlr0NCb-N0/s1600/Raspberry-Pi-Logo.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="350" data-original-width="620" height="112" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWpRIxc8lOrP3SatObAzZVf1yqo34okAR0eDCdY1BQ1Y5yNsy444NO4SHRPYz4Vdh94cAnRy4r-rBCuvV-wVutGkiwn1F3Dq17HYNtE39C6Zfv0EBXj0FivNZoERorILlZGnLlr0NCb-N0/s200/Raspberry-Pi-Logo.png" width="200" /></a></div>
<h3 style="font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<b style="font-family: inherit;"><span style="color: blue; font-size: small;">Install on Raspberry pi</span></b></h3>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<br /></div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<b>Dependency </b></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
sudo apt install libopenblas-dev libblas-dev m4 cmake cython python3-dev python3-yaml python3-setuptools python3-wheel python3-pillow python3-numpy -y</div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
</div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
</div>
<br />
<div class="p3" style="-webkit-text-stroke-width: 0px; background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; line-height: normal; orphans: 2; text-align: start; text-decoration-color: initial; text-decoration-style: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;">
<div style="margin: 0px;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div style="margin: 0px;">
<span class="s1" style="font-kerning: none;">git clone https://github.com/marcusvlc/pytorch-on-rpi.git</span><br />
<span class="s1" style="font-kerning: none;"><br /></span>
cd pytorch-on-rpi/</div>
<div style="margin: 0px;">
<br /></div>
</div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">sudo pip3 install torch-1.4.0a0+7f73f1d-cp37-cp37m-linux_armv7l.whl</span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<br />
sudo pip3 install torchvision-0.5.0a0+85b8fbf-cp37-cp37m-linux_armv7l.whl</div>
<div class="p3" style="-webkit-text-stroke-width: 0px; background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; line-height: normal; orphans: 2; text-align: start; text-decoration-color: initial; text-decoration-style: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;">
<div style="margin: 0px;">
<br /></div>
</div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<span style="color: black; font-family: "calibri"; font-size: 11pt; line-height: 15.6933px;"><span style="font-size: 11pt; line-height: 15.6933px;"><br /></span></span></div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<span style="color: black; font-family: "calibri"; font-size: 11pt; line-height: 15.6933px;"><span style="font-size: 11pt; line-height: 15.6933px;"><b>Change Filename</b></span></span></div>
<div class="MsoListParagraphCxSpFirst" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-family: "times new roman"; font-size: 7pt; font-stretch: normal; line-height: normal;"> </span><span lang="TH" style="font-family: "cordia new" , serif; font-size: 14pt; line-height: 19.9733px;">Goto. /</span>usr/local/lib/python<span lang="TH" style="font-family: "cordia new" , serif; font-size: 14pt; line-height: 19.9733px;">3.7/</span>dist-packages/torch<span lang="TH" style="font-family: "angsana new"; font-size: 14pt; line-height: 19.9733px;"> </span><o:p></o:p></div>
<div class="MsoListParagraphCxSpFirst" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span lang="TH" style="font-family: "angsana new"; font-size: 14pt; line-height: 19.9733px;"><br /></span></div>
<div class="MsoListParagraphCxSpFirst" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span lang="TH" style="font-family: "angsana new"; font-size: 14pt; line-height: 19.9733px;">Change</span></div>
<div class="MsoListParagraphCxSpFirst" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span lang="TH" style="font-family: "angsana new"; font-size: 14pt; line-height: 19.9733px;"><br /></span></div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt;">
_CXXXXXXXX.so to <o:p></o:p><span style="font-size: 14.6667px;">_C.so</span></div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt;">
_dlXXXXXXXX.so to <span style="font-size: 14.6667px;">_dl.so</span><span style="font-size: 11pt;"> </span></div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt;">
<o:p></o:p></div>
<div class="MsoListParagraphCxSpMiddle" style="line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-align: left;">
<div style="color: black; font-family: calibri; font-size: 11pt;">
<br /></div>
<div style="color: black; font-family: calibri; font-size: 11pt;">
<br /></div>
<div>
<div style="background-color: #e9eff5; color: #222938; font-family: menlo;">
<span class="s1" style="font-kerning: none;">cd /usr/local/lib/python3.7/dist-packages/torch</span></div>
<div style="background-color: #e9eff5; color: #222938; font-family: menlo;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div style="background-color: #e9eff5;">
<span class="s1" style="font-kerning: none;"><span style="color: #222938; font-family: "menlo";">sudo mv _C.cpython-37m-arm-linux-gnueabi.so _C.so</span></span></div>
<div style="background-color: #e9eff5;">
<span class="s1" style="font-kerning: none;"><span style="color: #222938; font-family: "menlo";"><br /></span></span><span style="color: #222938; font-family: "menlo";">sudo mv _dl.cpython-37m-arm-linux-gnueabi.so _dl.so</span></div>
</div>
<div style="color: black; font-family: calibri; font-size: 11pt;">
<br /></div>
</div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgzeUkgvRG5_pbJkw22o-h4ffQCkgo-U0Km63wLbZZ-is0oluVTHGRww9dOgT_4nEGbdSTuhi3IJdtjXo0Q20HLN5uE4BKTtjuvtAJ4blmJtmg6cUlH1FIOnaN6yjMgDgDQM4NBFKCqUdGt/s1600/pytorch-checkversion.png" style="clear: left; float: left; font-size: 11pt; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="299" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgzeUkgvRG5_pbJkw22o-h4ffQCkgo-U0Km63wLbZZ-is0oluVTHGRww9dOgT_4nEGbdSTuhi3IJdtjXo0Q20HLN5uE4BKTtjuvtAJ4blmJtmg6cUlH1FIOnaN6yjMgDgDQM4NBFKCqUdGt/s640/pytorch-checkversion.png" width="640" /></a></div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-align: left;">
<span style="font-size: 14.6667px;"><b>Check Version. </b></span><span style="font-size: 11pt; text-indent: -18pt;">Goto python3 shell</span></div>
<div class="MsoListParagraphCxSpFirst" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<o:p></o:p></div>
<div class="MsoListParagraphCxSpMiddle" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 0.0001pt 36pt;">
<br /></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">>>> import torch </span><br />
<span class="s1" style="font-kerning: none;">>>> torch.__version__</span><br />
<br />
>>> import torchvision </div>
<div class="p3" style="-webkit-text-stroke-width: 0px; background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; line-height: normal; orphans: 2; text-align: start; text-decoration-color: initial; text-decoration-style: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;">
<div style="margin: 0px;">
<span class="s1" style="font-kerning: none;">>>> torchvision.__version__</span></div>
</div>
<div class="MsoNormal" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIs8by3yqWOBj6T76N1pelCgCgpgGAuuYlif_hXuaSd0Zx6dfGGKg5M-ZCzE-_sSE0pp9I7ahE6S7CgjkOO12xtmS40vvMBZiAVaMYoVfujo0jCt9beuwJlb2SMo738ajjXmShQbld3zlm/s1600/pytorch-logo1.jpeg"><img border="0" height="100" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIs8by3yqWOBj6T76N1pelCgCgpgGAuuYlif_hXuaSd0Zx6dfGGKg5M-ZCzE-_sSE0pp9I7ahE6S7CgjkOO12xtmS40vvMBZiAVaMYoVfujo0jCt9beuwJlb2SMo738ajjXmShQbld3zlm/s200/pytorch-logo1.jpeg" width="200" /></a></b></div>
<div class="MsoNormal" style="font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b><span style="color: blue;">Source Code</span></b></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">git clone https://github.com/qfgaohao/pytorch-ssd.git</span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<br /></div>
<div class="MsoNormal" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b><br /></b></div>
<div class="MsoNormal" style="font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b><span style="color: blue;">Pre-Trained Model </span>( </b><span style="color: black; font-size: 11pt;">MobileNetV</span><span lang="TH" style="color: black; font-family: "cordia new" , serif; font-size: 14pt; line-height: 19.9733px;">2 </span><span style="color: black; font-size: 11pt;">SSD-Lite )</span></div>
<div class="MsoNormal" style="color: black; font-family: Calibri; font-size: 11pt; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<o:p></o:p></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">cd pytorch-ssd/models</span><br />
<br />
wget https://storage.googleapis.com/models-hao/mb2-ssd-lite-mp-0_686.pth</div>
<div class="p3" style="background-color: #e9eff5; font-stretch: normal; line-height: normal; orphans: 2; text-align: start; text-decoration-color: initial; text-decoration-style: initial; text-indent: 0px; widows: 2;">
<div style="-webkit-text-stroke-width: 0px; color: #222938; font-family: menlo; font-size: 16px; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; margin: 0px; text-transform: none; white-space: normal; word-spacing: 0px;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div style="margin: 0px;">
<span class="s1" style="color: #222938; font-family: "menlo"; font-kerning: none;">wget https://storage.googleapis.com/models-hao/voc-model-labels.txt</span></div>
<div style="-webkit-text-stroke-width: 0px; color: #222938; font-family: menlo; font-size: 16px; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; margin: 0px; text-transform: none; white-space: normal; word-spacing: 0px;">
<br /></div>
</div>
<div class="MsoNormal" style="color: black; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<br /></div>
<h3 style="font-family: inherit; margin-bottom: 6px;">
<b><span style="color: blue; font-size: small;">Run demo Code</span></b></h3>
<div>
<b><span style="color: blue; font-size: small;"><br /></span></b></div>
<div>
<b><span style="color: blue; font-size: small;">For Image file </span></b></div>
<div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">python3 run_ssd_example.py mb2-ssd-lite models/mb2-ssd-lite-mp-0_686.pth models/voc-model-labels.txt your_image_file</span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: menlo; font-size: 16px; font-stretch: normal; line-height: normal;">
<br /></div>
</div>
<div style="color: #1c1e21; font-size: 14px; margin-bottom: 6px;">
<br /></div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjs0olgHSMhCA-jprBJn9vCF895y36tD_5a8IQNNPjvzP7bQzPBgS6tevd4DEdnhT8IJn4iRXDs9vVPqMFwMLTmZdULvWHFtp4q00gs2F3E5WA5lhHx_gjlk3UQmU1oqe-1dGZkloTabbFQ/s1600/run_ssd_example_output1.jpg"><img border="0" height="312" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjs0olgHSMhCA-jprBJn9vCF895y36tD_5a8IQNNPjvzP7bQzPBgS6tevd4DEdnhT8IJn4iRXDs9vVPqMFwMLTmZdULvWHFtp4q00gs2F3E5WA5lhHx_gjlk3UQmU1oqe-1dGZkloTabbFQ/s640/run_ssd_example_output1.jpg" width="640" /></a><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgY8RtJLoaui10r8BGG5FB98cgKCnjAkYviB0OfXgcNh0rS_r0Q-6GupqZT_TTUeCfHDFSQdfaxPpeA4C3_Pj-lxgQrSEq3cWMX-0XZ_S5XIKUMgj9mi0EOATNJTvNXkuEQJ68bHURPAqbR/s1600/Screen+Shot+2563-05-10+at+13.59.44.png"><img border="0" height="456" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgY8RtJLoaui10r8BGG5FB98cgKCnjAkYviB0OfXgcNh0rS_r0Q-6GupqZT_TTUeCfHDFSQdfaxPpeA4C3_Pj-lxgQrSEq3cWMX-0XZ_S5XIKUMgj9mi0EOATNJTvNXkuEQJ68bHURPAqbR/s640/Screen+Shot+2563-05-10+at+13.59.44.png" width="640" /></a></div>
<h3 style="color: #1c1e21; font-family: inherit; margin-bottom: 6px;">
<b>Reference</b></h3>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<a href="https://github.com/qfgaohao/pytorch-ssd">https://github.com/qfgaohao/pytorch-ssd</a><br />
<br />
<a href="https://pytorch.org/">https://pytorch.org/</a></div>
<div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;">
<br /></div><div style="color: #1c1e21; font-family: inherit; font-size: 14px; margin-bottom: 6px;"><span style="color: #050505; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;">Website : </span><a href="https://softpower.tech" style="font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 15px; white-space: pre-wrap;">https://softpower.tech</a></div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-52720467728411338712020-04-19T20:30:00.002-07:002021-04-19T21:40:54.749-07:00Raspberry pi TensorFlow.JS Facemesh<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/OW7E7OzwMEs" width="560"></iframe><br />
<br />
<br />
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/Lz8GgoBZCPg" width="560"></iframe><br />
<br />
<h2>
<span face=""roboto" , sans-serif" style="color: magenta; font-size: x-large;"><b>Raspberry pi TensorFlow.JS Facemesh</b></span></h2>
<span face=""roboto" , sans-serif" style="font-size: 16px;">The facemesh package infers approximate 3D facial surface geometry from an image or video stream, requiring only a single camera input without the need for a depth sensor. This geometry locates features such as the eyes, nose, and lips within the face, including details such as lip contours and the facial silhouette. This information can be used for downstream tasks such as expression classification (but not for identification). Refer to our </span><a href="https://drive.google.com/file/d/1VFC_wIpw4O7xBOiTgUldl79d9LA-LsnA/view" style="color: #425066; font-family: Roboto, sans-serif; font-size: 16px; transition: color 0.2s linear 0s;">model card</a><span face=""roboto" , sans-serif" style="font-size: 16px;"> for details on how the model performs across different datasets. This package is also available through </span><a href="https://github.com/google/mediapipe/" style="color: #425066; font-family: Roboto, sans-serif; font-size: 16px; transition: color 0.2s linear 0s;">MediaPipe</a><span face=""roboto" , sans-serif" style="font-size: 16px;">.</span><br />
<h4 style="font-family: "Google Sans", sans-serif; font-size: 20px; font-weight: 500; line-height: 30px; margin-bottom: 14px !important; margin-left: 0px; margin-right: 0px; margin-top: 40px; margin: 40px 0px 14px; position: relative;">
Performance characteristics</h4>
<span face=""roboto" , sans-serif" style="font-size: 16px;">Facemesh is a lightweight package containing only ~3MB of weights, making it ideally suited for real-time inference on a variety of mobile devices. When testing, note that TensorFlow.js also provides several different backends to choose from, including WebGL and WebAssembly (WASM) with </span><a href="https://github.com/google/XNNPACK" style="color: #425066; font-family: Roboto, sans-serif; font-size: 16px; transition: color 0.2s linear 0s;">XNNPACK</a><span face=""roboto" , sans-serif" style="font-size: 16px;"> for devices with lower-end GPU's. The table below shows how the package performs across a few different devices and TensorFlow.js backends:</span><br />
<span face=""roboto" , sans-serif" style="font-size: 16px;"><br /></span>
<img alt="The table shows how the package performs across different devices and TensorFlow.js backends" height="96" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhHl02TBT5LViLT6e-8q7pKESh_2sg2iWBO1V1ycY3GQI29bqwWhtyIXL-yJqREuyR6XqSzokZDO1gl7eVvlII47pfWfAADrTtHvbxS_72r2u40_PLrL0iQ1sRYHs1RTyswJ84Vz0BA1zM/s640/Screen+Shot+2020-03-08+at+2.53.22+PM.png" width="640" /><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg7L091ApAy_rfKgsf6xQrsJ6AFHt2q79Tqv-iEv928fZbKeE5xhOdFttF91HtFfINrwSSIyHM972xsLMQMzo-4vd8d165d-u0JXRUN_AL3s2lNr0bRDgx6EO_cuBiJ9yUuTutRIKlP96mO/s1600/tfjs.png"><img border="0" height="160" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg7L091ApAy_rfKgsf6xQrsJ6AFHt2q79Tqv-iEv928fZbKeE5xhOdFttF91HtFfINrwSSIyHM972xsLMQMzo-4vd8d165d-u0JXRUN_AL3s2lNr0bRDgx6EO_cuBiJ9yUuTutRIKlP96mO/s320/tfjs.png" width="320" /></a><br />
<b>Demo Source Code</b><br />
<a href="https://github.com/tensorflow/tfjs-models/tree/master/facemesh">https://github.com/tensorflow/tfjs-models/tree/master/facemesh</a><br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhnQrGuNzPnihnnPHBsNTKqOxqjffo5Y6EwWOQwUQ3Kl0NHPjr82N5Xj-xEdJ52ULa43d43b_KCJc_YxjVfyHSS1MhqCovi0jqifL4_6D9N5TpVU0UyKnfiXifJy2LLOfUBYRqh14tpsVgc/s1600/Raspi-PGB001.png"><img border="0" height="177" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhnQrGuNzPnihnnPHBsNTKqOxqjffo5Y6EwWOQwUQ3Kl0NHPjr82N5Xj-xEdJ52ULa43d43b_KCJc_YxjVfyHSS1MhqCovi0jqifL4_6D9N5TpVU0UyKnfiXifJy2LLOfUBYRqh14tpsVgc/s200/Raspi-PGB001.png" width="200" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhFEKZeoiiiPvIXhcq2cH4Jhew5bb7zY-IvJ7LwV3pO8BB18zrjTKbdQ5-prhBfoHFj1l_-QijZQ0RHncievOjc0u-afgRHAUkc2AhQi8pT4nbOZDkYn5349Vs0iAG7EyGao1e-zAwZaGfp/s1600/1280px-Node.js_logo.svg.png"><img border="0" height="122" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhFEKZeoiiiPvIXhcq2cH4Jhew5bb7zY-IvJ7LwV3pO8BB18zrjTKbdQ5-prhBfoHFj1l_-QijZQ0RHncievOjc0u-afgRHAUkc2AhQi8pT4nbOZDkYn5349Vs0iAG7EyGao1e-zAwZaGfp/s200/1280px-Node.js_logo.svg.png" width="200" /></a><br />
<br />
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/wDbVz69ucmA" width="560"></iframe>
<br />
<h3>
<span style="color: blue;">Installation on Raspberry pi <span style="font-weight: normal;">( see in Youtube )</span></span></h3>
<div class="p1" style="font-family: helvetica; font-stretch: normal; line-height: normal;">
<b>Install NodeJS and npm</b></div>
<div class="p2" style="font-family: Helvetica; font-size: 12px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal; min-height: 14px;">
<br /></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: Menlo; font-size: 16px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">curl -sL https://deb.nodesource.com/setup_12.x | sudo bash -</span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: Menlo; font-size: 16px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: Menlo; font-size: 16px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">sudo apt-get install nodejs</span></div>
<div class="p3" style="background-color: #e9eff5; color: #222938; font-family: Menlo; font-size: 16px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<br />
<b>Install Yarn</b><br />
<br />
<div class="p1" style="background-color: #f4f6f9; color: #1b1f22; font-family: Menlo; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | sudo apt-key add -</span></div>
<div class="p1" style="background-color: #f4f6f9; color: #1b1f22; font-family: Menlo; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div class="p1" style="background-color: #f4f6f9; color: #1b1f22; font-family: Menlo; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;">echo "deb https://dl.yarnpkg.com/debian/ stable main" | sudo tee /etc/apt/sources.list.d/yarn.list</span></div>
<div class="p1" style="background-color: #f4f6f9; color: #1b1f22; font-family: Menlo; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span class="s1" style="font-kerning: none;"><br /></span></div>
<div class="p1" style="background-color: #f4f6f9; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;">
<span style="color: #1b1f22; font-family: "menlo";">sudo apt-get update && sudo apt-get install yarn</span></div>
<br />
<br />
<b>Check Version</b><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEifUlmkgKkyPrRCcCCZ5O4GzEI7EA_sk4XMc0jiuE7TehJbzO8JBgB4L-speCAiGv0t4ZyhNsVBxjFET6McJIFuFgUu1t1OYTFD7_LO481Z91f9YgDL7OgFFxJWgiOS8GLSpDEOCARYOV6j/s1600/nodejs-version.png"><img border="0" height="126" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEifUlmkgKkyPrRCcCCZ5O4GzEI7EA_sk4XMc0jiuE7TehJbzO8JBgB4L-speCAiGv0t4ZyhNsVBxjFET6McJIFuFgUu1t1OYTFD7_LO481Z91f9YgDL7OgFFxJWgiOS8GLSpDEOCARYOV6j/s320/nodejs-version.png" width="320" /></a><br />
<br />
<h3>
<b><span style="color: orange;">Run Demo code ( need USB Webcam )</span></b></h3>
<b>Git Clone code</b><br />
<span style="background-color: #eeeeee;">git clone https://github.com/tensorflow/tfjs-models.git</span><br />
<br />
<br />
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Go into the facemesh folder:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;"><span class="pl-c1" style="box-sizing: border-box; color: #005cc5;">cd</span> facemesh</pre>
</div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Install dependencies:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;">yarn</pre>
</div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Publish facemesh locally:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;">yarn build <span class="pl-k" style="box-sizing: border-box; color: #d73a49;">&&</span> yarn yalc publish</pre>
</div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Cd into the demos and install dependencies:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;"><span class="pl-c1" style="box-sizing: border-box; color: #005cc5;">cd</span> demo
yarn</pre>
</div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Link the local facemesh to the demos:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;">yarn yalc link @tensorflow-models/facemesh</pre>
</div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
Start the dev demo server:</div>
<div class="highlight highlight-source-shell" style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 16px; margin-bottom: 16px;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;">yarn watch</pre>
</div>
Then Open Web Browser and use domain <span style="color: blue; font-size: large;">localhost:1234</span><br />
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgwpHT_FmhaTcjj6kxfHwlDG02BJAVqI1atfb7-EQ8m0fE2OPrRiUsEQtQfcpVt-Fk86rjB4nPWJcMhciQDKcwYkN9em5DMcLK5nDWXgBafLv2mvRkg9jQj1hviB1iHkFnIi6OpqaAE-skb/s1600/logitechC270.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="474" data-original-width="592" height="160" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgwpHT_FmhaTcjj6kxfHwlDG02BJAVqI1atfb7-EQ8m0fE2OPrRiUsEQtQfcpVt-Fk86rjB4nPWJcMhciQDKcwYkN9em5DMcLK5nDWXgBafLv2mvRkg9jQj1hviB1iHkFnIi6OpqaAE-skb/s200/logitechC270.png" width="200" /></a></div>
Need USB Webcam<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRo2e8ETWwSIJf5Jrjx1ln1T7zJkIgK3vbnQ_Kmjw2EFCnKMflcCwVSEcUx6PEHXifYx8jd96ZwSKX4E-OwuK0j9E9dZKCl5Qd4COWZE5evGMb39C1a8JGNG-ayeIoC1GDw_xosJONLsQU/s1600/allow-webcam.png"><img border="0" height="272" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRo2e8ETWwSIJf5Jrjx1ln1T7zJkIgK3vbnQ_Kmjw2EFCnKMflcCwVSEcUx6PEHXifYx8jd96ZwSKX4E-OwuK0j9E9dZKCl5Qd4COWZE5evGMb39C1a8JGNG-ayeIoC1GDw_xosJONLsQU/s640/allow-webcam.png" width="640" /></a><br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiix_qnTIXkLxYMNOanCtaJrw1PjRBHDy5Oy1sTXslzCDcg-8AaOHWld1YwPuw0p9O0S72laPVof4oduZ3X6cYR6O5Hq9jjsa1siwKS-drdSNWevtIvRoVSHTt9LUSx-dgerYme88V-4UKb/s1600/raspberrypi-facemesh-demo1.png"><img border="0" height="361" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiix_qnTIXkLxYMNOanCtaJrw1PjRBHDy5Oy1sTXslzCDcg-8AaOHWld1YwPuw0p9O0S72laPVof4oduZ3X6cYR6O5Hq9jjsa1siwKS-drdSNWevtIvRoVSHTt9LUSx-dgerYme88V-4UKb/s640/raspberrypi-facemesh-demo1.png" width="640" /></a><br />
<div>
<br />
<br />
<h3>
<b><span style="color: blue;">Test on Android Web Browser</span></b></h3>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEidR2FJY4A5fcvX8RfwKO-lG4mnT69nJse1hc3tUibgXzMVE4m9znf2XmNTozwfEkDohF-Ig-21kuXBsfVUtN02b9kpXeNTw12HTilW643V_G8-wdCPa-8jt_KQ6FU82FApnALPAmgpIn_7/s1600/1586931862093-1.jpg"><img border="0" height="292" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEidR2FJY4A5fcvX8RfwKO-lG4mnT69nJse1hc3tUibgXzMVE4m9znf2XmNTozwfEkDohF-Ig-21kuXBsfVUtN02b9kpXeNTw12HTilW643V_G8-wdCPa-8jt_KQ6FU82FApnALPAmgpIn_7/s640/1586931862093-1.jpg" width="640" /></a><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiwcCmCHZG9uYwQxphK24gMwzc8IimWAeB8RpQqvc1Q5HvAPKxxwBC6Bx6EpFFtLAI0CsBZ1RnOWeFYoHsqYuY1H-_QmVijcDis48qUC22VQoZQC-c2c8XFagnXnyq1DBoJQSebeDLHpsQh/s1600/1586930921488-1.jpg"><img border="0" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiwcCmCHZG9uYwQxphK24gMwzc8IimWAeB8RpQqvc1Q5HvAPKxxwBC6Bx6EpFFtLAI0CsBZ1RnOWeFYoHsqYuY1H-_QmVijcDis48qUC22VQoZQC-c2c8XFagnXnyq1DBoJQSebeDLHpsQh/s400/1586930921488-1.jpg" width="183" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhGBIXdyPtVbfYLWJVI8PKnzltfbd5lodcOfdIhzi0Yqx7gberYr8z4f4yio_ozV-crW3Mu7sGDbi4SAWaCbd6J8_x8VEoCTc-K5bGOBGN6xJQaeR0jzNwjXAVma8DqapMUFxqhhYyRZPf7/s1600/1586930923070-1.jpg"><img border="0" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhGBIXdyPtVbfYLWJVI8PKnzltfbd5lodcOfdIhzi0Yqx7gberYr8z4f4yio_ozV-crW3Mu7sGDbi4SAWaCbd6J8_x8VEoCTc-K5bGOBGN6xJQaeR0jzNwjXAVma8DqapMUFxqhhYyRZPf7/s400/1586930923070-1.jpg" width="183" /></a>.<br />
<br /></div>
<h3>
<span style="color: orange;"><u>Reference</u></span></h3>
<span face=""google sans" , sans-serif" style="font-weight: 700;"><span style="font-size: x-small;">Face and hand tracking in the browser with MediaPipe and TensorFlow.js</span></span><br />
<a href="https://blog.tensorflow.org/2020/03/face-and-hand-tracking-in-browser-with-mediapipe-and-tensorflowjs.html">https://blog.tensorflow.org/2020/03/face-and-hand-tracking-in-browser-with-mediapipe-and-tensorflowjs.html</a><br />
<br />
<b>MediaPipe</b><br />
<a href="https://github.com/google/mediapipe">https://github.com/google/mediapipe</a><div><br /></div><div><b>Online Demo</b></div><div><a href="https://storage.googleapis.com/tfjs-models/demos/facemesh/index.html">https://storage.googleapis.com/tfjs-models/demos/facemesh/index.html</a><br />
<br /></div>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-59424125298033915362020-04-10T01:09:00.000-07:002020-04-10T01:39:07.580-07:00Raspberry pi Person Tracking with Intel AI<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/1qEc800Q6Aw" width="560"></iframe>
<h2>
<b><span style="color: magenta; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: large;">Raspberry pi Person Tracking with Intel AI</span></b> </h2>
<span data-offset-key="cpdv0-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">Multi Person Detect and Tracking with Intel AI on Raspberry pi</span><span data-offset-key="cpdv0-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><span style="color: #4a4a4a; font-size: 15px; white-space: normal;">This demo demonstrates how to run Multi Camera Multi Person demo using OpenVINO</span><span style="color: #4a4a4a; font-size: 11.6667px; white-space: normal;">.</span></span><br />
<br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; margin-left: 1em; margin-right: 1em;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi_yU0nPwqPSG7ZCvkpULH3Xdxe_39ohEj_HNhqMLdfPhlL2nsrqh8rjSFPSKrjk6tzeuT4Z_00VJD6UG4pE5BMOe-OztdN8U5qAU5Rsnz4pcQETUtFhNmFBqz7XbMpZE-5gOyOzayFypMN/s1600/openvino.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="119" data-original-width="584" height="65" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi_yU0nPwqPSG7ZCvkpULH3Xdxe_39ohEj_HNhqMLdfPhlL2nsrqh8rjSFPSKrjk6tzeuT4Z_00VJD6UG4pE5BMOe-OztdN8U5qAU5Rsnz4pcQETUtFhNmFBqz7XbMpZE-5gOyOzayFypMN/s320/openvino.png" width="320" /></a></span><br />
<h3>
<span data-offset-key="cpdv0-0-0" style="font-family: inherit;"><span style="color: #4a4a4a; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; white-space: normal;"><b><a href="https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html" target="_blank">W</a></b></span></span><span data-offset-key="cpdv0-0-0" style="font-family: inherit;"><span style="color: #4a4a4a; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; white-space: normal;"><b><a href="https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html" target="_blank">hat is OpenVINO?</a></b></span></span></h3>
<span data-offset-key="cpdv0-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html">https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html</a></span><br />
<h3>
<span data-offset-key="49lqg-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b>Pre-trained Model</b></span><span data-offset-key="dr8v6-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"> </span></h3>
<span data-offset-key="dr8v6-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• Person-detection-retail-0013 Model</span><span data-offset-key="6fvvf-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"> </span><br />
<span data-offset-key="6fvvf-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• Person-reidentification-retail-0076 Model</span><br />
<span data-offset-key="6fvvf-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><br /></span>
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; margin-left: 1em; margin-right: 1em;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVcQATO-vjslu29M-7Dy6vDgymJYSym2U7dHTNMHw4sd2ShE5-2sQuEqBDWyzrEjylHt3z_r4tN4ROas3B_C3yFqZ3mzryiQnF1acWrROmj8pRyf4pPOh00oagEwUEkMHnI9-_u4CPQmiw/s1600/raspi4_intel_neural-compute_stick.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="900" data-original-width="1200" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVcQATO-vjslu29M-7Dy6vDgymJYSym2U7dHTNMHw4sd2ShE5-2sQuEqBDWyzrEjylHt3z_r4tN4ROas3B_C3yFqZ3mzryiQnF1acWrROmj8pRyf4pPOh00oagEwUEkMHnI9-_u4CPQmiw/s320/raspi4_intel_neural-compute_stick.jpg" width="320" /></a></span><br />
<h3>
<span data-offset-key="enmam-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b>Hardware</b></span></h3>
<span data-offset-key="7s4qe-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• Raspberry Pi Board (4B 1 GB)</span><br />
<span data-offset-key="9267e-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• Intel Neural Compute Stick 2</span><br />
<span data-offset-key="fm5ai-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b><br /></b></span>
<br />
<h3>
<span data-offset-key="fm5ai-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b>Software</b></span></h3>
<span data-offset-key="9v6mo-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• OS Raspbien 10 ( Buster )</span><br />
<span data-offset-key="9gehv-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• Python 3.7.3</span><span data-offset-key="a7eol-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• OpenVINO Toolkit 2020.1</span><br />
<span data-offset-key="fd93l-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">• OpenCV 4.0.0</span><br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; margin-left: 1em; margin-right: 1em;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg9Vc1BE_BRCjomO0Hmn7jrnXu4KIEITtFm-mSzuON2KXomBLZHugEalBhep6K7iEad4o2F3z561pKcwdhDeh1ndYC7C8MUPPk4MH7jGJWLoM51VgpBKcAXLbRCnu4j_g1uwgyzVro2aZMr/s1600/Python+%25281%2529.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="200" data-original-width="273" height="146" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg9Vc1BE_BRCjomO0Hmn7jrnXu4KIEITtFm-mSzuON2KXomBLZHugEalBhep6K7iEad4o2F3z561pKcwdhDeh1ndYC7C8MUPPk4MH7jGJWLoM51VgpBKcAXLbRCnu4j_g1uwgyzVro2aZMr/s200/Python+%25281%2529.png" width="200" /></a></span><br />
<h3>
<span data-offset-key="dj3cl-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b>Python Source code</b></span></h3>
<span data-offset-key="4r1qi-0-0" style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://docs.openvinotoolkit.org/latest/_demos_python_demos_multi_camera_multi_person_tracking_README.html">https://docs.openvinotoolkit.org/latest/_demos_python_demos_multi_camera_multi_person_tracking_README.html</a></span><br />
<br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjQQEYAhS_jDoc47i9KdMNcH2bvN1U0SUGMS_rjai3n7ump0KudrZTqv1wNkg3iGx784qHjZfAr3RjSJsg8N7fJHlTjnnKll6ZL63CoDCc5N7jSxHl-QVZlstMI9q48tNKQRC7ewe46iAWG/s1600/pedestrain1.jpg" imageanchor="1"><img border="0" height="272" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjQQEYAhS_jDoc47i9KdMNcH2bvN1U0SUGMS_rjai3n7ump0KudrZTqv1wNkg3iGx784qHjZfAr3RjSJsg8N7fJHlTjnnKll6ZL63CoDCc5N7jSxHl-QVZlstMI9q48tNKQRC7ewe46iAWG/s400/pedestrain1.jpg" width="400" /></a></span><br />
<br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi84AXETuzsUY7YUc2x8BIXSWbFiN_Q_MdbH0Wcsecu3dwGKZy9Y_ED7HZ-3hnNyw5uDbYAEUac8n2kOaR5nubs-s1cEzfDaCT7Jpm35EXbFS-gkR_zVo_a9NDFaox2rbntMOJbuY8cxf9S/s1600/pedestrain2.jpg" imageanchor="1"><img border="0" height="266" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi84AXETuzsUY7YUc2x8BIXSWbFiN_Q_MdbH0Wcsecu3dwGKZy9Y_ED7HZ-3hnNyw5uDbYAEUac8n2kOaR5nubs-s1cEzfDaCT7Jpm35EXbFS-gkR_zVo_a9NDFaox2rbntMOJbuY8cxf9S/s400/pedestrain2.jpg" width="400" /></a></span><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMzu7vjEdG3fu7jkOsP7sf3uG_F050InC5JJqpQTaLKG82ZCE2yGQre6jZi209aUBFGnOV12RSlw3XzW4mRbAaUC9vHVe699rSBOICeT_t8G1y-2dVsVUJJiEONu4puU1MrHY15aG-NK4c/s1600/pedestrain3.jpg" imageanchor="1"><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><img border="0" height="270" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMzu7vjEdG3fu7jkOsP7sf3uG_F050InC5JJqpQTaLKG82ZCE2yGQre6jZi209aUBFGnOV12RSlw3XzW4mRbAaUC9vHVe699rSBOICeT_t8G1y-2dVsVUJJiEONu4puU1MrHY15aG-NK4c/s400/pedestrain3.jpg" width="400" /></span></a><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh7Byqp5ZtaN0BHdxvaAe4UPFxfCOiA76NDqHEbcpSa51UFquJ4qbB-ozGvA1HXEijIHbOZwT7EHwY3659hneK0c1bYsAsAvV5F0-JQpA1jRUn3gx_HrfdHe0axD4O8PJ85i7rv3nKTULFl/s1600/pedestrain4.jpg" imageanchor="1"><img border="0" height="266" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh7Byqp5ZtaN0BHdxvaAe4UPFxfCOiA76NDqHEbcpSa51UFquJ4qbB-ozGvA1HXEijIHbOZwT7EHwY3659hneK0c1bYsAsAvV5F0-JQpA1jRUn3gx_HrfdHe0axD4O8PJ85i7rv3nKTULFl/s400/pedestrain4.jpg" width="400" /></a></span><br />
<h3>
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><b>Detect Output</b></span></h3>
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">The demo displays bounding boxes of tracked objects and unique IDs of those objects. To save output video with the result please use the option <code style="background: rgb(249, 249, 249); box-sizing: border-box;">--output_video</code>, to change configuration parameters please open the <code style="background: rgb(249, 249, 249); box-sizing: border-box;">config.py</code> file and edit it.</span><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">Also demo can dump resulting tracks to a json file. To specify the file use the <code style="background: rgb(249, 249, 249); box-sizing: border-box;">--history_file</code> argument.</span><br />
<h3>
<b style="font-size: 16px;"><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">Reference</span></b></h3>
<span style="font-size: 16px;"><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">OpenViNO Toolkit</span></span><br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://docs.openvinotoolkit.org/latest/index.html">https://docs.openvinotoolkit.org/latest/index.html</a></span><br />
<span style="background-color: white; color: #2171b8; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: 13.2px;"><br /></span>
<span style="background-color: white; color: #2171b8; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: 13.2px;">Install OpenVINO™ toolkit for Raspbian* OS</span><br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html">https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html</a></span><br />
<span style="color: #2171b8; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><br /></span>
<span style="color: #2171b8; font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;">Multi Camera Multi Person Python* Demo </span><br />
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: x-small; white-space: pre-wrap;"><a href="https://docs.openvinotoolkit.org/latest/_demos_python_demos_multi_camera_multi_person_tracking_README.html" style="font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; white-space: pre-wrap;">https://docs.openvinotoolkit.org/latest/_demos_python_demos_multi_camera_multi_person_tracking_README.html</a></span>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-37488090669316949142020-04-06T22:49:00.003-07:002020-04-10T00:23:55.477-07:00Raspberry pi Object Detection with Intel AI Stick<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/AHWs9z1Xwms" width="560"></iframe><br />
<h2>
<span style="color: blue; font-size: x-large;"><b>Raspberry pi Object Detection with Intel AI Stick</b></span></h2>
<span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;">This project showcases Object Detection with SSD and new Async API. Async API usage can improve overall frame-rate of the application, because rather than wait for inference to complete, the app can continue doing things on the host, while accelerator is busy. </span><br />
<span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;"><br /></span>
<span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;">Specifically, this demo keeps two parallel infer requests and while the current is processed, the input frame for the next is being captured. This essentially hides the latency of capturing, so that the overall framerate is rather determined by the </span><code style="background: rgb(249, 249, 249); box-sizing: border-box; color: #4a4a4a; font-family: "Roboto Mono", monospace, fixed; font-size: 15px;">MAXIMUM(detection time, input capturing time)</code><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;"> and not the </span><code style="background: rgb(249, 249, 249); box-sizing: border-box; color: #4a4a4a; font-family: "Roboto Mono", monospace, fixed; font-size: 15px;">SUM(detection time, input capturing time)</code><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;">.</span><br />
<span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;"><br /></span>
<span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px;">The technique can be generalized to any available parallel slack, for example, doing inference and simultaneously encoding the resulting (previous) frames or running further inference,</span><br />
<div style="background-color: white; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
This and other performance implications and tips for the Async API are covered in the <a href="https://docs.openvinotoolkit.org/latest/_docs_optimization_guide_dldt_optimization_guide.html" style="box-sizing: border-box; color: #3eb6e0; font-weight: inherit; text-decoration-line: none;">Optimization Guide</a></div>
<div style="background-color: white; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
Other demo objectives are:</div>
<ul style="background-color: white; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">Video as input support via OpenCV</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">Visualization of the resulting bounding boxes and text labels (from the <code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">.labels</code> file) or class number (if no file is provided)</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">OpenCV is used to draw resulting bounding boxes, labels, so you can copy paste this code without need to pull Open Model Zoo demos helpers to your app</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">Demonstration of the Async API in action, so the demo features two modes (toggled by the <b style="box-sizing: border-box;">Tab</b> key)</li>
<ul style="box-sizing: border-box; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">Old-style "Sync" way, where the frame capturing with OpenCV executes back to back with the Detection</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;">"Truly Async" way when the Detection performed on the current frame, while the OpenCV captures the next one.</li>
</ul>
</ul>
<h3>
<b>System Requirements</b></h3>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVcQATO-vjslu29M-7Dy6vDgymJYSym2U7dHTNMHw4sd2ShE5-2sQuEqBDWyzrEjylHt3z_r4tN4ROas3B_C3yFqZ3mzryiQnF1acWrROmj8pRyf4pPOh00oagEwUEkMHnI9-_u4CPQmiw/s1600/raspi4_intel_neural-compute_stick.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="900" data-original-width="1200" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVcQATO-vjslu29M-7Dy6vDgymJYSym2U7dHTNMHw4sd2ShE5-2sQuEqBDWyzrEjylHt3z_r4tN4ROas3B_C3yFqZ3mzryiQnF1acWrROmj8pRyf4pPOh00oagEwUEkMHnI9-_u4CPQmiw/s320/raspi4_intel_neural-compute_stick.jpg" width="320" /></a></div>
<h4>
<b>Hardware</b></h4>
· Raspberry Pi Board (4B , 3B+)<br />
· Intel Neural Compute Stick ( V1 or V2 )<br />
· Pi Camera ( V1 or V2 ) or USB cam<br />
· SD Card 32GB<br />
· 5V DC. 2A Power Supply<br />
<h4>
<b>Software</b></h4>
· OS Raspbien 10 ( Buster )<br />
· Python 3.7.3<br />
· OpenVINO Toolkit 2019.R3<br />
· OpenCV 4.0.0<br />
<br />
Machine Learning Object Detection Model : Mobilenet SSD V2<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhRCf8cvYisJmch-myNyD5W9Yg-QL_ZDna7tUESfMJlkBDb8r8dkpgMZnx0QvBdcI5jpKYQ0Ii3fX9esLacDTdGIo_KzJFRuGQ3RB2Lp_gtO9xfVP4gS4X3QE9wV6vczsB4xDbNDhyad4eR/s1600/rpi-objectdetection1.jpg" imageanchor="1"><img border="0" height="246" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhRCf8cvYisJmch-myNyD5W9Yg-QL_ZDna7tUESfMJlkBDb8r8dkpgMZnx0QvBdcI5jpKYQ0Ii3fX9esLacDTdGIo_KzJFRuGQ3RB2Lp_gtO9xfVP4gS4X3QE9wV6vczsB4xDbNDhyad4eR/s400/rpi-objectdetection1.jpg" width="400" /></a><br />
<h3>
<b>Output Detection</b></h3>
<div style="background-color: white; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
he demo uses OpenCV to display the resulting frame with detections (rendered as bounding boxes and labels, if provided). In the default mode the demo reports</div>
<ul style="background-color: white; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><b style="box-sizing: border-box;">OpenCV time</b>: frame decoding + time to render the bounding boxes, labels, and displaying the results.</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><b style="box-sizing: border-box;">Detection time</b>: inference time for the (object detection) network. It is reported in the "SYNC" mode only.</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><b style="box-sizing: border-box;">Wallclock time</b>, which is combined (application level) performance.</li>
</ul>
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgNPtKH3m9K4NfQjWPcoeJvfryqhhkyNPYadtnH_Q1OS4CYxiBcG6Ivgy965Id_rpMCaWmAWa_izFGkJT0xHbM4Vv-y-TNyDwjzs32LT2uZLTIg1wQBHMqO39tIsCqa14g07lfWG0zc0mm8/s1600/raspberrpi4-intel-neural-stick.jpg" imageanchor="1"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgNPtKH3m9K4NfQjWPcoeJvfryqhhkyNPYadtnH_Q1OS4CYxiBcG6Ivgy965Id_rpMCaWmAWa_izFGkJT0xHbM4Vv-y-TNyDwjzs32LT2uZLTIg1wQBHMqO39tIsCqa14g07lfWG0zc0mm8/s320/raspberrpi4-intel-neural-stick.jpg" width="320" /></a><br />
<h3>
<b><span style="color: blue; font-size: small;">Compare with Raspberry pi 3B+ , 4 and Intel AI Stick 1 ,2</span></b></h3>
<div>
<b>Raspberry pi 4 + Intel AI stick 2 </b><br />
Frame rate 25 fps</div>
<div>
<b><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh9RtLw-48YwS1R12RHr3yDe1OZUGRN87FF5UKdm3CU1QtBmF-aPCxi6HQWg87mIubzwpVdzv5TvkQAIB1eu8Bg-QThjyaj3UcZgHm7o1YoGIK7PuvTE6W4zu5xRflBDVFWnLXfaLOVamSs/s1600/raspberrypi4-car-detect-ncs2.png" imageanchor="1"><img border="0" height="287" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh9RtLw-48YwS1R12RHr3yDe1OZUGRN87FF5UKdm3CU1QtBmF-aPCxi6HQWg87mIubzwpVdzv5TvkQAIB1eu8Bg-QThjyaj3UcZgHm7o1YoGIK7PuvTE6W4zu5xRflBDVFWnLXfaLOVamSs/s400/raspberrypi4-car-detect-ncs2.png" width="400" /></a></b></div>
<div>
<b><br /></b></div>
<div>
<b>Raspberry pi 4 + Intel AI stick 1</b><br />
Frame rate 8 fps</div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi2q3I8asvrVnse49gw5oU7ZiGXx0ZET9LlAyZtsq9wy60gYTlx7py9sfw9xqz1750pcIxMjFndguTmYkJwYYmEqUIF44BED6iZGZG6nhygY8Gb6A7gGVjfC6BC7fBg9-DS0IrhiPv1hz0w/s1600/raspberrypi4-car-detection-ncs1.png" imageanchor="1"><img border="0" height="288" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi2q3I8asvrVnse49gw5oU7ZiGXx0ZET9LlAyZtsq9wy60gYTlx7py9sfw9xqz1750pcIxMjFndguTmYkJwYYmEqUIF44BED6iZGZG6nhygY8Gb6A7gGVjfC6BC7fBg9-DS0IrhiPv1hz0w/s400/raspberrypi4-car-detection-ncs1.png" width="400" /></a><br />
<br />
<br />
<b>Raspberry pi 3B+ and Intel AI stick 2</b><br />
Frame rate 14 fps<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVOMyK3z1D-EXEUCCBbaaAENbkOGaGQEwPIzGNxMe_ZY-0_d5ZIjbs1iihRsmbh8ZoMgjW68FXBTSnj6VEspXsEP4Er-s61hjn59YEenjClLDSVOFfsxx8C3amm799sexKNATuGQi9IuQq/s1600/raspberrypi3-car-detection-ncs2.png" imageanchor="1"><img border="0" height="295" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVOMyK3z1D-EXEUCCBbaaAENbkOGaGQEwPIzGNxMe_ZY-0_d5ZIjbs1iihRsmbh8ZoMgjW68FXBTSnj6VEspXsEP4Er-s61hjn59YEenjClLDSVOFfsxx8C3amm799sexKNATuGQi9IuQq/s400/raspberrypi3-car-detection-ncs2.png" width="400" /></a><br />
<br />
<br />
<b>Raspberry pi 3B+ and Intel AI stick 1</b><br />
Frame rate 25 fps<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiuAQ5hd3oIXZMDdq5USGSr1D2TxJL9N7hxdKMUO2X2H9M1Pe-lX4buNMLzYsd7V5FZsGKzoVFsHbEYzWPz1Waa_KAZC0nslr1YWiz8kHSb9NOVLUjgLIcq69nZbDqc8Kd0yc-WUa0hwTMr/s1600/raspberrypi3-car-detection-ncs1.png" imageanchor="1"><img border="0" height="286" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiuAQ5hd3oIXZMDdq5USGSr1D2TxJL9N7hxdKMUO2X2H9M1Pe-lX4buNMLzYsd7V5FZsGKzoVFsHbEYzWPz1Waa_KAZC0nslr1YWiz8kHSb9NOVLUjgLIcq69nZbDqc8Kd0yc-WUa0hwTMr/s400/raspberrypi3-car-detection-ncs1.png" width="400" /></a><br />
<br />
<b>Summary</b><br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjrrbB1gyNPpelbrTe6c4kcT5ZNbvTJ4Ia1UMoW8UJT75Rf-Ju5bPQ3LUB4lOpFoZR4ays_BBU76-0j5e38-dI9-qxWRrbhSAcgMH8x2pZn9i9-rLBeRgalnYRxpZApjEnEp7Q-Nn9yW7I2/s1600/raspberrypi4-vs-Raspberrypi3.png" imageanchor="1"><img border="0" height="121" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjrrbB1gyNPpelbrTe6c4kcT5ZNbvTJ4Ia1UMoW8UJT75Rf-Ju5bPQ3LUB4lOpFoZR4ays_BBU76-0j5e38-dI9-qxWRrbhSAcgMH8x2pZn9i9-rLBeRgalnYRxpZApjEnEp7Q-Nn9yW7I2/s400/raspberrypi4-vs-Raspberrypi3.png" width="400" /></a><br />
<br />
<br />
<h3>
<b>Retrain Model with your own dataset. </b></h3>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEihVPmPwMkEwouWwlAl78aVqm9sT8RNx4t7x1iK05I94TZ5tDX7g4jXxUCt74Qd406xIhvc_6_WBY8MYvXn1ov29glwgm8UTYpZzIg_VAsPTti0LgiGrGVgynks6g5PGBnDMYPfyjpEP-al/s1600/Screen+Shot+2562-08-26+at+12.07.51.png" imageanchor="1"><img border="0" height="376" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEihVPmPwMkEwouWwlAl78aVqm9sT8RNx4t7x1iK05I94TZ5tDX7g4jXxUCt74Qd406xIhvc_6_WBY8MYvXn1ov29glwgm8UTYpZzIg_VAsPTti0LgiGrGVgynks6g5PGBnDMYPfyjpEP-al/s640/Screen+Shot+2562-08-26+at+12.07.51.png" width="640" /></a><br />
<a href="https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10">https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10</a><br />
<br />
<div style="background-color: white; color: #666666; font-family: calibri; font-size: 11pt;">
<b style="font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 16px;">Reference</b></div>
<div style="background-color: white; color: #666666; font-family: calibri; font-size: 11pt;">
<b style="font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 16px;"><br /></b></div>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif; font-size: 13.2px;">Install OpenVINO™ toolkit for Raspbian* OS</span><br />
<div style="background-color: white; color: #666666; font-family: calibri; font-size: 11pt;">
<a href="https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html" style="color: #888888; text-decoration-line: none;">https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html</a></div>
<div style="background-color: white; color: #666666; font-family: calibri; font-size: 11pt;">
<br /></div>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif; font-size: 13.2px;">Object Detection SSD Python* Demo, Async API performance showcase</span><br />
<a href="https://docs.openvinotoolkit.org/latest/_demos_python_demos_object_detection_demo_ssd_async_README.html" style="background-color: white; color: #888888; font-family: calibri; font-size: 13.2px; text-decoration-line: none;">https://docs.openvinotoolkit.org/latest/_demos_python_demos_object_detection_demo_ssd_async_README.html</a><br />
<br />
<div class="flex-auto min-width-0 width-fit mr-3" style="box-sizing: border-box; flex: 1 1 auto !important; margin-right: 16px !important; max-width: 100%; min-width: 0px !important;">
<h1 class="public d-flex flex-wrap flex-items-center break-word float-none " style="align-items: center !important; box-sizing: border-box; color: #586069; display: flex !important; flex-wrap: wrap !important; float: none !important; margin: 0px; min-height: 32px; overflow-wrap: break-word !important; position: relative; word-break: break-word !important;">
<span class="mr-2 flex-self-stretch" itemprop="name" style="align-self: stretch !important; box-sizing: border-box; margin-right: 8px !important;"><a data-pjax="#js-repo-pjax-container" href="https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10" style="box-shadow: none; box-sizing: border-box; color: #0366d6; outline: none;"><span style="font-size: small; font-weight: normal;">TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10</span></a></span></h1>
</div>
<ul class="pagehead-actions flex-shrink-0 " style="box-sizing: border-box; flex-shrink: 0 !important; float: right; margin: 0px; padding-left: 0px; position: relative; z-index: 31;">
<li style="box-sizing: border-box; color: #24292e; float: left; list-style-type: none; margin: 0px 10px 0px 0px;"><form accept-charset="UTF-8" action="https://github.com/notifications/subscribe" class="clearfix js-social-form js-social-container" data-remote="true" method="post" style="box-sizing: border-box;">
<br />
<br />
<br />
<details class="details-reset details-overlay select-menu float-left" style="background-color: #fafbfc; box-sizing: border-box; float: left !important; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; position: relative;"><summary aria-haspopup="menu" class="select-menu-button float-left btn btn-sm btn-with-count" data-ga-click="Repository, click Watch settings, action:files#disambiguate" data-hydro-click-hmac="017085de46b4f74fc66c51791ce8636ac51cb22716fffe77d829a48aa5b370d1" data-hydro-click="{"event_type":"repository.click","payload":{"target":"WATCH_BUTTON","repository_id":120985410,"originating_url":"https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10","user_id":12647290}}" role="button" style="-webkit-appearance: none; background-color: #eff3f6; background-image: linear-gradient(-180deg, rgb(250, 251, 252), rgb(239, 243, 246) 90%); background-position: -1px -1px; background-repeat: repeat-x; background-size: 110% 110%; border-radius: 0.25em 0px 0px 0.25em; border: 1px solid rgba(27, 31, 35, 0.2); box-sizing: border-box; cursor: pointer; display: inline-block; float: left !important; font-weight: 600; line-height: 20px; list-style: none; padding: 3px 10px; position: relative; user-select: none; vertical-align: middle; white-space: nowrap;"><span data-menu-button="" style="box-sizing: border-box;"><svg aria-hidden="true" class="octicon octicon-eye v-align-text-bottom" height="16" version="1.1" viewbox="0 0 16 16" width="16"><path d="M8.06 2C3 2 0 8 0 8s3 6 8.06 6C13 14 16 8 16 8s-3-6-7.94-6zM8 12c-2.2 0-4-1.78-4-4 0-2.2 1.8-4 4-4 2.22 0 4 1.8 4 4 0 2.22-1.78 4-4 4zm2-4c0 1.11-.89 2-2 2-1.11 0-2-.89-2-2 0-1.11.89-2 2-2 1.11 0 2 .89 2 2z" fill-rule="evenodd"></path></svg> Watch </span></summary></details></form>
</li>
</ul>
<a href="https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10"><span style="font-size: x-small;">https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10</span></a>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-85195821723189732132020-02-22T01:17:00.000-08:002020-04-08T23:49:14.939-07:00Raspberry pi Smart cam with Intel Neural Compute Stick<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/JBXodt3p_Q0" width="560"></iframe>
<br />
<h2>
<b><span style="color: magenta; font-size: large;">Raspberry pi Smart cam with Intel Neural Compute Stick</span></b></h2>
<b>Intel Neural Compute Stick + OpenVINO Version</b><br />
<br />
<br />
<b>System Diagram</b><br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjGh8kEMiFqJiK6ZBFb9h8vZHbpbh9mPw7EtcjVKYYS221vrmIcYZW8r5XP534iocEhBw2kA9gSC6F0vXDzKPK565ybX8cBhFp9cBk4lYyiv0hBo_EyxttKm43gYePUSF6lDgQIZe0kIH0q/s1600/Raspberrypi-smartcam-diagram.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="511" data-original-width="812" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjGh8kEMiFqJiK6ZBFb9h8vZHbpbh9mPw7EtcjVKYYS221vrmIcYZW8r5XP534iocEhBw2kA9gSC6F0vXDzKPK565ybX8cBhFp9cBk4lYyiv0hBo_EyxttKm43gYePUSF6lDgQIZe0kIH0q/s640/Raspberrypi-smartcam-diagram.png" width="640" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<h3 style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; margin: 0px; position: relative;">
<span style="font-family: "angsana new";"><span style="font-size: small;">System Requirements</span></span></h3>
<div>
<span style="font-family: "angsana new";"><br /></span></div>
<div class="MsoNormal" style="background-color: white; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<span style="font-family: "angsana new";"><b>Hardware</b><o:p></o:p></span></div>
<div class="MsoListParagraphCxSpFirst" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: xx-small;"><span style="color: black; font-family: "symbol";"><span style="font-size: xx-small;">·</span><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"><span style="font-size: xx-small;"> </span><span style="font-size: x-small;"> </span></span></span><span style="font-size: x-small;"><span style="color: black; font-family: "angsana new";">Raspberry Pi Board (4B , 3B+)</span><span style="color: black; font-family: "angsana new";"><o:p></o:p></span></span></span><br />
<span style="font-size: xx-small;"><span style="font-size: x-small;"><span style="color: black; font-family: "angsana new";"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> Intel Neural Compute Stick ( V1 or V2 )</span></span></span></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">Pi Camera ( V1 or V2 ) or USB cam<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">SD Card 32GB<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">5V DC. 2A Power Supply</span></span><br />
<span style="font-size: x-small;"><span style="color: black; font-family: "angsana new";"><br /></span></span></div>
<div class="MsoNormal" style="background-color: white; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b style="font-family: "angsana new";">Software</b></div>
<div class="MsoListParagraphCxSpFirst" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: xx-small;"><span style="color: black; font-family: "symbol"; font-size: xx-small;">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new"; font-size: x-small;">OS Raspbien 10 ( Buster )<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">Python 3.7.3<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">OpenVINO Toolkit 2019.R3<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<div style="font-family: calibri;">
<span style="color: black; font-family: "symbol"; font-size: x-small;">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new"; font-size: x-small;">OpenCV 4.0.0</span></div>
<div style="font-family: calibri;">
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> Flask 1.0.2</span></span></span></div>
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black;"><span style="font-stretch: normal; line-height: normal;"><span style="color: black;"><span style="font-family: "calibri";"><br />·</span><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span><span style="font-stretch: normal; line-height: normal;">LINE Notify 0.1.4</span></span></span></span></span><br />
<div style="font-family: calibri;">
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black; font-family: "symbol";"><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"><br /></span></span></span></div>
<div style="font-family: calibri;">
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black; font-family: "symbol";"><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;">Detect up to 12 FPS. on Pi camara V2</span></span></span></div>
<div style="font-family: calibri;">
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black; font-family: "symbol";"><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"><br /></span></span></span></div>
<div style="font-family: calibri;">
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA0tFoFquyaIYJwE7-3091jmRGakNFUrdj0xig1CCy2vtjxqlfC_iHM2Y927ryNAVxf9sRG1MU1cIuWkD1kxT0lhJBnNMqmcxsV9p8mAapTdYOnfE8yPaZrXlzZ1qEefpGjYFzE7FFCwnb/s1600/raspberrpi-smartcam-ncs+copy.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="1027" data-original-width="1600" height="256" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA0tFoFquyaIYJwE7-3091jmRGakNFUrdj0xig1CCy2vtjxqlfC_iHM2Y927ryNAVxf9sRG1MU1cIuWkD1kxT0lhJBnNMqmcxsV9p8mAapTdYOnfE8yPaZrXlzZ1qEefpGjYFzE7FFCwnb/s400/raspberrpi-smartcam-ncs+copy.jpg" width="400" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<span style="color: black; font-family: "angsana new"; font-size: x-small;"><span style="color: black; font-family: "symbol";"><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjEOhTlCoJxes6kKw3mRy_Igw7DaZi-0EE1j4D3SdZslrssgzgJbyBv1ZadS117B_3Af8zqkA4H9PQ44T4KccFXZvwHls90iOMopGuKyq6T7LT5a0y7jaGznmsPCuXibwB_OOn_HYKIbVLX/s1600/img2020-02-01-160029.jpg" imageanchor="1"><img border="0" height="300" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjEOhTlCoJxes6kKw3mRy_Igw7DaZi-0EE1j4D3SdZslrssgzgJbyBv1ZadS117B_3Af8zqkA4H9PQ44T4KccFXZvwHls90iOMopGuKyq6T7LT5a0y7jaGznmsPCuXibwB_OOn_HYKIbVLX/s400/img2020-02-01-160029.jpg" width="400" /></a></span></span></span></div>
</div>
<div class="MsoListParagraphCxSpLast" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt;">
<br />
<br />
Setting<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgO-UD5e3RGoW62GcEIw7K2FLgoxXNZNlkCTAiie70eu6AYaujadtQiWUBsEqpSbxtEO9_UVsS1B9_ElKX76umFLdTU7sVlViEsMTdKZt9aaXcuyvVyDeGYllnwCqKoftstY9xkrt7ysEWN/s1600/Screen+Shot+2563-02-07+at+23.11.39.png" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" height="250" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgO-UD5e3RGoW62GcEIw7K2FLgoxXNZNlkCTAiie70eu6AYaujadtQiWUBsEqpSbxtEO9_UVsS1B9_ElKX76umFLdTU7sVlViEsMTdKZt9aaXcuyvVyDeGYllnwCqKoftstY9xkrt7ysEWN/s400/Screen+Shot+2563-02-07+at+23.11.39.png" width="400" /></a></div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
Report ( Save to database )<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgJeJUSau2K9yr-iAB1vRZ6u6TA_AsNKiA9iTCPlG3lDhk8xkU1LD3phmZHd7j0dOLTA2bA5DdSutIQNJpBUtLynGXNrImgITF2LEbQEPFQ7URDkTPfAV5eKSOzEuvUq_XGR9GNZjDDWP0S/s1600/Screen+Shot+2563-02-07+at+23.24.56.png" imageanchor="1"><img border="0" height="250" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgJeJUSau2K9yr-iAB1vRZ6u6TA_AsNKiA9iTCPlG3lDhk8xkU1LD3phmZHd7j0dOLTA2bA5DdSutIQNJpBUtLynGXNrImgITF2LEbQEPFQ7URDkTPfAV5eKSOzEuvUq_XGR9GNZjDDWP0S/s400/Screen+Shot+2563-02-07+at+23.24.56.png" width="400" /></a><br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhFMvnrj6_PxJ6qgal1ib7bJC9zqIw3cM5cVuo9vKfGQdZietprWsNEeqqMdIYomnzFKNqun_qC0WsqRzYscag4n06rpSQZmQ1laEnwXaqQUijSl4cULF2Dd9ggAeQviPi9eL1RTJK_kqkt/s1600/line-notify.png" imageanchor="1"><img border="0" height="112" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhFMvnrj6_PxJ6qgal1ib7bJC9zqIw3cM5cVuo9vKfGQdZietprWsNEeqqMdIYomnzFKNqun_qC0WsqRzYscag4n06rpSQZmQ1laEnwXaqQUijSl4cULF2Dd9ggAeQviPi9eL1RTJK_kqkt/s200/line-notify.png" width="200" /></a><br />
LINE Notify<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjQhs3w_ElUnaFg7Zorb8QYZbo1maGUFALMc5y7SHfKD9Y9tx-zE_jM_lxnE1T4DGWf4ERmXY0CskjufYrv_gBIWipbo6Rvg0mLdBy42iZ5rNYBWM4V54HcxK0UyWXxEMjycMq18vL4Uuve/s1600/Screen+Shot+2563-02-08+at+12.01.17.png" imageanchor="1"><img border="0" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjQhs3w_ElUnaFg7Zorb8QYZbo1maGUFALMc5y7SHfKD9Y9tx-zE_jM_lxnE1T4DGWf4ERmXY0CskjufYrv_gBIWipbo6Rvg0mLdBy42iZ5rNYBWM4V54HcxK0UyWXxEMjycMq18vL4Uuve/s320/Screen+Shot+2563-02-08+at+12.01.17.png" width="212" /></a><br />
<br />
<br />
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgZ498HDnq5wSnquB5XcOm7V9IQ_kWACqacKkbxCjsA37MIwvYdcnv5R_InaJkCwu3qF-5988csCSUktVe8H5ltafxavnHItNQ5TAUHy5uJaAq-ddNA62BbPP80w5xom3OBCkfPbEzdjkJ0/s1600/raspberrypi-smartcam-picam.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="717" data-original-width="1199" height="191" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgZ498HDnq5wSnquB5XcOm7V9IQ_kWACqacKkbxCjsA37MIwvYdcnv5R_InaJkCwu3qF-5988csCSUktVe8H5ltafxavnHItNQ5TAUHy5uJaAq-ddNA62BbPP80w5xom3OBCkfPbEzdjkJ0/s320/raspberrypi-smartcam-picam.jpg" width="320" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<div style="color: #666666; font-family: calibri;">
<span style="font-size: small;"><b>Raspberry pi Smart Cam AI kit. </b>( Include Full Source Code in SD card )</span></div>
<div class="MsoListParagraphCxSpFirst" style="border: none; text-indent: -18pt;">
<br />
<ol>
<li><span style="font-family: inherit;"><span style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"><span style="font-size: small;"><span style="color: #666666;"> </span></span></span><span style="color: #444444; font-size: small;">Raspberry pi 4B ( 1 GB ) + Case<o:p></o:p></span></span></li>
<li><span style="color: #444444; font-family: inherit; font-size: small;"><span style="mso-list: Ignore;"><span style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"> </span></span>SDcard 32 GB.<span dir="RTL"></span><span dir="RTL"></span><span dir="RTL"><span dir="RTL"></span><span dir="RTL"></span> </span><span dir="LTR"></span><span dir="LTR"></span><span dir="LTR"></span><span dir="LTR"></span>( Software installed )</span></li>
<li><span style="color: #444444; font-family: inherit; font-size: small;"><span style="mso-list: Ignore;"><span style="font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: normal;"> </span></span>5V DC. 2A Power Supply</span></li>
</ol>
</div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; margin-left: 18pt;">
<span style="color: #444444; font-family: inherit; font-size: small;">Option</span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none;">
<ul>
<li><span style="color: #444444; font-family: inherit; font-size: small;">USB Webcam Model Logitech C270 </span></li>
<li><span style="font-family: inherit;"><span style="color: #444444; font-size: small;">Intel Neural Compute Stick2<span style="mso-spacerun: yes;"> </span></span></span></li>
</ul>
</div>
<div style="font-family: calibri;">
<b><span style="color: blue;">If You want Raspberry pi AI Kit.</span></b><span style="font-size: 11pt;"><span style="color: blue;"> </span><span style="color: #666666;"><b>Please contact email amphancm@gmail.com </b></span></span><br />
<div style="color: #666666;">
<div style="font-size: 11pt;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgELTWHnJIUVbiBOT_c7tzoeQhUl-QqcrVQcyXDF5m5_kV_HAj9OOxLRVkODIKqv__ufTxtdTjk2V8RwVgoNN8VZRZYBoeAU7VM_eWMP99htlPUkRWLEo3Z_AVC2M-JR3TsXxCms-KctAVu/s1600/ncs2-lid-box.png" imageanchor="1"><img border="0" height="205" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgELTWHnJIUVbiBOT_c7tzoeQhUl-QqcrVQcyXDF5m5_kV_HAj9OOxLRVkODIKqv__ufTxtdTjk2V8RwVgoNN8VZRZYBoeAU7VM_eWMP99htlPUkRWLEo3Z_AVC2M-JR3TsXxCms-KctAVu/s320/ncs2-lid-box.png" width="320" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA4gFlR2ZLtzfB22z8FEtU04QLpPbMVtmIciQaGsgjYgVA3ogGCR2e6NooRgrWdgKvjKOYLSrxxlna9mSFjBL5flhwhxm1SUanKz3SlPSY8l9k9KSv0OjBeeW7v0xL4GeP4hMyWG5-LqZQ/s1600/logitechC270.png" imageanchor="1"><img border="0" height="160" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA4gFlR2ZLtzfB22z8FEtU04QLpPbMVtmIciQaGsgjYgVA3ogGCR2e6NooRgrWdgKvjKOYLSrxxlna9mSFjBL5flhwhxm1SUanKz3SlPSY8l9k9KSv0OjBeeW7v0xL4GeP4hMyWG5-LqZQ/s200/logitechC270.png" width="200" /></a><br />
<br />
<br />
<h3>
<b>UPDATE ( 2020 APR )</b></h3>
Select time to Line Notification<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIxb-RnP0Pj6zbaXM40Jlo1eo_tEsI7ym0PVR73V9IUxG90Bf9F3Q2b5NYdgepAW1GYUyrWI1mrwXNSEHTzr5z3nf-1ITL_nv14IMIuxh4NifwtjVENFoccUXJcR9BJoRaWN_CcZk-Zrxw/s1600/Screen+Shot+2563-04-09+at+12.49.47.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="625" data-original-width="1263" height="315" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIxb-RnP0Pj6zbaXM40Jlo1eo_tEsI7ym0PVR73V9IUxG90Bf9F3Q2b5NYdgepAW1GYUyrWI1mrwXNSEHTzr5z3nf-1ITL_nv14IMIuxh4NifwtjVENFoccUXJcR9BJoRaWN_CcZk-Zrxw/s640/Screen+Shot+2563-04-09+at+12.49.47.png" width="640" /></a></div>
<br />
<br />
<br /></div>
<div style="font-size: 11pt;">
<b style="background-color: white; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 16px;">Reference</b></div>
<div style="font-size: 11pt;">
<b style="background-color: white; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 16px;"><br /></b></div>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;">Install OpenVINO™ toolkit for Raspbian* OS</span><br />
<div style="font-size: 11pt;">
<a href="https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html">https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html</a></div>
<div style="font-size: 11pt;">
<br /></div>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;">Object Detection SSD Python* Demo, Async API performance showcase</span><br />
<a href="https://docs.openvinotoolkit.org/latest/_demos_python_demos_object_detection_demo_ssd_async_README.html">https://docs.openvinotoolkit.org/latest/_demos_python_demos_object_detection_demo_ssd_async_README.html</a><br />
<br />
<br />
<div style="font-size: 11pt;">
<br /></div>
</div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-36870121722013024272020-02-02T09:16:00.000-08:002020-02-04T23:37:51.368-08:00Raspberry pi Smart cam AI kit with Pi Cam<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/SKf-1toDkPA" width="560"></iframe>
<br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<h2 style="background-color: white; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; margin: 0px; position: relative;">
<span style="color: blue; font-family: "angsana new"; font-size: large;">Raspberry pi Smart cam AI kit with Pi Cam or USB cam</span></h2>
<div>
<span style="color: #444444; font-family: "angsana new"; font-size: large;">TensorFlow-lite Version </span><span style="color: #444444; font-family: "angsana new"; font-size: medium;">then no need intel Neural Compute Stick ye</span><span style="color: #444444; font-family: "angsana new"; font-size: medium;">t.</span></div>
<div>
<span style="color: blue; font-family: "angsana new"; font-size: large;"><br /></span></div>
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<span style="font-family: "angsana new";"><span style="font-size: x-small;"><br /></span></span></h3>
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<span style="font-family: "angsana new";"><span style="font-size: small;">System Diagram</span></span></h3>
<div>
<span style="font-family: "angsana new";"><span style="font-size: x-small;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiQIrHx3mV-UzSfmlo4Rxu2jxtnhzulymUmyuBKtgiJq22K-on4DG2SDuzJHjuUfd86M5t54V5c6u2hLnINu1-w8INbrlzxYdctByrG7LASYLlN1Zns0-kLWHZWS5nQVKDwYVNKmUmULMiQ/s1600/Raspberrypi-smartcam-diagram.png" imageanchor="1" style="font-family: Times; font-size: medium; margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="511" data-original-width="812" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiQIrHx3mV-UzSfmlo4Rxu2jxtnhzulymUmyuBKtgiJq22K-on4DG2SDuzJHjuUfd86M5t54V5c6u2hLnINu1-w8INbrlzxYdctByrG7LASYLlN1Zns0-kLWHZWS5nQVKDwYVNKmUmULMiQ/s640/Raspberrypi-smartcam-diagram.png" width="640" /></a></span></span></div>
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<span style="font-family: "angsana new";"><span style="font-size: small;">System Requirements</span></span></h3>
<div>
<span style="font-family: "angsana new";"><span style="font-size: small;"><br /></span></span></div>
<div class="MsoNormal" style="background-color: white; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<span style="font-family: "angsana new";"><b>Hardware</b><o:p></o:p></span></div>
<div class="MsoListParagraphCxSpFirst" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: xx-small;"><span style="color: black; font-family: "symbol";"><span style="font-size: xx-small;">·</span><span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"><span style="font-size: xx-small;"> </span><span style="font-size: x-small;"> </span></span></span><span style="font-size: x-small;"><span style="color: black; font-family: "angsana new";">Raspberry Pi Board (4B , 3B+)</span><span style="color: black; font-family: "angsana new";"><o:p></o:p></span></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">Pi Camera ( V1 or V2 ) or USB cam<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">SD Card 32GB<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">5V DC. 2A Power Supply</span></span></div>
<div class="MsoNormal" style="background-color: white; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<b style="font-family: "angsana new";">Software</b></div>
<div class="MsoListParagraphCxSpFirst" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: xx-small;"><span style="color: black; font-family: "symbol"; font-size: xx-small;">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new"; font-size: x-small;">OS Raspbien 10 ( Buster )<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">Python 3.7.3<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">Tensorflow lite 1.14.0<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt; text-indent: -18pt;">
<span style="font-size: x-small;"><span style="color: black; font-family: "symbol";">·<span style="font-family: "times new roman"; font-stretch: normal; line-height: normal;"> </span></span><span style="color: black; font-family: "angsana new";">OpenCV 4.0.0</span></span></div>
<div class="MsoListParagraphCxSpLast" style="background-color: white; border: none; color: #666666; font-family: calibri; margin: 0cm 0cm 0.0001pt 36pt;">
<br /></div>
<div class="MsoNormal" style="background-color: white; border: none; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<span style="color: black; font-family: "angsana new";"><span style="font-size: xx-small;">Machine Learning Model : MobileNet SSD V2</span><span style="font-size: xx-small;"> <o:p></o:p></span></span><span style="font-family: "angsana new";">Quantised</span><br />
<div>
<span style="font-family: "angsana new"; font-size: xx-small;"><br /></span></div>
<div>
<span style="font-family: "angsana new"; font-size: x-small;"><br /></span></div>
<span style="font-family: "angsana new";"><b>Main Page ( Home )</b></span></div>
<div class="MsoNormal" style="background-color: white; border: none; color: #666666; font-family: calibri; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<div style="font-size: 11pt;">
<span style="font-family: "angsana new"; font-size: x-small;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEidzhlEupHDHJneIlaYOvfyDv_CP2l_6CiouC6wuv5YSBAUUKS1c6rVxe1D8_Cvpa_c30fxPYgH316nKgQvtCg3F5x9WI0XXc9U8CGH_XOLuK7p5qes8xHhPxSVjoVY4aUqSXVSgo237VV1/s1600/raspberrypi-picam-tfile.png" imageanchor="1"><img border="0" height="312" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEidzhlEupHDHJneIlaYOvfyDv_CP2l_6CiouC6wuv5YSBAUUKS1c6rVxe1D8_Cvpa_c30fxPYgH316nKgQvtCg3F5x9WI0XXc9U8CGH_XOLuK7p5qes8xHhPxSVjoVY4aUqSXVSgo237VV1/s640/raspberrypi-picam-tfile.png" width="640" /></a></span></div>
<div class="separator" style="clear: both; font-size: 11pt; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; font-size: 11pt; text-align: center;">
</div>
<div style="font-size: 11pt;">
<br /></div>
<div style="font-size: 11pt;">
<br /></div>
<span style="font-family: "angsana new";"><b>Report Page</b></span><br />
<div style="font-size: 11pt;">
<span style="font-family: "angsana new"; font-size: x-small;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjlcWF5azu8AiHdkp8vhysja68olocm4xpYc4wj-ZxfItmVN8hUbQzmzHwdjhpp_kHYL5vD_TOf3BGhyRsGLw6NGeC-GqpdObf-EGQRFkON7XIeR_dCB6QGjLWGnZnwREEys6KoT33sH8zN/s1600/Smartcam-report.png" imageanchor="1"><img border="0" height="376" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjlcWF5azu8AiHdkp8vhysja68olocm4xpYc4wj-ZxfItmVN8hUbQzmzHwdjhpp_kHYL5vD_TOf3BGhyRsGLw6NGeC-GqpdObf-EGQRFkON7XIeR_dCB6QGjLWGnZnwREEys6KoT33sH8zN/s640/Smartcam-report.png" width="640" /></a></span></div>
<span style="font-family: "angsana new";"><b>Setting Page</b></span><br />
<div style="font-size: 11pt;">
<span style="font-family: "angsana new"; font-size: x-small;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhTXRwbFuF_C9_y5BpMzNu4mWV7Z2suvfg0dpwisnyTR-E9BQTlgmNHJznDg1PkzqC39-2kteL4bN7yPVD6hPeOIymgIL1YwaVh83eKi-dFT6Z4S8oZKMnqOK_bC_AWf-n9TtDY0In99rsn/s1600/smartcam-setting-page.png" imageanchor="1"><img border="0" height="376" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhTXRwbFuF_C9_y5BpMzNu4mWV7Z2suvfg0dpwisnyTR-E9BQTlgmNHJznDg1PkzqC39-2kteL4bN7yPVD6hPeOIymgIL1YwaVh83eKi-dFT6Z4S8oZKMnqOK_bC_AWf-n9TtDY0In99rsn/s640/smartcam-setting-page.png" width="640" /></a></span></div>
<div style="font-size: 11pt;">
<br /></div>
<b>Set WiFi</b><br />
<div style="font-size: 11pt;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi3m9tWbjUYQBRtzwHWvQ5AeO4HU_frWmE2Ki7316eKQA6pqrhQV-hztbPn8rUHtnT41J55eycz829KwUZKoxNoWOg-gLAsNM6SLXtqHfWZfusMub2tn4ijO-doBL1krsTGbnvwcZxs-sEC/s1600/Smartcam-setwifi.png" imageanchor="1"><img border="0" height="376" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi3m9tWbjUYQBRtzwHWvQ5AeO4HU_frWmE2Ki7316eKQA6pqrhQV-hztbPn8rUHtnT41J55eycz829KwUZKoxNoWOg-gLAsNM6SLXtqHfWZfusMub2tn4ijO-doBL1krsTGbnvwcZxs-sEC/s640/Smartcam-setwifi.png" width="640" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg9Vc1BE_BRCjomO0Hmn7jrnXu4KIEITtFm-mSzuON2KXomBLZHugEalBhep6K7iEad4o2F3z561pKcwdhDeh1ndYC7C8MUPPk4MH7jGJWLoM51VgpBKcAXLbRCnu4j_g1uwgyzVro2aZMr/s1600/Python+%25281%2529.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: left;"><img border="0" data-original-height="200" data-original-width="273" height="146" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg9Vc1BE_BRCjomO0Hmn7jrnXu4KIEITtFm-mSzuON2KXomBLZHugEalBhep6K7iEad4o2F3z561pKcwdhDeh1ndYC7C8MUPPk4MH7jGJWLoM51VgpBKcAXLbRCnu4j_g1uwgyzVro2aZMr/s200/Python+%25281%2529.png" width="200" /></a></div>
</div>
<div class="MsoNormal" style="background-color: white; border: none; line-height: 15.6933px; margin: 0cm 0cm 8pt;">
<div style="color: #666666; font-family: calibri;">
<b style="font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">Source Code ( Python )</b></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<a href="https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi" style="color: #954f72; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;">https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi</a></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgw_JoxiUFizDqqZn65DKeAJyLUA7J8zmcD7KDfOBwFMlBt-Cgi5W6r46ArWtekRafZLMh92nBfL22h4FFPIi4k79MtDaumiZDQ8v2aRjJJx1ZBsovnOWIRf1zMvTG1amV7DBMhAxorjPU2/s1600/raspberrypi-smartcam-picam.jpg" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="717" data-original-width="1199" height="237" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgw_JoxiUFizDqqZn65DKeAJyLUA7J8zmcD7KDfOBwFMlBt-Cgi5W6r46ArWtekRafZLMh92nBfL22h4FFPIi4k79MtDaumiZDQ8v2aRjJJx1ZBsovnOWIRf1zMvTG1amV7DBMhAxorjPU2/s400/raspberrypi-smartcam-picam.jpg" width="400" /></a><br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br /></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br /></div>
<div style="color: #666666; font-family: calibri;">
<span style="font-size: small;"><b>Raspberry pi Smart Cam AI kit. ( Include Full Source Code in SD card )</b></span></div>
<div class="MsoListParagraphCxSpFirst" style="border: none; text-indent: -18pt;">
<br />
<ol>
<li><span style="font-family: inherit;"><span style="font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"><span style="font-size: small;"><span style="color: #666666;"> </span></span></span><span style="color: #444444; font-size: small;">Raspberry pi 4B ( 1 GB ) + Case<o:p></o:p></span></span></li>
<li><span style="color: #444444; font-family: inherit; font-size: small;"><span style="mso-list: Ignore;"><span style="font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span>SDcard 32 GB.<span dir="RTL"></span><span dir="RTL"></span><span dir="RTL"><span dir="RTL"></span><span dir="RTL"></span> </span><span dir="LTR"></span><span dir="LTR"></span><span dir="LTR"></span><span dir="LTR"></span>( Software installed )</span></li>
<li><span style="color: #444444; font-family: inherit; font-size: small;"><span style="mso-list: Ignore;"><span style="font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span>5V DC. 2A Power Supply</span></li>
</ol>
<!--[if !supportLists]--></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; margin-left: 18pt;">
<span style="color: #444444; font-family: inherit; font-size: small;">Option</span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none;">
<ul>
<li><span style="color: #444444; font-family: inherit; font-size: small;">USB Webcam Model Logitech C270 </span></li>
<li><span style="font-family: inherit;"><span style="color: #444444; font-size: small;">Intel Neural Compute Stick2<span style="mso-spacerun: yes;"> </span></span></span></li>
</ul>
</div>
<div style="font-family: calibri;">
<b><span style="color: blue;">If You want Raspberry pi AI Kit.</span></b><span style="font-size: 11pt;"><span style="color: blue;"> </span><span style="color: #666666;"><b>Please contact email amphancm@gmail.com </b></span></span><br />
<div style="color: #666666; font-size: 11pt;">
<br /></div>
</div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br /></div>
<div style="color: #666666; font-family: calibri;">
<b style="font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">Reference</b></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<b style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;"><br /></b><span style="font-family: "trebuchet ms" , "trebuchet" , "verdana" , sans-serif; font-size: 13.2px;">Install Tensorflow on Raspberry pi</span></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<a href="https://www.tensorflow.org/install/source_rpi" style="color: #954f72; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;">https://www.tensorflow.org/install/source_rpi</a></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<b style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;"><br /></b><span style="font-family: "trebuchet ms" , "trebuchet" , "verdana" , sans-serif; font-size: 13.2px;">Tensorflow Model Zoo</span></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md" style="color: #954f72; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;">https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md</a></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /></div>
<div style="color: #666666; font-family: calibri; font-size: 11pt;">
<br style="font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" /></div>
<div class="p1" style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px;">
<span class="s1" style="font-kerning: none;"><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: x-small;">How to Run TensorFlow Lite Object Detection</span></span></div>
<div class="p1" style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px;">
<span class="s1" style="font-kerning: none;"><span style="font-family: "arial" , "helvetica" , sans-serif; font-size: x-small;"><a href="https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/blob/master/Raspberry_Pi_Guide.md" style="color: #954f72;">https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/blob/master/Raspberry_Pi_Guide.md</a></span></span><br />
<span class="s1" style="font-kerning: none;"><br /></span>
<span class="s1" style="font-kerning: none;"><br /></span></div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com2tag:blogger.com,1999:blog-7853792980726640018.post-79770172045479179642020-01-24T23:41:00.000-08:002020-01-27T08:59:34.743-08:00Raspberry pi TensorFlow-lite Object detection<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/krT4JTg9KJE" width="560"></iframe>
<br />
<br />
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/SQKHJ2BSVjg" width="560"></iframe>
<br />
<h2>
<b><span style="color: magenta; font-size: x-large;">Raspberry pi TensorFlow-lite Object detection</span></b></h2>
How to use TensorFlow Lite object detection models on the Raspberry Pi.<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi6g7Gt88MOXxAVpJGd_Ux-78HppaRbzxELzmZLGZYUANAh0-LxdBGpyQXz7-YXqsCCsQXG6HzWUxLCIQaEqO6HAe2baIbynxz16kYhjcwLmiJPpB2SjRw2Z9a6okZF9NFy25IgWLkn-zTp/s1600/tensorflowlite-logo2.png" imageanchor="1"><img border="0" height="49" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi6g7Gt88MOXxAVpJGd_Ux-78HppaRbzxELzmZLGZYUANAh0-LxdBGpyQXz7-YXqsCCsQXG6HzWUxLCIQaEqO6HAe2baIbynxz16kYhjcwLmiJPpB2SjRw2Z9a6okZF9NFy25IgWLkn-zTp/s320/tensorflowlite-logo2.png" width="320" /></a><br />
<br />
TensorFlow Lite is an optimized framework for deploying lightweight deep learning models on resource-constrained edge devices. TensorFlow Lite models have faster inference time and require less processing power, so they can be used to obtain faster performance in realtime applications.<br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgxkKEHftHf4jHnkY6TxJ7M345oPwXwBL7eCkP_t-xTc6oyW9tn8gilMBG-RbzrvBz5FCh0Y2YZlMnGz_jUEycNJwU9osxykflAd5k-zvygdhD6xLj0i3ZjTEB_tD_nTtOPKhjFYqJ1-Hho/s1600/raspberrypi-tensorflowlite-objectdetection-hardware.jpg" imageanchor="1"><img border="0" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgxkKEHftHf4jHnkY6TxJ7M345oPwXwBL7eCkP_t-xTc6oyW9tn8gilMBG-RbzrvBz5FCh0Y2YZlMnGz_jUEycNJwU9osxykflAd5k-zvygdhD6xLj0i3ZjTEB_tD_nTtOPKhjFYqJ1-Hho/s320/raspberrypi-tensorflowlite-objectdetection-hardware.jpg" width="240" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi1nuutHm5vDP_D3AtdytW0v8_zZlaL-coTr4_B-YKPzjzjyreFKahaBSIOhPCC5MPb198WYD506-SdlTSibpIzkRXHeBxeAOKYRnUOZDoejhKPkBI1OM7CjhgpyYHuBcysQtTzw5lffxGA/s1600/raspberrypi-tensorflowlite-objectdetection-person1.png" imageanchor="1"><img border="0" height="280" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi1nuutHm5vDP_D3AtdytW0v8_zZlaL-coTr4_B-YKPzjzjyreFKahaBSIOhPCC5MPb198WYD506-SdlTSibpIzkRXHeBxeAOKYRnUOZDoejhKPkBI1OM7CjhgpyYHuBcysQtTzw5lffxGA/s400/raspberrypi-tensorflowlite-objectdetection-person1.png" width="400" /></a><br />
<!--[if gte mso 9]><xml>
<o:OfficeDocumentSettings>
<o:RelyOnVML/>
<o:AllowPNG/>
</o:OfficeDocumentSettings>
</xml><![endif]-->
<!--[if gte mso 9]><xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves/>
<w:TrackFormatting/>
<w:PunctuationKerning/>
<w:ValidateAgainstSchemas/>
<w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
<w:IgnoreMixedContent>false</w:IgnoreMixedContent>
<w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
<w:DoNotPromoteQF/>
<w:LidThemeOther>EN-US</w:LidThemeOther>
<w:LidThemeAsian>X-NONE</w:LidThemeAsian>
<w:LidThemeComplexScript>TH</w:LidThemeComplexScript>
<w:Compatibility>
<w:BreakWrappedTables/>
<w:SnapToGridInCell/>
<w:ApplyBreakingRules/>
<w:WrapTextWithPunct/>
<w:UseAsianBreakRules/>
<w:DontGrowAutofit/>
<w:SplitPgBreakAndParaMark/>
<w:EnableOpenTypeKerning/>
<w:DontFlipMirrorIndents/>
<w:OverrideTableStyleHps/>
</w:Compatibility>
<m:mathPr>
<m:mathFont m:val="Cambria Math"/>
<m:brkBin m:val="before"/>
<m:brkBinSub m:val="--"/>
<m:smallFrac m:val="off"/>
<m:dispDef/>
<m:lMargin m:val="0"/>
<m:rMargin m:val="0"/>
<m:defJc m:val="centerGroup"/>
<m:wrapIndent m:val="1440"/>
<m:intLim m:val="subSup"/>
<m:naryLim m:val="undOvr"/>
</m:mathPr></w:WordDocument>
</xml><![endif]--><!--[if gte mso 9]><xml>
<w:LatentStyles DefLockedState="false" DefUnhideWhenUsed="false"
DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="380">
<w:LsdException Locked="false" Priority="0" QFormat="true" Name="Normal"/>
<w:LsdException Locked="false" Priority="9" QFormat="true" Name="heading 1"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 9"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 1"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 2"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 3"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 4"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 5"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 6"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 7"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 8"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="header"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footer"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index heading"/>
<w:LsdException Locked="false" Priority="35" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of figures"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope return"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="line number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="page number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of authorities"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="macro"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="toa heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 5"/>
<w:LsdException Locked="false" Priority="10" QFormat="true" Name="Title"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Closing"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Signature"/>
<w:LsdException Locked="false" Priority="1" SemiHidden="true"
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Message Header"/>
<w:LsdException Locked="false" Priority="11" QFormat="true" Name="Subtitle"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Salutation"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Date"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Block Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Hyperlink"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="FollowedHyperlink"/>
<w:LsdException Locked="false" Priority="22" QFormat="true" Name="Strong"/>
<w:LsdException Locked="false" Priority="20" QFormat="true" Name="Emphasis"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Document Map"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Plain Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="E-mail Signature"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Top of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Bottom of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal (Web)"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Acronym"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Cite"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Code"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Definition"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Keyboard"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Preformatted"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Sample"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Typewriter"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Variable"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Table"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation subject"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="No List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Contemporary"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Elegant"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Professional"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Balloon Text"/>
<w:LsdException Locked="false" Priority="39" Name="Table Grid"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Theme"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 9"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Placeholder Text"/>
<w:LsdException Locked="false" Priority="1" QFormat="true" Name="No Spacing"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading"/>
<w:LsdException Locked="false" Priority="61" Name="Light List"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 1"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 1"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 1"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 1"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 1"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Revision"/>
<w:LsdException Locked="false" Priority="34" QFormat="true"
Name="List Paragraph"/>
<w:LsdException Locked="false" Priority="29" QFormat="true" Name="Quote"/>
<w:LsdException Locked="false" Priority="30" QFormat="true"
Name="Intense Quote"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 1"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 1"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 1"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 1"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 1"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 1"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 1"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 2"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 2"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 2"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 2"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 2"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 2"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 2"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 2"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 2"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 2"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 2"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 3"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 3"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 3"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 3"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 3"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 3"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 3"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 3"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 3"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 3"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 3"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 3"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 3"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 4"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 4"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 4"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 4"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 4"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 4"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 4"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 4"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 4"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 4"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 4"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 4"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 4"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 4"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 5"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 5"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 5"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 5"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 5"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 5"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 5"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 5"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 5"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 5"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 5"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 5"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 5"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 5"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 6"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 6"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 6"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 6"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 6"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 6"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 6"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 6"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 6"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 6"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 6"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 6"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 6"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 6"/>
<w:LsdException Locked="false" Priority="19" QFormat="true"
Name="Subtle Emphasis"/>
<w:LsdException Locked="false" Priority="21" QFormat="true"
Name="Intense Emphasis"/>
<w:LsdException Locked="false" Priority="31" QFormat="true"
Name="Subtle Reference"/>
<w:LsdException Locked="false" Priority="32" QFormat="true"
Name="Intense Reference"/>
<w:LsdException Locked="false" Priority="33" QFormat="true" Name="Book Title"/>
<w:LsdException Locked="false" Priority="37" SemiHidden="true"
UnhideWhenUsed="true" Name="Bibliography"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>
<w:LsdException Locked="false" Priority="41" Name="Plain Table 1"/>
<w:LsdException Locked="false" Priority="42" Name="Plain Table 2"/>
<w:LsdException Locked="false" Priority="43" Name="Plain Table 3"/>
<w:LsdException Locked="false" Priority="44" Name="Plain Table 4"/>
<w:LsdException Locked="false" Priority="45" Name="Plain Table 5"/>
<w:LsdException Locked="false" Priority="40" Name="Grid Table Light"/>
<w:LsdException Locked="false" Priority="46" Name="Grid Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="Grid Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="Grid Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="46" Name="List Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="List Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="List Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 6"/>
</w:LatentStyles>
</xml><![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Courier New";
panose-1:2 7 3 9 2 2 5 2 4 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536859905 -1073711037 9 0 511 0;}
@font-face
{font-family:Wingdings;
panose-1:5 0 0 0 0 0 0 0 0 0;
mso-font-charset:2;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:0 268435456 0 0 -2147483648 0;}
@font-face
{font-family:"Angsana New";
panose-1:2 2 6 3 5 4 5 2 3 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0cm;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Calibri;
mso-bidi-language:AR-SA;}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
{mso-style-priority:34;
mso-style-unhide:no;
mso-style-qformat:yes;
margin-top:0cm;
margin-right:0cm;
margin-bottom:0cm;
margin-left:36.0pt;
margin-bottom:.0001pt;
mso-add-space:auto;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Calibri;
mso-bidi-language:AR-SA;}
p.MsoListParagraphCxSpFirst, li.MsoListParagraphCxSpFirst, div.MsoListParagraphCxSpFirst
{mso-style-priority:34;
mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-type:export-only;
margin-top:0cm;
margin-right:0cm;
margin-bottom:0cm;
margin-left:36.0pt;
margin-bottom:.0001pt;
mso-add-space:auto;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Calibri;
mso-bidi-language:AR-SA;}
p.MsoListParagraphCxSpMiddle, li.MsoListParagraphCxSpMiddle, div.MsoListParagraphCxSpMiddle
{mso-style-priority:34;
mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-type:export-only;
margin-top:0cm;
margin-right:0cm;
margin-bottom:0cm;
margin-left:36.0pt;
margin-bottom:.0001pt;
mso-add-space:auto;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Calibri;
mso-bidi-language:AR-SA;}
p.MsoListParagraphCxSpLast, li.MsoListParagraphCxSpLast, div.MsoListParagraphCxSpLast
{mso-style-priority:34;
mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-type:export-only;
margin-top:0cm;
margin-right:0cm;
margin-bottom:0cm;
margin-left:36.0pt;
margin-bottom:.0001pt;
mso-add-space:auto;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Calibri;
mso-bidi-language:AR-SA;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-fareast-font-family:Calibri;
mso-hansi-font-family:Calibri;
mso-bidi-font-family:Calibri;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;
mso-header-margin:36.0pt;
mso-footer-margin:36.0pt;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:1118260545;
mso-list-type:hybrid;
mso-list-template-ids:-146794382 67698689 67698691 67698693 67698689 67698691 67698693 67698689 67698691 67698693;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Symbol;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:"Courier New";}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;
font-family:Wingdings;}
ol
{margin-bottom:0cm;}
ul
{margin-bottom:0cm;}
-->
</style>
<!--[if gte mso 10]>
<style>
/* Style Definitions */
table.MsoNormalTable
{mso-style-name:"Table Normal";
mso-tstyle-rowband-size:0;
mso-tstyle-colband-size:0;
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-parent:"";
mso-padding-alt:0cm 5.4pt 0cm 5.4pt;
mso-para-margin:0cm;
mso-para-margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;}
</style>
<![endif]-->
<!--StartFragment-->
<br />
<h3>
<span style="font-family: "angsana new";"><span style="font-size: small;">System
Requirements</span></span></h3>
<div class="MsoNormal">
<span style="font-family: "angsana new";"><span style="font-size: small;"><b>Hardware</b><o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpFirst" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="background: white; color: black; font-family: "angsana new";">Raspberry Pi Board (4B , 3B+)</span><span style="color: black; font-family: "angsana new";"><o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">IP</span><span style="color: black; font-family: "angsana new";"> Camera, USB Camera or Pi Camera<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">SD
Card 32GB<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">5V
DC. 2A Power Supply</span></span></div>
<div class="MsoNormal">
<br /></div>
<div class="MsoNormal">
<span style="font-family: "angsana new";"><span style="font-size: small;"><b>Software</b><o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpFirst" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">OS Raspbien
10 ( buster )<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">Python
3.7.2<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">Tensorflow
lite 1.14.0<o:p></o:p></span></span></div>
<div class="MsoListParagraphCxSpMiddle" style="border: none; mso-border-shadow: yes; mso-list: l0 level1 lfo1; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt; text-indent: -18.0pt;">
<!--[if !supportLists]--><span style="font-size: small;"><span style="color: black; font-family: "symbol";"><span style="mso-list: Ignore;">·<span style="font-family: "times new roman"; font-stretch: normal; font-style: normal; font-variant: normal; line-height: normal;"> </span></span></span><!--[endif]--><span style="color: black; font-family: "angsana new";">OpenCV
4.0.0</span></span></div>
<div class="MsoListParagraphCxSpLast" style="border: none; mso-border-shadow: yes; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt;">
<br /></div>
<div class="MsoNormal" style="border: none; mso-border-shadow: yes; mso-padding-alt: 31.0pt 31.0pt 31.0pt 31.0pt;">
<span style="color: black; font-family: "angsana new";"><span style="font-size: small;"><b>Machine Learning Model </b>: MobileNet SSD V2 <o:p></o:p></span></span><span style="font-family: "angsana new"; font-size: small;">Quantised</span></div>
<!--EndFragment--><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEis9grSYiyJDfrgNKqYkoB1HBwdeDzp2vkM6Ba5iDuIfn2nnyRgrUwW9NZRdX50vbT5zX4ekPjHCN31rXpBdFSvh40xvrvrtonhaC8oOCnf9-XvN7vOEHku6Wvg5kvEvDBxo2F7D_dPctWF/s1600/raspberrypi-tensorflowlite-objectdetection-car3.png" imageanchor="1"><img border="0" height="216" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEis9grSYiyJDfrgNKqYkoB1HBwdeDzp2vkM6Ba5iDuIfn2nnyRgrUwW9NZRdX50vbT5zX4ekPjHCN31rXpBdFSvh40xvrvrtonhaC8oOCnf9-XvN7vOEHku6Wvg5kvEvDBxo2F7D_dPctWF/s320/raspberrypi-tensorflowlite-objectdetection-car3.png" width="320" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhq-xlCSwqNJtx5-FfXENeEzEQksokW8u8HXQbeAceNFv6chh81ZdeAJIoJbU3QSMTjYikrptsk_PTfoXEjCJM1cmx2yZhYZjZD1p89aDKVETLm4QrYcGVr6KaH8Y_l5ls6ijDB6igxu_2V/s1600/raspberrypi-tensorflowlite-objectdetection-person2.png" imageanchor="1"><img border="0" height="220" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhq-xlCSwqNJtx5-FfXENeEzEQksokW8u8HXQbeAceNFv6chh81ZdeAJIoJbU3QSMTjYikrptsk_PTfoXEjCJM1cmx2yZhYZjZD1p89aDKVETLm4QrYcGVr6KaH8Y_l5ls6ijDB6igxu_2V/s320/raspberrypi-tensorflowlite-objectdetection-person2.png" width="320" /></a><br />
<br />
<b>Source Code</b><br />
<a href="https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi">https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi</a><br />
<br />
<br />
<b>Reference</b><br />
<b><br /></b>
Install Tensorflow on Raspberry pi<br />
<a href="https://www.tensorflow.org/install/source_rpi">https://www.tensorflow.org/install/source_rpi</a><br />
<b><br /></b>
Tensorflow Model Zoo<br />
<a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md">https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md</a><br />
<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 16.0px 0.0px; line-height: 30.0px; font: 24.0px 'Helvetica Neue'; color: #1b1f22; -webkit-text-stroke: #1b1f22; background-color: #ffffff}
span.s1 {font-kerning: none}
</style>
<br />
<div class="p1">
<span class="s1"><span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: small;">How to Run TensorFlow Lite Object Detection</span></span></div>
<div class="p1">
<span class="s1"><span style="font-family: "arial" , "helvetica" , sans-serif; font-size: small;"><a href="https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/blob/master/Raspberry_Pi_Guide.md">https://github.com/EdjeElectronics/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/blob/master/Raspberry_Pi_Guide.md</a></span></span></div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-39424186366453728482019-09-10T20:46:00.000-07:002019-09-10T20:46:42.962-07:00People tracking and counting with Raspberry pi 4 and Intel neural compute stick<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/1qEc800Q6Aw" width="560"></iframe>
<br />
<br />
<h2>
<span style="color: magenta; font-size: x-large;">People tracking and counting with Raspberry pi 4 and Intel neural compute stick</span></h2>
or Pedestrian Tracker<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoR9g4uZ7xn0YF8z2N81Ihp51oNnKI8mB9i9vqDmQAJ3ekOUTPtGUfTxbGWzQZMs_rieqNbMXfXwjFNlITP2v9mU9FEnkdYPVSpBshFWpRbuJcHe_9gmbSNCkDtAn60tpb-4It2QI202Dd/s1600/raspi4_intel_neural-compute_stick.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="900" data-original-width="1200" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoR9g4uZ7xn0YF8z2N81Ihp51oNnKI8mB9i9vqDmQAJ3ekOUTPtGUfTxbGWzQZMs_rieqNbMXfXwjFNlITP2v9mU9FEnkdYPVSpBshFWpRbuJcHe_9gmbSNCkDtAn60tpb-4It2QI202Dd/s320/raspi4_intel_neural-compute_stick.jpg" width="320" /></a></div>
<div style="background-color: white; color: #1c1e21; font-family: system-ui, -apple-system, system-ui, ".SFNSText-Regular", sans-serif; font-size: 14px; margin-bottom: 6px; margin-top: 6px;">
<br />
<h3>
<b>Hardware</b></h3>
<span class="text_exposed_show" style="display: inline; font-family: inherit;"><span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Raspberry pi 4B ( 1GB )<br /><span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Intel Neural Compute Stick 2<br /><span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> 32GB SD card</span></div>
<div class="text_exposed_show" style="background-color: white; color: #1c1e21; display: inline;">
<div style="font-family: inherit; margin-bottom: 6px;">
<h3 style="font-size: 14px;">
Software</h3>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Raspbien 10 ( buster )</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> OpenVINO toolkit 2019 R1</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> OpenCV 4.0.0</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Code C/C++</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Model : Person-detection-retail-0013</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Model : Person-reidentification-0031</div>
<div style="font-size: 14px;">
<span class="_5mfr" style="font-family: inherit; margin: 0px 1px;"><span class="_6qdm" style="background-image: url("https://static.xx.fbcdn.net/images/emoji.php/v9/t4c/1/16/25aa.png?_nc_eui2=AeFPT3pnwEJF-L30RO8T_aClEYlwzr4FrVWppee8kd1oD52vFftx4QUMuwQUd9-Ae3QDFu-jdZCSQiXSRTmzHGwu9RXhYdRpFy-gagnezvqBoQ"); background-repeat: no-repeat; background-size: contain; color: transparent; display: inline-block; font-family: inherit; font-size: 16px; height: 16px; text-shadow: none; vertical-align: text-bottom; width: 16px;">▪</span></span> Video MP4 768 x 432 12 fps</div>
<div style="font-size: 14px;">
<br /></div>
<div style="font-size: 14px;">
<br /></div>
<div class="separator" style="clear: both; font-size: 14px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNHVgePznxwxh9Uvz1xBDm9O3YGE8cUyvWp3AsDOo6V0gUlsl4Ie_Tb10D3r0OcugLqHeRt5IayrChGy62G6wljm7PriNMX6aPZSAZDe1Jjk7MTxOcpyl_yOvjbaRc51MrMHwNqcWp0vNs/s1600/NCS-Movidius-Stick.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="500" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNHVgePznxwxh9Uvz1xBDm9O3YGE8cUyvWp3AsDOo6V0gUlsl4Ie_Tb10D3r0OcugLqHeRt5IayrChGy62G6wljm7PriNMX6aPZSAZDe1Jjk7MTxOcpyl_yOvjbaRc51MrMHwNqcWp0vNs/s200/NCS-Movidius-Stick.png" width="200" /></a> <img height="40" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj8tqrvMpvAgHJtbH_ffJHS8oVQxVL914hRRivB10TSlBbxCHigvtP4MN5wc3nvN9NnLqww00rATpGnrFr5NwDbQLMA6lgw4aVVqGVsMEk2QfbhIun1dw7HSFPhinIRMXBU6UPP2Fg42m02/s200/openvino.png" style="font-family: inherit;" width="200" /></div>
<div style="font-size: 14px;">
<br /></div>
<div style="font-size: 14px;">
<br /></div>
<div style="font-size: 14px;">
<b>What is Intel Neural Compute Stick and OpenVINO?</b></div>
<div style="font-size: 14px;">
<a href="https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html">https://raspberrypi4u.blogspot.com/2019/04/raspberry-pi-openvino-intel-movidius.html</a></div>
<div style="font-size: 14px;">
<br /></div>
<div style="font-size: 14px;">
<br /></div>
<div class="header" style="background-attachment: initial; background-clip: initial; background-image: none; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin: 0px;">
<div class="headertitle" style="box-sizing: border-box; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; padding: 0px;">
<div style="box-sizing: border-box; color: #2171b8; font-family: inherit; font-stretch: inherit; font-style: inherit; font-variant: inherit; line-height: 1.16667em; margin: 1rem 0px 2.5rem;">
Pedestrian Tracker C++ Demo</div>
</div>
</div>
<div class="textblock" style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-size: 15px; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 2.5rem;">
<div style="box-sizing: border-box; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
This demo showcases Pedestrian Tracking scenario: it reads frames from an input video sequence, detects pedestrians in the frames, and builds trajectories of movement of the pedestrians in a frame-by-frame manner. You can use a set of the following pre-trained models with the demo:</div>
<ul style="box-sizing: border-box; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><em style="box-sizing: border-box;">person-detection-retail-0013</em>, which is the primary detection network for finding pedestrians</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><em style="box-sizing: border-box;">person-reidentification-retail-0031</em>, which is the network that is executed on top of the results from inference of the first network and makes reidentification of the pedestrians</li>
</ul>
</div>
<div style="font-size: 14px;">
Source Code</div>
<div style="font-size: 14px;">
<a href="https://docs.openvinotoolkit.org/latest/_demos_pedestrian_tracker_demo_README.html">https://docs.openvinotoolkit.org/latest/_demos_pedestrian_tracker_demo_README.html</a></div>
<div style="font-size: 14px;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgXmg36oN4BmSYkre_uzLaK99F8Z6JD1IjEKvLaiSmuLxXrDsFy-joC0lR_oH9mTcubANqEPnFs4PLo-sYje4oiNEGUh8ydlJ-i9IPE-H312li77CU5EMM9es3ZuAaniuyg82ihEd7-ByjS/s1600/pedestrain3.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="641" data-original-width="948" height="432" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgXmg36oN4BmSYkre_uzLaK99F8Z6JD1IjEKvLaiSmuLxXrDsFy-joC0lR_oH9mTcubANqEPnFs4PLo-sYje4oiNEGUh8ydlJ-i9IPE-H312li77CU5EMM9es3ZuAaniuyg82ihEd7-ByjS/s640/pedestrain3.jpg" width="640" /></a></div>
<div style="font-size: 14px;">
<br /></div>
<div style="font-size: 14px;">
<br /></div>
<h3 style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px; margin: 0px; position: relative;">
<span style="color: orange;">Reference</span></h3>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<b>Install the Intel® Distribution of OpenVINO™ Toolkit for Raspbian* OS</b></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI" style="color: #954f72;">https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI</a></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<span style="color: #555555; text-align: center;"><b>Pretrained Models</b></span></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<a href="https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models" style="color: #954f72;">https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models</a></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<span style="color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b>Inference Engine Samples</b> </span></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<a href="http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html" style="color: #954f72;">http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html</a></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
<div style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border: 0px; color: #3e3e3e; font-family: arial, sans-serif; font-size: 15px; font-stretch: normal; line-height: 1.1em; margin: 0px 0px 0.5em; outline: 0px; padding: 0px; vertical-align: baseline;">
<b>OpenVINO, OpenCV, and Movidius NCS on the Raspberry Pi</b></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<a href="https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/" style="color: #954f72;">https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/</a></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px;">
<br /></div>
</div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-437803681061873162019-07-17T02:45:00.002-07:002019-07-21T18:19:39.591-07:00Car Detection with Raspberry pi 4 + Intel Neural Compute Stick<div style="text-align: center;">
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/6XnktdajhxU" width="560"></iframe></div>
<h2>
<span style="color: magenta; font-size: large;">Car Detection with Raspberry pi 4 + Intel Neural Compute Stick</span></h2>
<div style="box-sizing: border-box; color: #53565a; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjJ1xi5yWgtWKlOTJr0LLlyH7RbmWkRl8o0DwwKoc5NRKiiu8CrgVLELSC8az5bFbYA5yjwjzkWAQjacNtsIXFAIGrJtmyGt0YAVFJ1MVYBQasAu_E9-ZXaCo0EG8U0aNIVy3T83Fsyflur/s1600/raspberrpi4-intel-neural-stick.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1200" data-original-width="1600" height="300" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjJ1xi5yWgtWKlOTJr0LLlyH7RbmWkRl8o0DwwKoc5NRKiiu8CrgVLELSC8az5bFbYA5yjwjzkWAQjacNtsIXFAIGrJtmyGt0YAVFJ1MVYBQasAu_E9-ZXaCo0EG8U0aNIVy3T83Fsyflur/s400/raspberrpi4-intel-neural-stick.jpg" width="400" /></a></div>
<b>System Requirements</b></div>
<div style="box-sizing: border-box; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><b>Hardware:</b></span></div>
<div style="box-sizing: border-box; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
</div>
<ul style="box-sizing: border-box; font-family: "helvetica neue", helvetica, arial, sans-serif; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">Raspberry Pi 4B board or 3B+ </span></li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">32GB microSD card</span></li>
</ul>
<ul style="box-sizing: border-box; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">One of Intel® Movidius™ Visual Processing Units (VPU):</span></li>
</ul>
<span style="color: #444444;">Intel® Movidius™ Neural Compute Stick or <span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">Intel® Neural Compute Stick 2</span></span><br />
<ul style="box-sizing: border-box; font-family: "helvetica neue", helvetica, arial, sans-serif; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;"></ul>
<span style="color: #444444;"><br /></span>
<br />
<div style="box-sizing: border-box; font-family: "helvetica neue", helvetica, arial, sans-serif; margin-bottom: 20px; margin-left: auto; margin-right: auto; max-width: 700px; overflow-wrap: break-word;">
<span style="box-sizing: border-box; color: #444444;"><b>Operating Systems:</b></span></div>
<ul style="box-sizing: border-box; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">Raspbian 10 ( Buster )</span></li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">OpenVINO for Raspberry pi ( 2019.1.094 )</span></li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">OpenCV 4.0.0</span></li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;"><span style="color: #444444;">Python 3.7.3</span></li>
</ul>
<div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"></span></span><br />
<div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"><b>Machine Learning</b></span></span></div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">
</span>
<br />
<div style="color: #444444; font-size: 15px;">
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">Model : SSD MobileNet V2</span></div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">
</span>
<br />
<div style="color: #444444; font-size: 15px;">
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><br /></span></div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">
</span>
<br />
<div style="color: #444444; font-size: 15px;">
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><b>Video Test</b></span></div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">
</span>
<div style="color: #444444; font-size: 15px;">
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">MP4 960x540 Resolution</span></div>
<span style="color: #444444; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<b>Source Code in Python</b><br />
<a href="https://docs.openvinotoolkit.org/latest/_inference_engine_ie_bridges_python_sample_object_detection_demo_ssd_async_README.html">https://docs.openvinotoolkit.org/latest/_inference_engine_ie_bridges_python_sample_object_detection_demo_ssd_async_README.html</a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div>
<h3 style="color: #444444; font-size: 15px;">
<span style="color: orange;">Run Code</span></h3>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><br /></span></div>
<div style="font-size: 15px;">
Test 1 Raspberry pi 4B NCS2</div>
<div style="font-size: 15px;">
<br /></div>
<div class="separator" style="clear: both; color: #444444; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhnWq-JKQO62EN_TK-A0tgxoabGTKdvh9gm-i66-5ShZS-GwoqVL_epe-q0ygdvhm8O-D0jwFqDi_bj8xhWKJTpV7lrCgPa_UoRLYfns9rgLP3J1uS9EsyZuMykXWcjpRxHie58OXpGKfN7/s1600/raspberrypi4-car-detect-ncs2.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="768" data-original-width="1068" height="459" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhnWq-JKQO62EN_TK-A0tgxoabGTKdvh9gm-i66-5ShZS-GwoqVL_epe-q0ygdvhm8O-D0jwFqDi_bj8xhWKJTpV7lrCgPa_UoRLYfns9rgLP3J1uS9EsyZuMykXWcjpRxHie58OXpGKfN7/s640/raspberrypi4-car-detect-ncs2.png" width="640" /></a></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><br /></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><span style="color: black;"><br /></span></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><span style="color: black;">Test 2 Raspberry pi 4B NCS1</span></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><br /></span></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilgzUMWhAoecH3S21lYSQpiuOx0D6iHc1FwfuuwJY6cCHQ5zXYsgnOCiJDb87EXBFKlUbEnB-sBfAq8qisRRp3CSX6EL2l-CPyj_myTFrpGuLRn9aFAu_XHsVADudLeLZF3z9lElC1XXBr/s1600/raspberrypi4-car-detection-ncs1.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="687" data-original-width="950" height="460" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEilgzUMWhAoecH3S21lYSQpiuOx0D6iHc1FwfuuwJY6cCHQ5zXYsgnOCiJDb87EXBFKlUbEnB-sBfAq8qisRRp3CSX6EL2l-CPyj_myTFrpGuLRn9aFAu_XHsVADudLeLZF3z9lElC1XXBr/s640/raspberrypi4-car-detection-ncs1.png" width="640" /></a></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><br /></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: orange;"><br /></span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: black;">Test 3 Raspberry pi 3B+ NCS2</span></div>
<div style="color: #444444; font-size: 15px;">
<span style="color: black;"><br /></span></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh17nvJIYx5b3335Wq6L-EJFu0tuH19TPqrZvlef6SY9nz-7-EbLaYXzkiUbPbR6clSy0BvxXJ8_mRsvevvGXIuA6P-1sgqjcXtTIu3fwQ_7SN4vYd5TA_a7RU_D4LwOSb93C-iF2E0YXwX/s1600/raspberrypi3-car-detection-ncs2.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="699" data-original-width="949" height="470" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh17nvJIYx5b3335Wq6L-EJFu0tuH19TPqrZvlef6SY9nz-7-EbLaYXzkiUbPbR6clSy0BvxXJ8_mRsvevvGXIuA6P-1sgqjcXtTIu3fwQ_7SN4vYd5TA_a7RU_D4LwOSb93C-iF2E0YXwX/s640/raspberrypi3-car-detection-ncs2.png" width="640" /></a></div>
<div style="color: #444444; font-size: 15px;">
</div>
<div class="separator" style="clear: both; color: #444444; font-size: 15px; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; color: #444444; font-size: 15px; text-align: center;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
Test 4 Raspberry pi 3B+ NCS1 </div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVOapgdC6b47xc9BgF6a358HTzFxTZS3o3EJN5VGEWkPaQydib2qiYNykkJ3qFYmktmDYWiUegWM03i8FMShmyBHCKT47liKxgaRwuzcFhhPujHLWUx0zk9YVNWyy-DMKhnJ9jfNyCeqym/s1600/raspberrypi3-car-detection-ncs1.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="683" data-original-width="952" height="458" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhVOapgdC6b47xc9BgF6a358HTzFxTZS3o3EJN5VGEWkPaQydib2qiYNykkJ3qFYmktmDYWiUegWM03i8FMShmyBHCKT47liKxgaRwuzcFhhPujHLWUx0zk9YVNWyy-DMKhnJ9jfNyCeqym/s640/raspberrypi3-car-detection-ncs1.png" width="640" /></a></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<br /></div>
<h3 style="clear: both; font-size: 15px; text-align: left;">
<b>Test Result</b></h3>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhb-LtPXPMABvZ8g1s97oat8kv3byT0sDnBuI5X10rEF4cKIpmhGF1BIOjNG3co_dHLDWursl_IMZ6kamgOSSTYsOiH3qP2ngTGiG2iO0d4_r-79xJ5IPlPRlBbDSHqOV-DycSV_xIXoeMt/s1600/raspberrypi4-vs-Raspberrypi3.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="216" data-original-width="706" height="121" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhb-LtPXPMABvZ8g1s97oat8kv3byT0sDnBuI5X10rEF4cKIpmhGF1BIOjNG3co_dHLDWursl_IMZ6kamgOSSTYsOiH3qP2ngTGiG2iO0d4_r-79xJ5IPlPRlBbDSHqOV-DycSV_xIXoeMt/s400/raspberrypi4-vs-Raspberrypi3.png" width="400" /></a></div>
<div class="separator" style="clear: both; font-size: 15px; text-align: center;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444;">
<b>Raspberry Pi 4 vs Raspberry pi 3B+</b></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div class="separator" style="clear: both; color: #444444; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhMsi8420qsZgTpF45Jjd8PlxvA5oOp-LOxg9pHVmv15Xy76QAOuVAnwq9SBpkQ0iWXnUnMmDsyEGhRBguhkMX5rVaeWCqg2e43zxtifNVepTknMZG4-rNuJVeVM8sKkkMilWJfwPYFMAlp/s1600/raspberrypi4-3.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="450" data-original-width="500" height="180" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhMsi8420qsZgTpF45Jjd8PlxvA5oOp-LOxg9pHVmv15Xy76QAOuVAnwq9SBpkQ0iWXnUnMmDsyEGhRBguhkMX5rVaeWCqg2e43zxtifNVepTknMZG4-rNuJVeVM8sKkkMilWJfwPYFMAlp/s200/raspberrypi4-3.jpg" width="200" /></a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div class="separator" style="clear: both; color: #444444; font-size: 15px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEghyphenhyphenR4nUpc7auV5HQIkJjLUfXbFYtUVnBVK-uehyvqYiSO6_7nMn6wW5hZzPg3l3IJZ4Yew8KSsIRoOKiaS7khKWcgPME43H3jfN0j3r7CORPcAU9tiE7bre5G3oJFwhWmAcxL_9Dvfi9G-/s1600/raspberrypi4-compare.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1268" data-original-width="1010" height="640" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEghyphenhyphenR4nUpc7auV5HQIkJjLUfXbFYtUVnBVK-uehyvqYiSO6_7nMn6wW5hZzPg3l3IJZ4Yew8KSsIRoOKiaS7khKWcgPME43H3jfN0j3r7CORPcAU9tiE7bre5G3oJFwhWmAcxL_9Dvfi9G-/s640/raspberrypi4-compare.png" width="507" /></a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<h3 style="color: #444444; font-size: 15px;">
<span style="color: orange;">Reference</span></h3>
<div style="color: #444444; font-size: 15px;">
<b>Install the Intel® Distribution of OpenVINO™ Toolkit for Raspbian* OS</b></div>
<div style="color: #444444; font-size: 15px;">
<a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI">https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI</a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<span style="background-color: white; color: #555555; font-family: , "helvetica neue" , "helvetica" , "arial" , sans-serif; text-align: center;"><b>Pretrained Models</b></span></div>
<div style="color: #444444; font-size: 15px;">
<a href="https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models">https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models</a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="color: #444444; font-size: 15px;">
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b>Inference Engine Samples</b> </span></div>
<div style="color: #444444; font-size: 15px;">
<a href="http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html">http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html</a></div>
<div style="color: #444444; font-size: 15px;">
<br /></div>
<div style="background: rgb(255, 255, 255); border: 0px; color: #3e3e3e; font-family: arial, sans-serif; font-size: 15px; font-stretch: normal; line-height: 1.1em; margin: 0px 0px 0.5em; outline: 0px; padding: 0px; vertical-align: baseline;">
<b>OpenVINO, OpenCV, and Movidius NCS on the Raspberry Pi</b></div>
<div style="color: #444444; font-size: 15px;">
<a href="https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/">https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/</a></div>
<div style="color: #444444; font-size: 15px;">
<br style="color: black; font-family: Times; font-size: medium;" /></div>
</div>
</span></div>
<br />Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-69443484233063868862019-07-15T20:52:00.001-07:002019-07-16T09:39:40.346-07:00Raspberry pi 4 TensorFlow Face Recognition<div style="text-align: center;">
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/r0h2aNqXbBw" width="560"></iframe>
</div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<h2>
<span style="color: magenta; font-size: large;">Raspberry pi 4 TensorFlow Face Recognition</span></h2>
<br />
<b>Hardware</b><br />
Raspberry pi 4B - 1GB , Raspberry pi 3B+<br />
SD card 32 GB.<br />
<br />
<b>Software</b><br />
Raspbien 10 ( buster )<br />
TensorFlow 1.13.1<br />
OpenCV 4.0.0<br />
Python 3.7.3<br />
<br />
<b>Machine Learning </b><br />
Model : Facenet Inception Resnet V1<br />
<br />
<b>Source Code</b><br />
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol";">FaceRec. </span><span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;">A simple working facial recognition program.</span><br />
<span style="font-family: "calibri"; line-height: 17.12px;"><a href="https://github.com/vudung45/FaceRec"><span style="font-family: "angsana new"; line-height: 17.12px;">https://github.com/vudung<span lang="TH">45/</span>FaceRec</span></a></span><span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"> </span><br />
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><br /></span>
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><b>Recognition Dataset</b></span><br />
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><br /></span>
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIzlREpl-Qmp1kdtSA9m0Hh93F8-KVYf9E7xkaG7MErRqOl5OzynTVVtoT24RtN-J6LHlKEravDuqPHr56FPoVQmTTp3OU1k-tX7xNeea0TTo7odqU2YGZ-fsZFhVu-EwiZK93FBjhOp3Z/s1600/build_face_dataset_jurassic_park.jpg" imageanchor="1" style="font-family: Times; margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="352" data-original-width="600" height="233" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIzlREpl-Qmp1kdtSA9m0Hh93F8-KVYf9E7xkaG7MErRqOl5OzynTVVtoT24RtN-J6LHlKEravDuqPHr56FPoVQmTTp3OU1k-tX7xNeea0TTo7odqU2YGZ-fsZFhVu-EwiZK93FBjhOp3Z/s400/build_face_dataset_jurassic_park.jpg" width="400" /></a></span>
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><br /></span>
<br />
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><br /></span>
<br />
<h3>
<span lang="TH" style="color: magenta; font-family: "angsana new"; font-size: large; line-height: 17.12px;"><b>Run Code on Raspberry pi 4 , 3B+ in Image</b></span></h3>
<div>
<span lang="TH" style="color: magenta; font-family: "angsana new"; font-size: large; line-height: 17.12px;"><b><br /></b></span></div>
<div>
Recognise with no dataset</div>
<div>
<span lang="TH" style="color: magenta; font-family: "angsana new"; font-size: large; line-height: 17.12px;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIQPZb76gwrz613ehjLGJxEiwQTJkrwu39tRieXSAGyol9UDX86ScEqz61IUsOsblC-dWhyU0VREd7f562B_FoKdedAlh_wCjvJ_yKqeezVdQz9sdcZP8JBqqkudcYYN57jh7FmW0CUhH5/s1600/raspberrypi4-face-recognition.png" imageanchor="1" style="font-family: Times; font-size: medium; margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="793" data-original-width="1000" height="505" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIQPZb76gwrz613ehjLGJxEiwQTJkrwu39tRieXSAGyol9UDX86ScEqz61IUsOsblC-dWhyU0VREd7f562B_FoKdedAlh_wCjvJ_yKqeezVdQz9sdcZP8JBqqkudcYYN57jh7FmW0CUhH5/s640/raspberrypi4-face-recognition.png" width="640" /></a></span></div>
<span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiFW1aLrUO7GnDZbq7voxhNMIuaOALQrPmdmhonBTi1PA5kyujPf5H6QHnTyJQ5Df16gq7WjU9UKsSHyr9BjsWhpYRezcMaUyIHKOM8xSQHNRYLwvFyyvKPH-EqsrBc5S3F6eeg65nPd2Th/s1600/raspberrypi4-face-recognition1.png" imageanchor="1" style="font-family: Times; margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="793" data-original-width="1000" height="505" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiFW1aLrUO7GnDZbq7voxhNMIuaOALQrPmdmhonBTi1PA5kyujPf5H6QHnTyJQ5Df16gq7WjU9UKsSHyr9BjsWhpYRezcMaUyIHKOM8xSQHNRYLwvFyyvKPH-EqsrBc5S3F6eeg65nPd2Th/s640/raspberrypi4-face-recognition1.png" width="640" /></a></span><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhxRiU0bHhyePj5M_oSshUatqPfWNg1_pq0jcgE0UxFdAKRX2wyB-TXMRxfUCebUPoXH0I8kiGEPWEDBqY-YhlIbtrpcreUtm42LMhO2Xh5Pg0lc0ZkaXiuEB-Jeyb2zuBniveQM5QwP4r_/s1600/raspberrypi3-face-recognition1.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="793" data-original-width="1000" height="506" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhxRiU0bHhyePj5M_oSshUatqPfWNg1_pq0jcgE0UxFdAKRX2wyB-TXMRxfUCebUPoXH0I8kiGEPWEDBqY-YhlIbtrpcreUtm42LMhO2Xh5Pg0lc0ZkaXiuEB-Jeyb2zuBniveQM5QwP4r_/s640/raspberrypi3-face-recognition1.png" width="640" /></a><br />
<br />
<h3>
<b><span lang="TH" style="font-family: "angsana new"; line-height: 17.12px;">Run Code on Macbook Pro </span><span style="font-family: "helvetica neue"; font-size: 11px;">2.3 GHz Intel Core i7 ( 2012 )</span></b></h3>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhjgoy4Pz6ZQSqFiLCVqjfrHZ6D3Ry8_kA4OqGOGy3oDtUoLW85A-gX64HHb-vl1uGmPDdxz8jHhwSMuiTWuGPitFwrpUhVl1ibTz8j6p-zpGd13nrHKEFmhjIZ0sVJlMbRFFVYvdGIAgf4/s1600/face-recognition-tensorflow.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="611" data-original-width="771" height="506" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhjgoy4Pz6ZQSqFiLCVqjfrHZ6D3Ry8_kA4OqGOGy3oDtUoLW85A-gX64HHb-vl1uGmPDdxz8jHhwSMuiTWuGPitFwrpUhVl1ibTz8j6p-zpGd13nrHKEFmhjIZ0sVJlMbRFFVYvdGIAgf4/s640/face-recognition-tensorflow.png" width="640" /></a><br />
<span style="font-family: "helvetica neue"; font-size: 11px;"><br /></span>
<span style="font-family: "helvetica neue"; font-size: 11px;"><br /></span><br />
<h3>
<b>Reference</b></h3>
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol";">FaceRec. </span><span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;">A simple working facial recognition program.</span><br />
<!--[if gte mso 9]><xml>
<o:OfficeDocumentSettings>
<o:RelyOnVML/>
<o:AllowPNG/>
</o:OfficeDocumentSettings>
</xml><![endif]-->
<!--[if gte mso 9]><xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves/>
<w:TrackFormatting/>
<w:PunctuationKerning/>
<w:ValidateAgainstSchemas/>
<w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
<w:IgnoreMixedContent>false</w:IgnoreMixedContent>
<w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
<w:DoNotPromoteQF/>
<w:LidThemeOther>EN-US</w:LidThemeOther>
<w:LidThemeAsian>X-NONE</w:LidThemeAsian>
<w:LidThemeComplexScript>TH</w:LidThemeComplexScript>
<w:Compatibility>
<w:BreakWrappedTables/>
<w:SnapToGridInCell/>
<w:ApplyBreakingRules/>
<w:WrapTextWithPunct/>
<w:UseAsianBreakRules/>
<w:DontGrowAutofit/>
<w:SplitPgBreakAndParaMark/>
<w:EnableOpenTypeKerning/>
<w:DontFlipMirrorIndents/>
<w:OverrideTableStyleHps/>
</w:Compatibility>
<m:mathPr>
<m:mathFont m:val="Cambria Math"/>
<m:brkBin m:val="before"/>
<m:brkBinSub m:val="--"/>
<m:smallFrac m:val="off"/>
<m:dispDef/>
<m:lMargin m:val="0"/>
<m:rMargin m:val="0"/>
<m:defJc m:val="centerGroup"/>
<m:wrapIndent m:val="1440"/>
<m:intLim m:val="subSup"/>
<m:naryLim m:val="undOvr"/>
</m:mathPr></w:WordDocument>
</xml><![endif]--><!--[if gte mso 9]><xml>
<w:LatentStyles DefLockedState="false" DefUnhideWhenUsed="false"
DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="380">
<w:LsdException Locked="false" Priority="0" QFormat="true" Name="Normal"/>
<w:LsdException Locked="false" Priority="9" QFormat="true" Name="heading 1"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 9"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 1"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 2"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 3"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 4"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 5"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 6"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 7"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 8"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="header"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footer"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index heading"/>
<w:LsdException Locked="false" Priority="35" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of figures"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope return"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="line number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="page number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of authorities"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="macro"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="toa heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 5"/>
<w:LsdException Locked="false" Priority="10" QFormat="true" Name="Title"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Closing"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Signature"/>
<w:LsdException Locked="false" Priority="1" SemiHidden="true"
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Message Header"/>
<w:LsdException Locked="false" Priority="11" QFormat="true" Name="Subtitle"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Salutation"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Date"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Block Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Hyperlink"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="FollowedHyperlink"/>
<w:LsdException Locked="false" Priority="22" QFormat="true" Name="Strong"/>
<w:LsdException Locked="false" Priority="20" QFormat="true" Name="Emphasis"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Document Map"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Plain Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="E-mail Signature"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Top of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Bottom of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal (Web)"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Acronym"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Cite"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Code"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Definition"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Keyboard"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Preformatted"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Sample"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Typewriter"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Variable"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Table"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation subject"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="No List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Contemporary"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Elegant"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Professional"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Balloon Text"/>
<w:LsdException Locked="false" Priority="39" Name="Table Grid"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Theme"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 9"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Placeholder Text"/>
<w:LsdException Locked="false" Priority="1" QFormat="true" Name="No Spacing"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading"/>
<w:LsdException Locked="false" Priority="61" Name="Light List"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 1"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 1"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 1"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 1"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 1"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Revision"/>
<w:LsdException Locked="false" Priority="34" QFormat="true"
Name="List Paragraph"/>
<w:LsdException Locked="false" Priority="29" QFormat="true" Name="Quote"/>
<w:LsdException Locked="false" Priority="30" QFormat="true"
Name="Intense Quote"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 1"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 1"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 1"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 1"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 1"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 1"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 1"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 2"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 2"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 2"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 2"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 2"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 2"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 2"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 2"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 2"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 2"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 2"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 3"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 3"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 3"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 3"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 3"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 3"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 3"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 3"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 3"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 3"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 3"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 3"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 3"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 4"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 4"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 4"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 4"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 4"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 4"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 4"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 4"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 4"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 4"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 4"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 4"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 4"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 4"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 5"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 5"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 5"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 5"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 5"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 5"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 5"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 5"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 5"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 5"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 5"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 5"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 5"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 5"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 6"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 6"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 6"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 6"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 6"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 6"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 6"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 6"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 6"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 6"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 6"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 6"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 6"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 6"/>
<w:LsdException Locked="false" Priority="19" QFormat="true"
Name="Subtle Emphasis"/>
<w:LsdException Locked="false" Priority="21" QFormat="true"
Name="Intense Emphasis"/>
<w:LsdException Locked="false" Priority="31" QFormat="true"
Name="Subtle Reference"/>
<w:LsdException Locked="false" Priority="32" QFormat="true"
Name="Intense Reference"/>
<w:LsdException Locked="false" Priority="33" QFormat="true" Name="Book Title"/>
<w:LsdException Locked="false" Priority="37" SemiHidden="true"
UnhideWhenUsed="true" Name="Bibliography"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>
<w:LsdException Locked="false" Priority="41" Name="Plain Table 1"/>
<w:LsdException Locked="false" Priority="42" Name="Plain Table 2"/>
<w:LsdException Locked="false" Priority="43" Name="Plain Table 3"/>
<w:LsdException Locked="false" Priority="44" Name="Plain Table 4"/>
<w:LsdException Locked="false" Priority="45" Name="Plain Table 5"/>
<w:LsdException Locked="false" Priority="40" Name="Grid Table Light"/>
<w:LsdException Locked="false" Priority="46" Name="Grid Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="Grid Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="Grid Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="46" Name="List Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="List Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="List Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 6"/>
</w:LatentStyles>
</xml><![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Angsana New";
panose-1:2 2 6 3 5 4 5 2 3 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cordia New";
panose-1:0 0 0 0 0 0 0 0 0 0;
mso-font-alt:"Angsana New";
mso-font-charset:222;
mso-generic-font-family:roman;
mso-font-format:other;
mso-font-pitch:variable;
mso-font-signature:16777217 0 0 0 65536 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin-top:0cm;
margin-right:0cm;
margin-bottom:8.0pt;
margin-left:0cm;
line-height:107%;
mso-pagination:widow-orphan;
font-size:11.0pt;
mso-bidi-font-size:14.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
mso-themecolor:hyperlink;
text-decoration:underline;
text-underline:single;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-noshow:yes;
mso-style-priority:99;
color:#954F72;
mso-themecolor:followedhyperlink;
text-decoration:underline;
text-underline:single;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
font-size:11.0pt;
mso-ansi-font-size:11.0pt;
mso-bidi-font-size:14.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
.MsoPapDefault
{mso-style-type:export-only;
margin-bottom:8.0pt;
line-height:107%;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;
mso-header-margin:36.0pt;
mso-footer-margin:36.0pt;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style>
<!--[if gte mso 10]>
<style>
/* Style Definitions */
table.MsoNormalTable
{mso-style-name:"Table Normal";
mso-tstyle-rowband-size:0;
mso-tstyle-colband-size:0;
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-parent:"";
mso-padding-alt:0cm 5.4pt 0cm 5.4pt;
mso-para-margin-top:0cm;
mso-para-margin-right:0cm;
mso-para-margin-bottom:8.0pt;
mso-para-margin-left:0cm;
line-height:107%;
mso-pagination:widow-orphan;
font-size:11.0pt;
mso-bidi-font-size:14.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;}
</style>
<![endif]-->
<!--StartFragment--><span style="font-family: "calibri"; line-height: 107%;"><a href="https://github.com/vudung45/FaceRec"><span style="font-family: "angsana new"; line-height: 107%;">https://github.com/vudung<span lang="TH">45/</span>FaceRec</span></a></span><span lang="TH" style="font-family: "angsana new"; line-height: 107%;"> </span><!--EndFragment--><br />
<span lang="TH" style="font-family: "angsana new"; line-height: 107%;"><br /></span>
<span lang="TH" style="line-height: 107%;"><span style="font-family: "angsana new";">Pretrained models from: https://github.com/davidsandberg/facenet</span></span><br />
<span lang="TH" style="line-height: 107%;"><span style="font-family: "angsana new";"><br /></span></span>
<span lang="TH" style="line-height: 107%;"><span style="font-family: "angsana new";">Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks</span></span><br />
<span lang="TH" style="line-height: 107%;"><a href="https://kpzhang93.github.io/MTCNN_face_detection_alignment/">https://kpzhang93.github.io/MTCNN_face_detection_alignment/</a></span><br />
<br />
<div style="background: rgb(255, 255, 255); border: 0px; color: #3e3e3e; font-family: Arial, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 1.1em; margin: 0px 0px 0.5em; outline: 0px; padding: 0px; vertical-align: baseline;">
Face recognition with OpenCV, Python, and deep learning</div>
<a href="https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/">https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/</a>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com3tag:blogger.com,1999:blog-7853792980726640018.post-73293632933928313522019-07-13T20:11:00.002-07:002019-07-15T20:12:17.719-07:00Raspberry pi4 Tensorflow object detection<div style="text-align: center;">
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/KC5q6SunxEU" width="560"></iframe></div>
<h2 style="clear: both; text-align: left;">
<b><span style="color: magenta;">Raspberry pi 4 TensorFlow Object Detection</span></b></h2>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhxJYqVJEjLK3Jw0aaJv8Zxv33vpLBR9HR76XkKqRJP7tZ_ncCk6rkH88nSr1KYprYtJU_vJnm1CaAt0Wh_PUXrX0p8p1btpd1PYPCMzDYfbF36Nq-R4IEtM68Dl7NWKdSMRbzBYcCj6uyJ/s1600/raspberrypi4.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhxJYqVJEjLK3Jw0aaJv8Zxv33vpLBR9HR76XkKqRJP7tZ_ncCk6rkH88nSr1KYprYtJU_vJnm1CaAt0Wh_PUXrX0p8p1btpd1PYPCMzDYfbF36Nq-R4IEtM68Dl7NWKdSMRbzBYcCj6uyJ/s320/raspberrypi4.jpg" width="240" /></a></div>
<br />
On June 2019 Raspberry pi announce new version of raspberry pi board.<br />
Now we have a new raspberry pi 4 model B 1GB So try to run TensorFlow object detection and then compare with Raspberry pi3B+ also.<br />
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjT5kXdyQnyYekAnMUUwXMeg5m77zXG4O4reNE-DgD9x8GbuJCQS4FUyrEdowivWYQWPXtn9d7J0Xmk7tnJOcKgGWrhIwiVL_DdOCWq9A4WdWA-pVp4o-mo0-WARcTmVPSSK3bk_b4z9Dnc/s1600/tensorflow-white-2.jpg" imageanchor="1"><img border="0" height="116" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjT5kXdyQnyYekAnMUUwXMeg5m77zXG4O4reNE-DgD9x8GbuJCQS4FUyrEdowivWYQWPXtn9d7J0Xmk7tnJOcKgGWrhIwiVL_DdOCWq9A4WdWA-pVp4o-mo0-WARcTmVPSSK3bk_b4z9Dnc/s320/tensorflow-white-2.jpg" width="320" /></a><br />
<h3>
<b><span style="color: magenta;">Install TensorFlow on Raspberry pi4</span></b></h3>
Add some dependency<br />
<br />
<div class="p1">
<span style="background-color: #cccccc;">sudo pip3 install grpcio</span></div>
<div class="p2">
<br /></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 18.0px Helvetica}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 18.0px Helvetica; min-height: 22.0px}
</style>
<br />
<div class="p1">
<span style="background-color: #cccccc;">sudo pip3 install h5py</span></div>
<br />
Then Download tensorFlow<br />
<a href="https://www.piwheels.org/simple/tensorflow/tensorflow-1.13.1-cp37-none-linux_armv7l.whl#sha256=25f4ff027beec1e568baf8e90a07bad59d354560533d6b37318b9efeb70beeb1">https://www.piwheels.org/simple/tensorflow/tensorflow-1.13.1-cp37-none-linux_armv7l.whl#sha256=25f4ff027beec1e568baf8e90a07bad59d354560533d6b37318b9efeb70beeb1</a><br />
<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 18.0px Helvetica}
</style>
<br />
<div class="p1">
<span style="background-color: #cccccc;">sudo pip3 install tensorflow-1.13.1-cp37-none-linux_armv7l.whl</span></div>
<br />
<br />
<br />
<b><span style="color: orange;">Summary Software for test.</span></b><br />
<div class="separator" style="clear: both; text-align: center;">
</div>
Rasbien 10 ( Buster )<br />
Python 3.7.3<br />
OpenCV 4.0.0<br />
Tensorflow 1.13.1<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgU5ro48pXvz_3jHjD6YmXoEJyvo6WBnJovoUtAI1On3hWD3CkHsPKI79KYa8pHsmcaDDw2AXjZ5KiQKrbdzRMmec5guWWSO5xwwMJfKLbz1uyhGjm0zO1WyGYAV24t0afNa23mzRuxRoZH/s1600/tf-version.png" imageanchor="1"><img border="0" height="369" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgU5ro48pXvz_3jHjD6YmXoEJyvo6WBnJovoUtAI1On3hWD3CkHsPKI79KYa8pHsmcaDDw2AXjZ5KiQKrbdzRMmec5guWWSO5xwwMJfKLbz1uyhGjm0zO1WyGYAV24t0afNa23mzRuxRoZH/s640/tf-version.png" width="640" /></a><br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhuwnzwvmvJ-F5MkFiWNxa29l3Y5XIZFU4zHEcj06xLlmDC533Iak0BCp4g-6j1ITZVxvDqzPBvbx-uwXk3zoWEIMXXtyoa7U353YZvvgK3oHpffJTLbOy4RvC2tdpdRQ80QDMtc7aB1KK4/s1600/cv2.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="305" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhuwnzwvmvJ-F5MkFiWNxa29l3Y5XIZFU4zHEcj06xLlmDC533Iak0BCp4g-6j1ITZVxvDqzPBvbx-uwXk3zoWEIMXXtyoa7U353YZvvgK3oHpffJTLbOy4RvC2tdpdRQ80QDMtc7aB1KK4/s640/cv2.jpg" width="640" /></a></div>
<br />
<br />
<h3>
<span style="color: magenta;">Run Tensorflow Object Detection</span></h3>
<div class="separator" style="clear: both; text-align: center;">
</div>
Model SSDlite Mobilenet V2<br />
Video MP4 768x432 12 fps<br />
<br />
run on the same img os in same sd-card.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj30Hkmr7rD9i3GVBeV67BMdRHcSvqMdnWmlKpXD7aGuuFN6lJ79A4rkqcJrISP_72o1UXfTGJFlN_E1V22dAMR6rsatroQjg7KhKNiF_FvADoQ4e27_-F_9kJ0rGSGj-jAeKDDNX2BDrqA/s1600/raspberrypi4-tensorflow-object-detection.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="570" data-original-width="816" height="444" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj30Hkmr7rD9i3GVBeV67BMdRHcSvqMdnWmlKpXD7aGuuFN6lJ79A4rkqcJrISP_72o1UXfTGJFlN_E1V22dAMR6rsatroQjg7KhKNiF_FvADoQ4e27_-F_9kJ0rGSGj-jAeKDDNX2BDrqA/s640/raspberrypi4-tensorflow-object-detection.png" width="640" /></a></div>
<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4tnAQmT54qXIuvwDoT99B16uiL-2lI8N8lr67CHcrA75J1_sgxNk0aQksogjENZdWmG-q5XYL8yIe7gZBsqR5a2hjMqZ9XYdMKsqH9UNSVaoJda_Dng-09JQRlPt3dDskOfrUazP0sM7e/s1600/raspberrypi3-tensorflow-object-detection.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="474" data-original-width="816" height="369" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4tnAQmT54qXIuvwDoT99B16uiL-2lI8N8lr67CHcrA75J1_sgxNk0aQksogjENZdWmG-q5XYL8yIe7gZBsqR5a2hjMqZ9XYdMKsqH9UNSVaoJda_Dng-09JQRlPt3dDskOfrUazP0sM7e/s640/raspberrypi3-tensorflow-object-detection.png" width="640" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
<b>Raspberry pi 4 is 2.xx fps .</b></div>
<div class="separator" style="clear: both; text-align: left;">
<b>Raspberry pi 3 is less than 1 fps.</b></div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
So, only Raspberry pi Board is not faster enough for tensorFlow object detection application.</div>
<div class="separator" style="clear: both; text-align: left;">
Then next we use raspberry pi with intel neural compute stick for better performance.</div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
<b>Raspberry pi 4 vs Raspberry pi3 specification</b></div>
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjkLCjwqKWwShMsKPxOFRF3TTr_tE0muvLrBTEx2fyjxownLq2Bzz1_0bgj0eaHfVEGYfhzDFUeEKCq3kdv_CmEZi9l_oNU4F26-41DnJK27rUMXV5dMeaJsUPHXTROI1Td48zuy5ze6YRz/s1600/rpi4-compare.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" height="640" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjkLCjwqKWwShMsKPxOFRF3TTr_tE0muvLrBTEx2fyjxownLq2Bzz1_0bgj0eaHfVEGYfhzDFUeEKCq3kdv_CmEZi9l_oNU4F26-41DnJK27rUMXV5dMeaJsUPHXTROI1Td48zuy5ze6YRz/s640/rpi4-compare.png" width="509" /></a></div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px;">
<h2 style="margin: 0px; position: relative;">
<b><span style="color: red;"><br class="Apple-interchange-newline" />My Website</span></b></h2>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="color: #888888; font-family: "arial" , "helvetica" , sans-serif;"><a href="http://softpowergroup.net/" style="color: #888888;" target="_blank">http://softpowergroup.net/</a></span></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-63058186564009166622019-04-08T10:33:00.002-07:002019-07-13T20:08:04.022-07:00Raspberry pi OpenVINO with Intel Movidius ( Neural Compute Stick )<h2>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiIKgRb4rRbZtIn6Shj9RmWiJZBv8HlBJjz04io92vhQmWJycr0FUZc3XVfYB6WWgP3Pwk30apvHTl_t5ZnZH0JPJCm_FRhpCw94c9yR2w_wGSNnbY6cQ6YNo9D4dcbFoN8Bxdu57A8dXal/s1600/Raspberrypi-openVINO-intel-movidius.jpg" imageanchor="1"><img border="0" height="201" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiIKgRb4rRbZtIn6Shj9RmWiJZBv8HlBJjz04io92vhQmWJycr0FUZc3XVfYB6WWgP3Pwk30apvHTl_t5ZnZH0JPJCm_FRhpCw94c9yR2w_wGSNnbY6cQ6YNo9D4dcbFoN8Bxdu57A8dXal/s400/Raspberrypi-openVINO-intel-movidius.jpg" width="400" /></a></h2>
<h2>
<span style="font-size: x-large;"><span style="color: magenta;">Raspberry pi OpenVINO with Intel Movidius</span> </span></h2>
<h2>
<span style="color: blue;">( Neural Compute Stick )</span></h2>
<div>
<span style="color: blue;"><br /></span></div>
<div>
<span style="color: blue;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj8tqrvMpvAgHJtbH_ffJHS8oVQxVL914hRRivB10TSlBbxCHigvtP4MN5wc3nvN9NnLqww00rATpGnrFr5NwDbQLMA6lgw4aVVqGVsMEk2QfbhIun1dw7HSFPhinIRMXBU6UPP2Fg42m02/s1600/openvino.png" imageanchor="1"><img border="0" height="65" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj8tqrvMpvAgHJtbH_ffJHS8oVQxVL914hRRivB10TSlBbxCHigvtP4MN5wc3nvN9NnLqww00rATpGnrFr5NwDbQLMA6lgw4aVVqGVsMEk2QfbhIun1dw7HSFPhinIRMXBU6UPP2Fg42m02/s320/openvino.png" width="320" /></a></span></div>
<h3>
<span style="color: orange;">
What is OpenVINO?</span></h3>
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">The Intel® Distribution of OpenVINO™ toolkit quickly deploys applications and solutions that emulate human vision. Based on Convolutional Neural Networks (CNN), the toolkit extends computer vision (CV) workloads across Intel® hardware, maximizing performance. The Intel Distribution of OpenVINO toolkit includes the Intel® Deep Learning Deployment Toolkit (Intel® DLDT).</span><br />
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<br />
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 1rem; overflow-wrap: break-word; padding: 0px; vertical-align: baseline;">
<span style="color: #666666;">OpenVINO™ toolkit, short for Open Visual Inference and Neural network Optimization toolkit, provides developers with improved neural network performance on a variety of Intel® processors and helps them further unlock cost-effective, real-time vision applications.The toolkit enables deep learning inference and easy heterogeneous execution across multiple Intel® platforms (CPU, Intel® Processor Graphics)—providing implementations across cloud architectures to edge devices. This open source distribution provides flexibility and availability to the developer community to innovate deep learning and AI solutions.</span></div>
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 1rem; overflow-wrap: break-word; padding: 0px; vertical-align: baseline;">
<span style="color: #666666;">OpenVINO™ toolkit contains:</span></div>
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">
<span style="color: #666666;"> • <a class="ext" href="https://github.com/opencv/dldt" rel="nofollow" style="border: 0px; cursor: pointer; font-family: inherit; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; text-decoration-line: none; vertical-align: baseline;" target="_blank">Deep Learning Deployment Toolkit</a></span></div>
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">
<span style="color: #666666;"> • <a class="ext" href="https://github.com/opencv/open_model_zoo" rel="nofollow" style="border: 0px; cursor: pointer; font-family: inherit; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; text-decoration-line: none; vertical-align: baseline;" target="_blank">Open Model Zoo</a></span></div>
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">
</div>
<span style="color: #666666; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"></span><br />
<div style="background-color: white; border: 0px; font-family: IntelClear-Light, tahoma, Helvetica, helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 1rem; overflow-wrap: break-word; padding: 0px; vertical-align: baseline;">
<span style="color: #666666;">The <span style="border: 0px; font-family: , "tahoma" , "helvetica" , "helvetica" , "arial" , sans-serif; font-stretch: inherit; font-style: inherit; font-variant: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">Intel® Distribution of OpenVINO™ toolkit</span> is also available with additional, proprietary support for Intel® FPGAs, Intel® Movidius™ Neural Compute Stick, Intel® Gaussian Mixture Model - Neural Network Accelerator (Intel® GMM-GNA) and provides optimized traditional computer vision libraries (OpenCV*, OpenVX*), and media encode/decode functions. To learn more and download this free commercial product, visit: <a class="ext" href="https://software.intel.com/en-us/openvino-toolkit" rel="nofollow" style="border: 0px; cursor: pointer; font-family: inherit; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; text-decoration-line: none; vertical-align: baseline;" target="_blank">https://software.intel.com/en-us/openvino-toolkit</a></span></div>
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s1600/NCS-banner-MovStick-500w-300h.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="500" height="192" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s320/NCS-banner-MovStick-500w-300h.png" width="320" /></a></div>
<h3>
<span style="color: orange;">
What is Intel Movidius ( Neural Compute Stick )?</span></h3>
<div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">The Intel® Movidius™ Neural Compute Stick (NCS) is a tiny fanless deep learning device that you can use to learn AI programming at the edge. NCS is powered by the same low power high performance Intel Movidius Vision Processing Unit (VPU) that can be found in millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, and more.</span></div>
<div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">more detail</span></div>
<a href="http://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html">http://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html</a><br />
<br />
<br />
<h3>
<span style="color: orange;">
Samples Code Demo</span></h3>
<b><span style="color: blue;"><a href="https://docs.openvinotoolkit.org/latest/_inference_engine_samples_object_detection_sample_ssd_README.html" target="_blank">Face Detection , Object Detection</a> </span></b><span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;">( Object Detection C++ Sample SSD )</span><br />
<b><span style="color: blue;"><br /></span></b>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">Identify faces for a variety of uses, such as observing if passengers are in a vehicle or counting indoor pedestrian traffic. Combine it with a person detector to identify who is coming and going.</span><br />
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/46TBBb5rAy4/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/46TBBb5rAy4?feature=player_embedded" width="320"></iframe></div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEil3K73TArg4m9R8ScI4bztsAkCbjvxBZ7g2bJH9mpRIKaoW_hjqVW_G2BWf9VsSpb5oUAlPA-PM-frV2jwn3mzSe2nST2SsqM-OnZBLSgbalB05GX4iuiIWejf72MClYS7D66nO12ToMpr/s1600/face-detect-openvino1.png" imageanchor="1"><img border="0" height="227" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEil3K73TArg4m9R8ScI4bztsAkCbjvxBZ7g2bJH9mpRIKaoW_hjqVW_G2BWf9VsSpb5oUAlPA-PM-frV2jwn3mzSe2nST2SsqM-OnZBLSgbalB05GX4iuiIWejf72MClYS7D66nO12ToMpr/s320/face-detect-openvino1.png" width="320" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjECeuTxNrpiz8KYZH5UxuLFdTblgPA8zD_Biy7Dtmv34kD-vsg_qVyW3snpT6AhBp5We15LRWUstyUpxrmS4jNA0BLr0hXWUKe9DvztgrLMSkvBzJL_2dy33rmxDhAEWjnuGlhvtuZp9CU/s1600/face-detect-openvino2.png" imageanchor="1"><img border="0" height="225" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjECeuTxNrpiz8KYZH5UxuLFdTblgPA8zD_Biy7Dtmv34kD-vsg_qVyW3snpT6AhBp5We15LRWUstyUpxrmS4jNA0BLr0hXWUKe9DvztgrLMSkvBzJL_2dy33rmxDhAEWjnuGlhvtuZp9CU/s320/face-detect-openvino2.png" width="320" /></a><br />
<br />
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">Pre-trained Face Detection model</span><br />
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<a href="https://download.01.org/openvinotoolkit/2018_R4/open_model_zoo/face-detection-adas-0001/FP16/face-detection-adas-0001.bin" style="background-color: #f8f8f8; box-sizing: border-box; color: rgb(0, 0, 0) !important; font-family: Consolas, "Bitstream Vera Sans Mono", "Courier New", Courier, monospace; font-size: 15px; outline: none; text-decoration-line: none;">https://download.01.org/openvinotoolkit/2018_R4/open_model_zoo/face-detection-adas-0001/FP16/face-detection-adas-0001.bin</a><br />
<br />
<a href="https://download.01.org/openvinotoolkit/2018_R4/open_model_zoo/face-detection-adas-0001/FP16/face-detection-adas-0001.xml" style="background-color: #f8f8f8; box-sizing: border-box; color: rgb(0, 0, 0) !important; font-family: Consolas, "Bitstream Vera Sans Mono", "Courier New", Courier, monospace; font-size: 15px; outline: none; text-decoration-line: none;">https://download.01.org/openvinotoolkit/2018_R4/open_model_zoo/face-detection-adas-0001/FP16/face-detection-adas-0001.xml</a><br />
<br />
<span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">To validate OpenCV* installation, you may try to run OpenCV's deep learning module with Inference Engine backend. Here is a Python* sample, which works with Face Detection model.</span><br />
<br />
Face Detect Python Code on Github<br />
<br />
<br />
<b><br /></b>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b><a href="https://docs.openvinotoolkit.org/latest/_inference_engine_samples_interactive_face_detection_demo_README.html" target="_blank">Interactive Face Detection C++ Demo</a></b></span><br />
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/UYBBxl6sM4o/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/UYBBxl6sM4o?feature=player_embedded" width="320"></iframe></div>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><br /></span>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b><br /></b></span>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhAInpTCoFJAcrxgDifIWYTzLpixKLe6fgUXfgJLFO42BnkzLPHf5yCQiHcQ0iBfuhJOAKtHWywd5_7qer-l1g1CaUyxKnkX6oINjV8cFP3m5HmbTUg-A_7bW4lwwYHBdoj4StlXfsUReGA/s1600/face-detection-adas-0001.png" imageanchor="1"><img border="0" height="348" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhAInpTCoFJAcrxgDifIWYTzLpixKLe6fgUXfgJLFO42BnkzLPHf5yCQiHcQ0iBfuhJOAKtHWywd5_7qer-l1g1CaUyxKnkX6oINjV8cFP3m5HmbTUg-A_7bW4lwwYHBdoj4StlXfsUReGA/s640/face-detection-adas-0001.png" width="640" /></a></b></span><br />
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><br /></span>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><br /></span>
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"></span><br />
<h4 style="background-color: white; box-sizing: border-box; color: #555555; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 22px; margin-bottom: 0.88889em; margin-top: 0em;">
<a href="http://docs.openvinotoolkit.org/latest/_age_gender_recognition_retail_0013_description_age_gender_recognition_retail_0013.html" rel="nofollow" style="box-sizing: border-box; color: #00aeef; outline: none; text-decoration-line: none;" target="_blank">Age & Gender Recognition</a></h4>
<div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">This neural network-based model provides age and gender estimates with enough accuracy to help you focus your marketing efforts.</span></div>
<div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/cn3cYUe8gvk/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/cn3cYUe8gvk?feature=player_embedded" width="320"></iframe></div>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span>
<span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;"><br /></span></div>
<div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhmFV2IlOHMgjT-bj1ugHIt9prMcAlYGHb88Mbs-Ah2aHofr2ZrCA39eoznU4aAqGnpLCtGsBGcCsIhMmU14sVyO1v_rM1aJK5qvCPoo7tf4b7ptIp2J4CMXd80pYsTNKHtj2aKyHeixw4-/s1600/age-emotion-detect-openvino3.png" imageanchor="1"><img border="0" height="384" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhmFV2IlOHMgjT-bj1ugHIt9prMcAlYGHb88Mbs-Ah2aHofr2ZrCA39eoznU4aAqGnpLCtGsBGcCsIhMmU14sVyO1v_rM1aJK5qvCPoo7tf4b7ptIp2J4CMXd80pYsTNKHtj2aKyHeixw4-/s640/age-emotion-detect-openvino3.png" width="640" /></a></div>
<div>
<br /></div>
<div>
<br /></div>
<div>
<h3 style="background-color: white; box-sizing: border-box; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin-bottom: 0.7276em; margin-top: 0em;">
<a href="http://docs.openvinotoolkit.org/latest/_emotions_recognition_retail_0003_description_emotions_recognition_retail_0003.html" rel="nofollow" style="box-sizing: border-box; outline: none; text-decoration-line: none;" target="_blank"><span style="color: #6fa8dc; font-size: small;">Emotion Recognition</span></a></h3>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
Identify neutral, happy, sad, surprised, and angry emotions.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/mAwcHFNZZG4/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/mAwcHFNZZG4?feature=player_embedded" width="320"></iframe></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/amkzhPaScOs/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/amkzhPaScOs?feature=player_embedded" width="320"></iframe></div>
<br /></div>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgN3qhFKlJqHBxlb0cQcy8cvQeu8PEsj1yud9KG-25b0Ob2oxVCwZyFcjguEq95BMH5Z9eIQg18DWkMrdLoBN_OBugwIhX26L3GlYMQXsPYfBZJeBc2V2YhmsfT2dDi-y-mDjgedwLgwLSD/s1600/face-emotion-detect-openvino-avanger-endgame.png" imageanchor="1"><img border="0" height="260" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgN3qhFKlJqHBxlb0cQcy8cvQeu8PEsj1yud9KG-25b0Ob2oxVCwZyFcjguEq95BMH5Z9eIQg18DWkMrdLoBN_OBugwIhX26L3GlYMQXsPYfBZJeBc2V2YhmsfT2dDi-y-mDjgedwLgwLSD/s640/face-emotion-detect-openvino-avanger-endgame.png" width="640" /></a></div>
<div style="box-sizing: border-box; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin-bottom: 0.7276em; margin-top: 0em;">
<span style="background-color: white; box-sizing: border-box; color: #6fa8dc; font-size: small; outline: none;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEghLCX9wBTWukyuxBE_Os-LHTLe1wFsbCpbN5OfumeumZF_yYpGwZsj7jaVNBEWU9RLTQZhjDQD2S9Hu4bbfWTByUA1LzfgMXm354J06U6Zhd0U6cg5ApRJ_9aAT2o5TtsfWsvDc71Ia91o/s1600/face-emotion-detect-openvino-avanger.png" imageanchor="1"><img border="0" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEghLCX9wBTWukyuxBE_Os-LHTLe1wFsbCpbN5OfumeumZF_yYpGwZsj7jaVNBEWU9RLTQZhjDQD2S9Hu4bbfWTByUA1LzfgMXm354J06U6Zhd0U6cg5ApRJ_9aAT2o5TtsfWsvDc71Ia91o/s320/face-emotion-detect-openvino-avanger.png" width="316" /></a></span></div>
<div style="box-sizing: border-box; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin-bottom: 0.7276em; margin-top: 0em;">
<span style="background-color: white; box-sizing: border-box; color: #6fa8dc; font-size: small; outline: none;"><br /></span></div>
<div style="box-sizing: border-box; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin-bottom: 0.7276em; margin-top: 0em;">
<span style="background-color: white; box-sizing: border-box; color: #6fa8dc; font-size: small; outline: none;"><b><a href="http://docs.openvinotoolkit.org/latest/_head_pose_estimation_adas_0001_description_head_pose_estimation_adas_0001.html" rel="nofollow" style="background-color: white; box-sizing: border-box; outline: none; text-decoration-line: none;" target="_blank">Head Position Estimation</a> </b></span></div>
<div style="box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<span style="background-color: white;">This model shows the position of the head and provides guidance on what caught the subject's attention.</span><br />
<span style="background-color: white;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/a7fIVqOqvvs/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/a7fIVqOqvvs?feature=player_embedded" width="320"></iframe></div>
<span style="background-color: white;"><br /></span></div>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgyw9ccYVN2EyVapZh4Qm3qW_GR6LbTU-cjaycWSLhUQs_oU6yfNgUUrWaTUZ3sWrbIu2zZT-G4IdVRuw5h-Dl8Bv8iGf_R6ShyN_v83FTbW1wE7zV9aZ1eUF_XWWCLjQGUQle0mDtaFWGo/s1600/face-pose-openvino3.png" imageanchor="1"><img border="0" height="332" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgyw9ccYVN2EyVapZh4Qm3qW_GR6LbTU-cjaycWSLhUQs_oU6yfNgUUrWaTUZ3sWrbIu2zZT-G4IdVRuw5h-Dl8Bv8iGf_R6ShyN_v83FTbW1wE7zV9aZ1eUF_XWWCLjQGUQle0mDtaFWGo/s640/face-pose-openvino3.png" width="640" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiGV14QmtvvmsEI4wz_-m0VeJezg3KtKMAmqRTyl7XyN4q6C0-rip6KIWPotsTgbz7yRLIwuDbCUF7RqxcsxUwe1nVI2RXqGKS-2isauglS4pa3z70qclxyKhl9nVDh0GljAFikyrwXLh-B/s1600/face-pose-openvino.png" imageanchor="1"><img border="0" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiGV14QmtvvmsEI4wz_-m0VeJezg3KtKMAmqRTyl7XyN4q6C0-rip6KIWPotsTgbz7yRLIwuDbCUF7RqxcsxUwe1nVI2RXqGKS-2isauglS4pa3z70qclxyKhl9nVDh0GljAFikyrwXLh-B/s640/face-pose-openvino.png" width="640" /></a></div>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<div style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
This demo showcases Object Detection task applied for face recognition using sequence of neural networks. Async API can improve overall frame-rate of the application, because rather than wait for inference to complete, the application can continue operating on the host while accelerator is busy. This demo executes four parallel infer requests for the Age/Gender Recognition, Head Pose Estimation, Emotions Recognition, and Facial Landmarks Detection networks that run simultaneously. You can use a set of the following pre-trained models with the demo:</div>
<ul style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">face-detection-adas-0001</code>, which is a primary detection network for finding faces</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">age-gender-recognition-retail-0013</code>, which is executed on top of the results of the first model and reports estimated age and gender for each detected face</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">head-pose-estimation-adas-0001</code>, which is executed on top of the results of the first model and reports estimated head pose in Tait-Bryan angles</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">emotions-recognition-retail-0003</code>, which is executed on top of the results of the first model and reports an emotion for each detected face</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">facial-landmarks-35-adas-0002</code>, which is executed on top of the results of the first model and reports normed coordinates of estimated facial landmarks</li>
</ul>
<div style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
For more information about the pre-trained models, refer to the https://github.com/opencv/open_model_zoo/blob/master/intel_models/index.md "Open Model Zoo" repository on GitHub*.</div>
<br /></div>
<div style="box-sizing: border-box; color: #555555; font-family: "helvetica neue", helvetica, arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<div style="background-color: white;">
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><a href="http://docs.openvinotoolkit.org/latest/_inference_engine_samples_security_barrier_camera_demo_README.html" target="_blank">Security Barrier Camera С++ Demo</a></b></div>
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px; font-weight: 400;">This code sample showcases vehicle detection, vehicle attributes, and license plate recognition.</span></b><br />
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px; font-weight: 400;"><br /></span></b>
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px; font-weight: 400;">The demo uses OpenCV to display the resulting frame with detections rendered as bounding boxes and text.</span></b><br />
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px; font-weight: 400;"><br /></span></b>
<br />
<div class="separator" style="clear: both; text-align: center;">
<iframe allowfullscreen="" class="YOUTUBE-iframe-video" data-thumbnail-src="https://i.ytimg.com/vi/ju-LN1svTsY/0.jpg" frameborder="0" height="266" src="https://www.youtube.com/embed/ju-LN1svTsY?feature=player_embedded" width="320"></iframe></div>
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><span style="background-color: white; color: #4a4a4a; font-family: "roboto" , "helvetica" , sans-serif; font-size: 15px; font-weight: 400;"><br /></span></b>
<br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<b style="background-color: white; color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgQimB7E1LEuZESMC6VCImJ4DYhXdQWqInqayoCRcSbpKQcwkR8MDl3cidP5IQ6gtGoXv0GcYiD_fMzZMBdSnuAaZEnmMG3k4XS1pk32PW1PaH75HePnCkNKknL2MAmUavlP4iY_yYLWbg_/s1600/car-licenseplate-detect-openvino.png" imageanchor="1"><img border="0" height="385" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgQimB7E1LEuZESMC6VCImJ4DYhXdQWqInqayoCRcSbpKQcwkR8MDl3cidP5IQ6gtGoXv0GcYiD_fMzZMBdSnuAaZEnmMG3k4XS1pk32PW1PaH75HePnCkNKknL2MAmUavlP4iY_yYLWbg_/s640/car-licenseplate-detect-openvino.png" width="640" /></a></b></div>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<b style="color: #2171b8; font-family: roboto, helvetica, sans-serif; font-size: medium;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBRg3Ih0txkGaVmh_DkOjcdnbBe1nHg-bwgxhPH4vAmogTXlgdXSmm273NayWqEHLCZ7RiEaEJEsFFlC5peXeW6SwN4hTBCtt4hF5PouHcXRPlCApsxNPBCN7cLhl5gawB3qO3azOgWtrN/s1600/car-color-detect-openvino-black.png" imageanchor="1"><img border="0" height="194" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBRg3Ih0txkGaVmh_DkOjcdnbBe1nHg-bwgxhPH4vAmogTXlgdXSmm273NayWqEHLCZ7RiEaEJEsFFlC5peXeW6SwN4hTBCtt4hF5PouHcXRPlCApsxNPBCN7cLhl5gawB3qO3azOgWtrN/s200/car-color-detect-openvino-black.png" width="200" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMrcIA1-QrO8ZuX6Pr01D6OJ95RU_Klm-PyZZjP17J8ApSuVwzsY-eckNvRXA7TQAqkSZQ0kDE7xY4-P4SwpCdE1HOGVHg6B7Ba8u8-5bxhEUmSLBr2oNJGvNwe4Fra3C6r31F248fxN-p/s1600/car-color-detect-openvino-red.png" imageanchor="1"><img border="0" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgMrcIA1-QrO8ZuX6Pr01D6OJ95RU_Klm-PyZZjP17J8ApSuVwzsY-eckNvRXA7TQAqkSZQ0kDE7xY4-P4SwpCdE1HOGVHg6B7Ba8u8-5bxhEUmSLBr2oNJGvNwe4Fra3C6r31F248fxN-p/s200/car-color-detect-openvino-red.png" width="187" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjJy_IDb5zJr591RTmcFqekLC7_H9FNSS06_cFFhh7SBiYRlpdfWAT90CkXU48wihLymkfI90piW4BGFFXoWMPVIXt27TWV3bzsNpLFsWURxszuSp-G7l1cK3olHB3nd-1JUMmtPIHz7eJD/s1600/car-color-detect-openvino-white-truck.png" imageanchor="1"><img border="0" height="176" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjJy_IDb5zJr591RTmcFqekLC7_H9FNSS06_cFFhh7SBiYRlpdfWAT90CkXU48wihLymkfI90piW4BGFFXoWMPVIXt27TWV3bzsNpLFsWURxszuSp-G7l1cK3olHB3nd-1JUMmtPIHz7eJD/s200/car-color-detect-openvino-white-truck.png" width="200" /></a></b></div>
<div style="background-color: white; box-sizing: border-box; color: #555555; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 1.06667em; max-width: none; overflow-wrap: break-word;">
<div style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
This demo showcases Vehicle and License Plate Detection network followed by the Vehicle Attributes Recognition and License Plate Recognition networks applied on top of the detection results. You can use a set of the following pre-trained models with the demo:</div>
<ul style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; margin: 0px 0px 1.5rem;">
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">vehicle-license-plate-detection-barrier-0106</code>, which is a primary detection network to find the vehicles and license plates</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">vehicle-attributes-recognition-barrier-0039</code>, which is executed on top of the results from the first network and reports general vehicle attributes, for example, vehicle type (car/van/bus/track) and color</li>
<li style="box-sizing: border-box; margin-bottom: 1.1rem;"><code style="background: rgb(249, 249, 249); box-sizing: border-box; font-family: "Roboto Mono", monospace, fixed;">license-plate-recognition-barrier-0001</code>, which is executed on top of the results from the first network and reports a string per recognized license plate</li>
</ul>
<div style="box-sizing: border-box; color: #4a4a4a; font-family: Roboto, Helvetica, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 22px; margin-bottom: 1.5rem; margin-top: 1rem;">
For more information about the pre-trained models, refer to the https://github.com/opencv/open_model_zoo/blob/master/intel_models/index.md "Open Model Zoo" repository on GitHub*.</div>
</div>
</div>
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5Hm18Fm8oxhzqYQGPQremmjfKy77lofV5cRNpZvjYsHmabZeI5qj-NjVyctiWvGvk2OH2Jll3oJXKHlz28KFC_pjh6SswmLowgoiH56LO1MkfYYGDAZTv02P3ju6fiVuosx503CFTGHqf/s1600/Raspberrypi-openVINO-intel-movidius.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="806" data-original-width="1600" height="100" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5Hm18Fm8oxhzqYQGPQremmjfKy77lofV5cRNpZvjYsHmabZeI5qj-NjVyctiWvGvk2OH2Jll3oJXKHlz28KFC_pjh6SswmLowgoiH56LO1MkfYYGDAZTv02P3ju6fiVuosx503CFTGHqf/s200/Raspberrypi-openVINO-intel-movidius.jpg" width="200" /></a></div>
<h3>
<span style="color: orange;">
Install OpenVINO on Raspberry Pi</span></h3>
<div style="box-sizing: border-box; color: #53565a; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
<b>System Requirements</b></div>
<div style="box-sizing: border-box; color: #53565a; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
<span style="font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">Hardware:</span></div>
<div style="box-sizing: border-box; color: #53565a; line-height: 1.20782em; margin: 0px auto 20px; max-width: 700px;">
</div>
<ul style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;">Raspberry Pi* board with ARMv7-A CPU architecture</li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;">32GB microSD card</li>
</ul>
<ul style="box-sizing: border-box; font-family: intel-clear-bold, "Helvetica Neue", Helvetica, Arial, sans-serif; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;">One of Intel® Movidius™ Visual Processing Units (VPU):</li>
</ul>
Intel® Movidius™ Neural Compute Stick or <span style="color: #53565a; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;">Intel® Neural Compute Stick 2</span><br />
<ul style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;">
</ul>
<br />
<div style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; margin-bottom: 20px; margin-left: auto; margin-right: auto; max-width: 700px; overflow-wrap: break-word;">
<span style="box-sizing: border-box;">Operating Systems:</span></div>
<ul style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; list-style-position: outside; margin: 0px auto 20px; max-width: 700px; overflow: inherit; padding: 0px 20px 0px 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; margin-bottom: 10px; padding-left: 5px; padding-right: 20px; position: relative;">Raspbian* Stretch, 32-bit</li>
</ul>
<br />
<div style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin-bottom: 20px; margin-left: auto; margin-right: auto; max-width: 700px; overflow-wrap: break-word;">
Your installation is complete when these are all completed:</div>
<ol style="box-sizing: border-box; color: #53565a; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 15px; margin: 0px auto 20px; max-width: 700px; padding: 0px 15px 0px 0px;">
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; padding-left: 5px; padding-right: 20px; position: relative;"><a href="http://download.01.org/openvinotoolkit/2018_R5/packages/l_openvino_toolkit_ie_p_2018.5.445.tgz" rel="nofollow" style="box-sizing: border-box; color: #0071c5; outline: none; text-decoration-line: none;">Install</a> the Intel® Distribution of OpenVINO™ toolkit.</li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; padding-left: 5px; padding-right: 20px; position: relative;"><a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI#set-the-environment-variables" style="box-sizing: border-box; color: #0071c5; outline: none; text-decoration-line: none;" target="_blank">Set the environment variables</a>.</li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; padding-left: 5px; padding-right: 20px; position: relative;"><a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI#add-usb-rules" style="box-sizing: border-box; color: #0071c5; outline: none; text-decoration-line: none;" target="_blank">Add USB rules</a>.</li>
<li style="box-sizing: border-box; left: 2em; list-style-position: outside; list-style-type: inherit; padding-left: 5px; padding-right: 20px; position: relative;">Run the <a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI#object-detection-sample" style="box-sizing: border-box; color: #0071c5; outline: none; text-decoration-line: none;" target="_blank">Object Detection Sample</a> and the <a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI#face-detection-model" style="box-sizing: border-box; color: #0071c5; outline: none; text-decoration-line: none;" target="_blank">Face Detection Model</a> (for OpenCV*) to validate your installation.</li>
</ol>
<br />
<h3>
<span style="color: orange;">Reference</span></h3>
<b>Install the Intel® Distribution of OpenVINO™ Toolkit for Raspbian* OS</b><br />
<div>
<a href="https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI">https://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI</a></div>
<div>
<br /></div>
<span style="background-color: white; color: #555555; font-family: , "helvetica neue" , "helvetica" , "arial" , sans-serif; text-align: center;"><b>Pretrained Models</b></span><br />
<a href="https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models">https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models</a><br />
<br />
<span style="background-color: white; color: #2171b8; font-family: "roboto" , "helvetica" , sans-serif;"><b>Inference Engine Samples</b> </span><br />
<a href="http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html">http://docs.openvinotoolkit.org/latest/_docs_IE_DG_Samples_Overview.html</a><br />
<br />
<div style="background: rgb(255, 255, 255); border: 0px; color: #3e3e3e; font-family: Arial, sans-serif; font-stretch: normal; font-variant-east-asian: normal; font-variant-numeric: normal; line-height: 1.1em; margin: 0px 0px 0.5em; outline: 0px; padding: 0px; vertical-align: baseline;">
<b>OpenVINO, OpenCV, and Movidius NCS on the Raspberry Pi</b></div>
<a href="https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/">https://www.pyimagesearch.com/2019/04/08/openvino-opencv-and-movidius-ncs-on-the-raspberry-pi/</a><br />
<br />
<br />Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com3tag:blogger.com,1999:blog-7853792980726640018.post-10292424810096383492019-03-24T20:04:00.000-07:002019-03-24T20:17:02.314-07:00Raspberry pi DIY Smart Security Camera System<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEij3QgldYz3FJvdNu5o9S0E6EoyNVnEYZq0NPfGISFd7N_7rpeLga9pC2sN4i_Q5hi03QQHujIz4FwRPOLr1LQFwEVp7ZCv409hCcI2p-1NXUwJYyusWyLHRyw-6ZKAqiAuObcU8MzeO8D1/s1600/Ras%255Bberrypi-diy-smart-cam.gif" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="720" data-original-width="1280" height="360" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEij3QgldYz3FJvdNu5o9S0E6EoyNVnEYZq0NPfGISFd7N_7rpeLga9pC2sN4i_Q5hi03QQHujIz4FwRPOLr1LQFwEVp7ZCv409hCcI2p-1NXUwJYyusWyLHRyw-6ZKAqiAuObcU8MzeO8D1/s640/Ras%255Bberrypi-diy-smart-cam.gif" width="640" /></a></div>
<h2>
<span style="color: magenta;">Raspberry pi DIY Smart Security Camera System</span></h2>
<div>
<span style="color: blue;">with Intel Movidius ( Neural Compute Stick )</span></div>
<h3>
<span style="color: orange;"></span></h3>
<h2>
<span style="color: magenta;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhgvJ_CcqpTKz6r117SB95VEvzKvVgG-rmSP82plQgT-KkqSig5lCBRc007IaH9gqRS4lZeiZ1fkaCMKld67Tan7R3XMA3LajwcCY5EWIsDkA-GbsQbEwSqMA9BLSdTXup_a3s2rDpZeyhL/s1600/raspberrypi-smart-camera.png" imageanchor="1"><img border="0" height="184" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhgvJ_CcqpTKz6r117SB95VEvzKvVgG-rmSP82plQgT-KkqSig5lCBRc007IaH9gqRS4lZeiZ1fkaCMKld67Tan7R3XMA3LajwcCY5EWIsDkA-GbsQbEwSqMA9BLSdTXup_a3s2rDpZeyhL/s200/raspberrypi-smart-camera.png" width="200" /></a> </span><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheDBSwhBVMr41ctxacA_7boPEU10LlsugJteccnnw5Yrb54gscTDXkQUdT0c5zf7fF_9m59hS-u7dZyWan7SQ_8lZ6j0zhtMK1W3pepzdR0u9TaV4uGRraNEYJ3z7mkQA-HaMgFIKwJF9r/s1600/NCS-Movidius-Stick.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="300" data-original-width="500" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheDBSwhBVMr41ctxacA_7boPEU10LlsugJteccnnw5Yrb54gscTDXkQUdT0c5zf7fF_9m59hS-u7dZyWan7SQ_8lZ6j0zhtMK1W3pepzdR0u9TaV4uGRraNEYJ3z7mkQA-HaMgFIKwJF9r/s200/NCS-Movidius-Stick.png" width="200" /></a></h2>
<h3>
<span style="color: orange;">
Features</span></h3>
<ul>
<li>Detect's a 'Person' in real time</li>
<li>Person detected and notify user</li>
<li>Saved Detect Person Image</li>
<li>Set Duration time to Notify</li>
</ul>
<ul>
<li>Low-cost Hardware requirements.</li>
<li>Low-power consumption.</li>
</ul>
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh0OrRTYdk94v5iYsrTpnOFQcjAkt1Z7aGsMTi4AcUwvbfD-zAhBbsiOlySHlgqLH0BYGsD0jR9e9HtIbWuLqkCFaHko9d8ogiLsrElkhwU51tJja4_EIQvZx0EsHXSj-nIOIaeyRgRSSvd/s1600/raspberrypi-hardware.png" imageanchor="1"><img border="0" height="300" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh0OrRTYdk94v5iYsrTpnOFQcjAkt1Z7aGsMTi4AcUwvbfD-zAhBbsiOlySHlgqLH0BYGsD0jR9e9HtIbWuLqkCFaHko9d8ogiLsrElkhwU51tJja4_EIQvZx0EsHXSj-nIOIaeyRgRSSvd/s400/raspberrypi-hardware.png" width="400" /></a><br />
<h3>
<span style="color: orange;">
Hardware</span></h3>
<ul>
<li>Raspberry pi 3B+ with accessories</li>
<li>32 GB SD card</li>
<li>Picam or USB Webcam</li>
<li>Intel Movidius ( Neural Compute Stick )</li>
</ul>
<br />
if you want Raspberry pi Development kits. <a href="https://www.facebook.com/softpowergroup/" target="_blank">pls contact us.</a><br />
<br />
<h3>
<span style="color: orange;">
Software</span></h3>
<div class="p1">
<ul>
<li>Raspbien OS </li>
<li>Python 3.5.3</li>
<li>OpenCV 3.3.0</li>
<li>TensorFlow 1.12</li>
<li>NCSDK </li>
</ul>
</div>
<div class="p1">
if you want SD card with pre-install software. <a href="https://www.facebook.com/softpowergroup/" target="_blank">pls contact us.</a></div>
<div class="p1">
<br /></div>
<br />
<h3>
<span style="color: blue;">
System Diagram</span></h3>
<div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhqQQVI0Jn6pglfXSxF8ScuYLvqgW7aEsbZcYClUPP9B0MgCS0GGzorcsFeN4X_R-e2TjLbx6JPxZwkeaYfB29ubHnPNRz40CSovj-pyv-1Pd4dA3P1LuJCAwpueRSDZOZ0_p47TsX-qpNA/s1600/Raspberrypi-smart-camera-diagram.png" imageanchor="1"><img border="0" height="283" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhqQQVI0Jn6pglfXSxF8ScuYLvqgW7aEsbZcYClUPP9B0MgCS0GGzorcsFeN4X_R-e2TjLbx6JPxZwkeaYfB29ubHnPNRz40CSovj-pyv-1Pd4dA3P1LuJCAwpueRSDZOZ0_p47TsX-qpNA/s640/Raspberrypi-smart-camera-diagram.png" width="640" /></a></div>
<br />
<br />
<h3>
<span style="color: orange;">
Machine Learning Object Detection with Intel Movidius</span></h3>
<div>
<span style="color: blue;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgqYggJeNPk_Fgr7SDeeYdo45L2NXh0tXwTv8P1qcLZu1eXpzoC1UHjJWThug2cIOqieiijgeMpBvNq5Yu_8aw26lDNqDvzvrA-qwZEjiwoo0rVtHOLLLj-KBYILE9Ad85WjwFONQg76GS-/s1600/machine-learning-.png" imageanchor="1"><img border="0" height="167" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgqYggJeNPk_Fgr7SDeeYdo45L2NXh0tXwTv8P1qcLZu1eXpzoC1UHjJWThug2cIOqieiijgeMpBvNq5Yu_8aw26lDNqDvzvrA-qwZEjiwoo0rVtHOLLLj-KBYILE9Ad85WjwFONQg76GS-/s200/machine-learning-.png" width="200" /></a></span></div>
<div>
<h3>
<span style="color: blue; font-size: small;"><a href="https://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html" style="font-weight: normal;" target="_blank">What is Machine Learning?</a></span></h3>
</div>
<div>
<br /></div>
<div>
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s1600/NCS-banner-MovStick-500w-300h.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="500" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s200/NCS-banner-MovStick-500w-300h.png" width="200" /></a></div>
<div>
<br /></div>
<div>
<span style="color: blue;"></span><br />
<div style="color: black;">
<span style="color: blue;"><span style="background-color: white;"><span style="color: blue;"><a href="https://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html" target="_blank">What is Intel Movidius Neural Compute Stick?</a></span></span></span></div>
<span style="color: blue;">
</span>
<br />
<div style="color: black;">
<span style="color: blue;"><span style="background-color: white;"><br /></span></span></div>
<span style="color: blue;">
</span></div>
<div>
<br /></div>
<div>
<br /></div>
<div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEju3EuWvZezCqDkmQhVTNRX_7sX-R3hGbARW8DsenaK8fMqRm8DUNr6rQuiHIgdxdHxMyNDMeykth6N4AaeqtYeWCpkAcrCegdQKXKIgXiziie0ZVC_w_N9SMmrtgnzSZ5l5QHbm37cO-hX/s1600/ncsdk.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="568" data-original-width="1056" height="213" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEju3EuWvZezCqDkmQhVTNRX_7sX-R3hGbARW8DsenaK8fMqRm8DUNr6rQuiHIgdxdHxMyNDMeykth6N4AaeqtYeWCpkAcrCegdQKXKIgXiziie0ZVC_w_N9SMmrtgnzSZ5l5QHbm37cO-hX/s400/ncsdk.png" width="400" /></a></div>
<div>
<br /></div>
<div>
<span style="color: blue;"><a href="https://raspberrypi4u.blogspot.com/2018/10/install-intel-movidius-neural-compute-sdk.html" target="_blank">Install NCSDK on Raspberry pi</a></span></div>
<div>
<span style="color: blue;"><br /></span></div>
<br />
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg2rfT0rfHHMnLBI0HqE7j2sATPSynqLCvwSE6EphmG6o1YODb3nLryCn2flPDp_HtRSv8QMBnTmB81Juf2pl4azytSG5A1dNfpElVlQ_3nB4AloLl_VBRF02j7tQ8YDt_SvOsJWXUrqS4u/s1600/python-logo.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="203" data-original-width="601" height="67" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg2rfT0rfHHMnLBI0HqE7j2sATPSynqLCvwSE6EphmG6o1YODb3nLryCn2flPDp_HtRSv8QMBnTmB81Juf2pl4azytSG5A1dNfpElVlQ_3nB4AloLl_VBRF02j7tQ8YDt_SvOsJWXUrqS4u/s200/python-logo.png" width="200" /></a></div>
<h4>
<b><span style="color: blue;">Source Code</span></b></h4>
<div>
<a href="https://github.com/movidius/ncappzoo/tree/master/apps/security-cam" rel="noopener" style="background-color: white; box-sizing: border-box; color: #00365f; font-family: intel-clear, tahoma, Helvetica, helvetica, Arial, sans-serif; font-size: 18px; outline: none; transition: all 0.2s ease 0s;">https://github.com/movidius/ncappzoo/tree/master/apps/security-cam</a></div>
<br />
<br />
Notification<br />
update soon ! we've plan to set notify with firebase.<br />
<br />
<br />
Applications<br />
Detect your children come back home<br />
<br />
<br />
<h3>
<span style="color: blue;">
Reference</span></h3>
<div style="border: 0px; box-sizing: border-box; color: #222222; font-stretch: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif; font-size: small;">MobileNets on Intel® Movidius™ Neural Compute Stick and Raspberry Pi 3 </span><a href="https://movidius.github.io/blog/ncs-rpi3-mobilenets/" style="font-family: "Helvetica Neue", Arial, Helvetica, sans-serif;">https://movidius.github.io/blog/ncs-rpi3-mobilenets/</a></div>
<span style="font-family: "helvetica neue" , "arial" , "helvetica" , sans-serif;"><a href="https://github.com/cagbal/ros_people_object_detection_tensorflow">https://github.com/cagbal/ros_people_object_detection_tensorflow</a></span><br />
<br />
<a href="https://www.intel.ai/practical-applications-of-deep-learning-build-a-diy-smart-security-camera-using-the-intel-movidius-neural-compute-stick/#gs.28b37z">https://www.intel.ai/practical-applications-of-deep-learning-build-a-diy-smart-security-camera-using-the-intel-movidius-neural-compute-stick/#gs.28b37z</a><br />
<br />
<h1 class="graf graf--h3 graf--leading graf--title" id="2635" name="2635" style="--baseline-multiplier: 0.22; --margin-top-multiplier: 0; --x-height-multiplier: 0.342; background-color: white; color: rgba(0, 0, 0, 0.84); font-family: medium-content-title-font, Georgia, Cambria, "Times New Roman", Times, serif; line-height: 1.25; margin: 0px; padding-top: 16px !important;">
<span style="font-size: small;">How to make a smart security camera system</span></h1>
<a href="https://www.hackster.io/hackershack/smart-security-camera-90d7bd">https://www.hackster.io/hackershack/smart-security-camera-90d7bd</a><br />
<br />
<br />
<br />
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px;">
<h2 style="margin: 0px; position: relative;">
<b><span style="color: red;">My Website</span></b></h2>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="color: #888888; font-family: "arial" , "helvetica" , sans-serif;"><a href="http://softpowergroup.net/" style="color: #888888; text-decoration-line: none;" target="_blank">http://softpowergroup.net/</a></span></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
<br />Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com2tag:blogger.com,1999:blog-7853792980726640018.post-47825396070857215842018-11-03T04:54:00.003-07:002018-11-04T08:23:07.877-08:00Raspberry pi Image Classifier with Intel Movidius ( Neural Compute Stick )<h2>
<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/HHECMCueHeE" width="560"></iframe></h2>
<h2>
<span style="font-size: medium;"><span style="color: magenta; font-size: x-large;">Raspberry pi Image Classifier with Intel Movidius </span></span><span style="font-weight: normal;">( Neural Compute Stick )</span></h2>
<h3 style="border: 0px; box-sizing: border-box; font-family: "helvetica neue", helvetica, arial, sans-serif; font-stretch: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
<span style="color: blue; font-size: small;">What is Image Classification?</span></h3>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: helvetica, arial, sans-serif; font-stretch: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Image classification is a computer vision problem that aims to classify a subject or an object present in an image into predefined classes. A typical real-world example of image classification is showing an image flash card to a toddler and asking the child to recognize the object printed on the card. Traditional approaches to providing such visual perception to machines have relied on complex computer algorithms that use feature descriptors, like edges, corners, colors, and so on, to identify or recognize objects in the image.</div>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: helvetica, arial, sans-serif; font-stretch: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Deep learning takes a rather interesting, and by far most efficient approach, to solving real-world imaging problems. It uses multiple layers of interconnected neurons, where each layer uses a specific computer algorithm to identify and classify a specific descriptor. For example if you wanted to classify a traffic stop sign, you would use a deep neural network (DNN) that has one layer to detect edges and borders of the sign, another layer to detect the number of corners, the next layer to detect the color red, the next to detect a white border around red, and so on. The ability of a DNN to break down a task into many layers of simple algorithms allows it work with a larger set of descriptors, which makes DNN-based image processing much more effective in real-world applications.<br />
<br />
<div style="font-size: 18px; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhP8bMml0wR_JVz4wNVYczpKrXBzrM-k6xfRJ0UGaQ22G1Qi54bMINd8bv39hTV0V9UxvQz0GikWbEOHN98Fx5pnaOJK-R8vcr8xJuFgsSM3whGLMCrkkAUahD_152Hp2tjU1vx4cKx0kFq/s1600/rpi-ncs-ad.png" imageanchor="1" style="font-family: Times; font-size: medium;"><img border="0" height="210" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhP8bMml0wR_JVz4wNVYczpKrXBzrM-k6xfRJ0UGaQ22G1Qi54bMINd8bv39hTV0V9UxvQz0GikWbEOHN98Fx5pnaOJK-R8vcr8xJuFgsSM3whGLMCrkkAUahD_152Hp2tjU1vx4cKx0kFq/s400/rpi-ncs-ad.png" width="400" /></a></div>
</div>
<b>Hardware</b><br />
<ul>
<li>Raspberry pi 3B or 3B+ and SD card 16 GB or more</li>
<li>Intel Movidius ( Neural Computer Stick ) </li>
</ul>
<b>Software</b><br />
<ul>
<li>Python 3.x</li>
<li>OpenCV 3.3.0 ( <a href="http://raspberrypi4u.blogspot.com/2018/08/raspberry-pi-install-opencv.html" target="_blank">Install OpenCV</a> )</li>
<li>NCSDK 2.xx ( <a href="http://raspberrypi4u.blogspot.com/2018/10/install-intel-movidius-neural-compute-sdk.html" target="_blank">Install NCSDK</a> )</li>
<li><a href="http://raspberrypi4u.blogspot.com/2018/10/intel-movidius-neural-compute-sdk.html" target="_blank">ncappzoo</a> ( <a href="http://raspberrypi4u.blogspot.com/2018/10/intel-movidius-neural-compute-sdk.html" target="_blank">more info</a> )</li>
</ul>
<h2>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjT5kbSN0hCs75fci2X2jXzNXrRQZrtyIvqBUg_lO8RGM_Cq-omZva3fdBbIByQtMX-wMiOBY9S8l7QsV2lQUhkrOSj2ElHUC6R2ciFjBC7cMjzxyfecWtHsO4eeEK2_ugDPB_GurEdhyphenhyphenWi/s1600/ncs-rpi-tensorflow-image-classifier.PNG" imageanchor="1" style="font-size: medium; font-weight: 400; margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="638" data-original-width="1021" height="196" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjT5kbSN0hCs75fci2X2jXzNXrRQZrtyIvqBUg_lO8RGM_Cq-omZva3fdBbIByQtMX-wMiOBY9S8l7QsV2lQUhkrOSj2ElHUC6R2ciFjBC7cMjzxyfecWtHsO4eeEK2_ugDPB_GurEdhyphenhyphenWi/s320/ncs-rpi-tensorflow-image-classifier.PNG" width="320" /></a></h2>
<h1 style="border-bottom: 1px solid rgb(234, 236, 239); box-sizing: border-box; line-height: 1.25; margin: 0px 0px 16px; padding-bottom: 0.3em;">
<span style="color: blue;">
image-classifier</span></h1>
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Perform image classification using deep neural networks (DNNs) on Intel® Movidius™ Neural Compute Stick (NCS). The <a href="https://movidius.github.io/blog/ncs-image-classifier/" rel="nofollow" style="box-sizing: border-box; color: #0366d6; text-decoration-line: none;">NCS developer blog</a> has a step by step tutorial on how to build this project, and also has a detailed explanation of the source code.</div>
<br />
Let's begin<br />
<br />
<b style="color: #d53bd3; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">Change Directory</b><br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures}
span.s3 {font-variant-ligatures: no-common-ligatures; color: #5330e1}
span.s4 {font-variant-ligatures: no-common-ligatures; color: #000000}
</style>
<br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b>~ $</b></span><span class="s2"> <span style="background-color: yellow;">cd ncappzoo/apps/image-classifier/</span></span></div>
<div class="p2">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s4">:</span><span class="s2"><b>~/ncappzoo/apps/image-classifier $</b></span><span class="s4"><span class="Apple-converted-space"> </span></span></div>
<div class="p2">
<span class="s4"><span class="Apple-converted-space"><br /></span></span></div>
<div class="p2">
<span class="s4"><span class="Apple-converted-space" style="color: magenta;"><b>File</b></span></span></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
span.s4 {font-variant-ligatures: no-common-ligatures; color: #d53bd3}
</style>
<br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b><span style="color: black;">~/ncappzoo/apps/image-classifier $</span></b></span><span class="s2"> <span style="background-color: yellow;">ls</span></span></div>
<div class="p2">
<span class="s3">AUTHORS<span class="Apple-converted-space"> </span>image-classifier.py<span class="Apple-converted-space"> </span>Makefile<span class="Apple-converted-space"> </span>README.md<span class="Apple-converted-space"> </span></span><span class="s4"><b>screen_shot.jpg</b></span></div>
<div class="p2">
<span class="s4"><b><br /></b></span></div>
<div class="p2">
<span class="s4" style="color: magenta;"><b>Make Help</b></span></div>
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b><span style="color: black;">~/ncappzoo/apps/image-classifier $</span></b></span><span class="s2"> <span style="background-color: yellow;">make help</span></span></div>
<br />
<div class="p2">
<span class="s3">possible make targets:<span class="Apple-converted-space"> </span></span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>make help - Shows this message</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>make - Builds all dependencies, but does not run this program</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>make run - Runs this program</span></div>
<div class="p2">
<span class="s4">
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
</style>
</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>make clean - removes files files and directories created in this directory</span></div>
<br />
<b style="color: #d53bd3; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">Make</b><br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; min-height: 18.0px}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b>~/ncappzoo/apps/image-classifier $</b></span><span class="s2"> <span style="background-color: yellow;">make</span></span></div>
<div class="p2">
<span class="s3">\making ilsvrc12</span></div>
<div class="p2">
<span class="s3">(cd ../../data/ilsvrc12; make;)</span></div>
<div class="p2">
<span class="s3">make[1]: Entering directory '/home/pi/ncappzoo/data/ilsvrc12'</span></div>
<div class="p2">
<span class="s3">make[1]: Leaving directory '/home/pi/ncappzoo/data/ilsvrc12'</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">making googlenet</span></div>
<div class="p2">
<span class="s3">(cd ../../caffe/GoogLeNet; make compile;)</span></div>
<div class="p2">
<span class="s3">make[1]: Entering directory '/home/pi/ncappzoo/caffe/GoogLeNet'</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">making prereqs</span></div>
<div class="p2">
<span class="s3">(cd ../../data/ilsvrc12; make)</span></div>
<div class="p2">
<span class="s3">make[2]: Entering directory '/home/pi/ncappzoo/data/ilsvrc12'</span></div>
<div class="p2">
<span class="s3">make[2]: Leaving directory '/home/pi/ncappzoo/data/ilsvrc12'</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">making prototxt</span></div>
<div class="p2">
<span class="s3">Prototxt file already exists</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">making caffemodel</span></div>
<div class="p2">
<span class="s3">caffemodel file already exists</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">making compile</span></div>
<div class="p2">
<span class="s3">mvNCCompile -w bvlc_googlenet.caffemodel -s 12 deploy.prototxt</span></div>
<br />
.<br />
.<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; min-height: 18.0px}
p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #ecec15}
span.s1 {font-variant-ligatures: no-common-ligatures}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
</style>
<br />
<div class="p1">
<span class="s1"><b>mvNCCompile v02.00, Copyright @ Intel Corporation 2017</b></span></div>
<div class="p2">
<span class="s1"></span><br /></div>
<div class="p1">
<span class="s1">Layer<span class="Apple-converted-space"> </span>inception_3b/1x1<span class="Apple-converted-space"> </span>forced to im2col_v2, because its output is used in concat</span></div>
<div class="p3">
<span class="s2">/usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: </span><span class="s1">You are using a large type. Consider reducing your data sizes for best performance</span></div>
<div class="p1">
<span class="s1">Blob generated</span></div>
<div class="p1">
<span class="s1">make[1]: Leaving directory '/home/pi/ncappzoo/caffe/GoogLeNet'</span></div>
<br />
<br />
<b style="color: #d53bd3; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">Run Python code</b><br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b>~/ncappzoo/apps/image-classifier $</b></span><span class="s2"> <span style="background-color: yellow;">python3 image-classifier.py<span class="Apple-converted-space"> </span></span></span></div>
<div class="p2">
<span class="s3">/usr/local/lib/python3.5/dist-packages/skimage/transform/_warps.py:105: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>warn("The default mode, 'constant', will be changed to 'reflect' in "</span></div>
<div class="p2">
<span class="s3">/usr/local/lib/python3.5/dist-packages/skimage/transform/_warps.py:110: UserWarning: Anti-aliasing will be enabled by default in skimage 0.15 to avoid aliasing artifacts when down-sampling images.</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>warn("Anti-aliasing will be enabled by default in skimage 0.15 to "</span></div>
<div class="p2">
<span class="s3">/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:418: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead</span></div>
<div class="p2">
<span class="s3"><span class="Apple-converted-space"> </span>tensor = numpy.fromstring(tensor.raw, dtype=numpy.float32)</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<div class="p2">
<span class="s3">==============================================================</span></div>
<div class="p2">
<span class="s3" style="background-color: cyan;">Top predictions for cat.jpg</span></div>
<div class="p2">
<span class="s3" style="background-color: cyan;">Execution time: 93.694756ms</span></div>
<div class="p2">
<span class="s3">--------------------------------------------------------------</span></div>
<div class="p2">
<span class="s3" style="background-color: cyan;">40.5%<span class="Apple-tab-span"> </span>n02123159 tiger cat</span></div>
<div class="p2">
<span class="s3">32.6%<span class="Apple-tab-span"> </span>n02123045 tabby, tabby cat</span></div>
<div class="p2">
<span class="s3">8.9%<span class="Apple-tab-span"> </span>n02124075 Egyptian cat</span></div>
<div class="p2">
<span class="s3">5.0%<span class="Apple-tab-span"> </span>n02127052 lynx, catamount</span></div>
<div class="p2">
<span class="s3">1.2%<span class="Apple-tab-span"> </span>n04074963 remote control, remote</span></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; min-height: 18.0px}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
span.Apple-tab-span {white-space:pre}
</style>
<br />
<div class="p2">
<span class="s3">==============================================================</span></div>
<br />
If you run on VNC or Raspberry pi Desktop.It's show the Image.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhuL7vWqEhwZciYRrL26MFhxnlo7SCXZeq7nmEy02h2Y8egCrUb8PsyvXXB4qDAn5jfSn9zQ-u1gHH-we8cI6YOW6BA2jeivVwdLBZ_rNvNjM75-5MZ6HuVvOkQ9PpPaZdqZFZna7PgeE2D/s1600/ncs-rpi-im-class-show.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="618" data-original-width="1006" height="392" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhuL7vWqEhwZciYRrL26MFhxnlo7SCXZeq7nmEy02h2Y8egCrUb8PsyvXXB4qDAn5jfSn9zQ-u1gHH-we8cI6YOW6BA2jeivVwdLBZ_rNvNjM75-5MZ6HuVvOkQ9PpPaZdqZFZna7PgeE2D/s640/ncs-rpi-im-class-show.png" width="640" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
Code Parameter</div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg1OErTLiiz92B45GOqi_ofQ0lpfLn3hIEqp0jQKQVLELbtrIJSwBnyQRDP4DgCwfMBnbNhE4C6V8UA149YKzwORr3fOVtoIhUxHLAedwmfajrsDYfrSifFcZ_Baebk31I_u-WSbKE3SIZn/s1600/im-classifer-code+2.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="634" data-original-width="880" height="459" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg1OErTLiiz92B45GOqi_ofQ0lpfLn3hIEqp0jQKQVLELbtrIJSwBnyQRDP4DgCwfMBnbNhE4C6V8UA149YKzwORr3fOVtoIhUxHLAedwmfajrsDYfrSifFcZ_Baebk31I_u-WSbKE3SIZn/s640/im-classifer-code+2.png" width="640" /></a></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><b>GRAPH_PATH</b></code><span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">: Location of the graph file, against with we want to run the inference By default it is set to</span><span style="color: #333333; font-family: inherit; font-size: inherit; font-style: inherit; font-weight: inherit;"> </span><code class="highlighter-rouge" style="background-color: cyan; border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">~/workspace/ncappzoo/caffe/GoogLeNet/graph</code><br />
<div>
<span style="color: #333333; font-family: "bitstream vera sans mono" , "courier" , monospace;"><span style="font-size: 16.2px;"><br /></span></span><code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><b>IMAGE_PATH</b></code><span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">: Location of the image we want to classify </span></div>
<div>
<span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">By default it is set to</span><span style="color: #333333; font-family: inherit; font-size: inherit; font-style: inherit; font-weight: inherit;"> </span><code class="highlighter-rouge" style="background-color: cyan; border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">~/workspace/ncappzoo/data/images/cat.jpg</code></div>
<div>
<span style="color: #333333; font-family: "bitstream vera sans mono" , "courier" , monospace;"><span style="font-size: 16.2px;"><br /></span></span><code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_DIM</code><span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">: Dimensions of the image as defined by the choosen neural network ex. GoogLeNet uses 224x224 pixels, AlexNet uses 227x227 pixels</span></div>
<div>
<span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif;"><span style="font-size: 18px;"><br /></span></span><code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_STDDEV</code><span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">: Standard deviation (scaling value) as defined by the choosen neural network </span><br />
<span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">ex. GoogLeNet uses no scaling factor, InceptionV3 uses 128 (stddev = 1/128)</span></div>
<div>
<span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif;"><span style="font-size: 18px;"><br /></span></span><code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; color: #333333; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_MEAN</code><span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">: Mean subtraction is a common technique used in deep learning to center the data</span><br />
<span style="color: #333333; font-family: "helvetica" , "arial" , sans-serif; font-size: 18px;">For ILSVRC dataset, the mean is B = 102 Green = 117 Red = 123</span><br />
<br />
<br />
If you want to change image<br />
<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1">python3 image-classifier.py -i image file</span></div>
<br />
Ex.<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1">python3 image-classifier.py -i ../../data/images/pic_005.jpg</span></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhzUULFill5Qlrjtn5_4qlv99ESnRplkJZ17CtTMKiTHYhAHo0obRhCTwtXgLvHA4UNEUAXshI5Nwd9Fn-KEedtvfoMXx77bjZyo2KYwxAsx0c2MZBnZeGxjoKc3WXq36dzfqznG_nQdsvk/s1600/Python+%25281%2529.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="200" data-original-width="273" height="146" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhzUULFill5Qlrjtn5_4qlv99ESnRplkJZ17CtTMKiTHYhAHo0obRhCTwtXgLvHA4UNEUAXshI5Nwd9Fn-KEedtvfoMXx77bjZyo2KYwxAsx0c2MZBnZeGxjoKc3WXq36dzfqznG_nQdsvk/s200/Python+%25281%2529.png" width="200" /></a></div>
<h3>
<b><span style="color: blue;">Python Code</span></b></h3>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Before using the NCSDK API framework, we have to import mvncapi module from mvnc library</div>
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="kn" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">import</span> <span class="nn" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">mvnc.mvncapi</span> <span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">as</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">mvnc</span></code></pre>
</figure><br />
<h4 id="step-1-open-the-enumerated-device" style="border: 0px; box-sizing: border-box; color: #666666; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
Step 1: Open the enumerated device</h4>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Just like any other USB device, when you plug the NCS into your application processor’s (Ubuntu laptop/desktop) USB port, it enumerates itself as a USB device. We will call an API to look for the enumerated NCS device.</div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Look for enumerated Intel Movidius NCS device(s); quit program if none found.</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">devices</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">mvnc</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">EnumerateDevices</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">if</span> <span class="nb" style="border: 0px; box-sizing: border-box; color: #b58900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">len</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">devices</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">==</span> <span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">0</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">:</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">print</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'No devices found'</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">quit</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span></code></pre>
</figure><br />
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Did you know that you can connect multiple Neural Compute Sticks to the same application processor to scale inference performance? More about this in a later blog, but for now let’s call the APIs to pick just one NCS and open it (get it ready for operation).</div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Get a handle to the first enumerated device and open it</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">device</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">mvnc</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">Device</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">devices</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">[</span><span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">0</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">]</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">device</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">OpenDevice</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span></code></pre>
</figure><br />
<h4 id="step-2-load-a-graph-file-onto-the-ncs" style="border: 0px; box-sizing: border-box; color: #666666; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
Step 2: Load a graph file onto the NCS</h4>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
To keep this project simple, we will use a pre-compiled graph of a pre-trained AlexNet model, which was downloaded and compiled when you ran <code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">make</code> inside the <code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">ncappzoo</code> folder. We will learn how to compile a pre-trained network in an another blog, but for now let’s figure out how to load the graph into the NCS.</div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Read the graph file into a buffer</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">with</span> <span class="nb" style="border: 0px; box-sizing: border-box; color: #b58900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">open</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">GRAPH_PATH</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">mode</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span><span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'rb'</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span> <span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">as</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">f</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">:</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">blob</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">f</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">read</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Load the graph buffer into the NCS</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">graph</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">device</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">AllocateGraph</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">blob</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span></code></pre>
</figure><br />
<h4 id="step-3-offload-a-single-image-onto-the-intel-movidius-ncs-to-run-inference" style="border: 0px; box-sizing: border-box; color: #666666; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
Step 3: Offload a single image onto the Intel Movidius NCS to run inference</h4>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
The Intel Movidius NCS is powered by the Intel Movidius visual processing unit (VPU). It is the same chip that provides visual intelligence to millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, and more. Just like the VPU, the NCS acts as a visual co-processor in the entire system. In our case, we will use the Ubuntu system to simply read images from a folder and offload it to the NCS for inference. All of the neural network processing is done solely by the NCS, thereby freeing up the application processor’s CPU and memory resources to perform other application-level tasks.</div>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
In order to load an image onto the NCS, we will have to pre-process the image.</div>
<ol style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; list-style-image: initial; list-style-position: initial; margin: 14px 0px; padding: 0px 0px 0px 30px; vertical-align: baseline;">
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">Resize/crop the image to match the dimensions defined by the pre-trained network.<ul style="border: 0px; box-sizing: border-box; font: inherit; list-style-image: initial; list-style-position: initial; margin: 0px; padding: 0px 0px 0px 30px; vertical-align: baseline;">
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">GoogLeNet uses 224x224 pixels, AlexNet uses 227x227 pixels.</li>
</ul>
</li>
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">Subtract mean per channel (Blue, Green and Red) from the entire dataset.<ul style="border: 0px; box-sizing: border-box; font: inherit; list-style-image: initial; list-style-position: initial; margin: 0px; padding: 0px 0px 0px 30px; vertical-align: baseline;">
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">This is a common technique used in deep learning to center the data.</li>
</ul>
</li>
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">Convert the image into a half-precision floating point (fp16) array and use <code class="highlighter-rouge" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">LoadTensor</code>function-call to load the image onto NCS.<ul style="border: 0px; box-sizing: border-box; font: inherit; list-style-image: initial; list-style-position: initial; margin: 0px; padding: 0px 0px 0px 30px; vertical-align: baseline;">
<li style="border: 0px; box-sizing: border-box; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">skimage library can do this in just one line of code.</li>
</ul>
</li>
</ol>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Read & resize image [Image size is defined during training]</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">print_img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">skimage</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">io</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">imread</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGES_PATH</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">skimage</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">transform</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">resize</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_DIM</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">preserve_range</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span><span class="bp" style="border: 0px; box-sizing: border-box; color: #268bd2; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">True</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Convert RGB to BGR [skimage reads image in RGB, but Caffe uses BGR]</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">[:,</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">:,</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">::</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">-</span><span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">1</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">]</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Mean subtraction & scaling [A common technique used to center the data]</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">astype</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">numpy</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">float32</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">-</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_MEAN</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">*</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGE_STDDEV</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Load the image as a half-precision floating point array</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">graph</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">LoadTensor</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">img</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">astype</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">numpy</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">float16</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">),</span> <span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'user object'</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span></code></pre>
</figure><br />
<h4 id="step-4-read-and-print-inference-results-from-the-ncs" style="border: 0px; box-sizing: border-box; color: #666666; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
Step 4: Read and print inference results from the NCS</h4>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
Depending on how you want to integrate the inference results into your application flow, you can choose to use either a blocking or non-blocking function call to load tensor (previous step) and read inference results. We will learn more about this functionality in a later blog, but for now let’s just use the default, which is a blocking call (no need to call a specific API).</div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Get the results from NCS</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">output</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">userobj</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">graph</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">GetResult</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Print the results</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">print</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span><span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'</span><span class="se" style="border: 0px; box-sizing: border-box; color: #cb4b16; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">\n</span><span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">------- predictions --------'</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">labels</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">numpy</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">loadtxt</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">LABELS_FILE_PATH</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="nb" style="border: 0px; box-sizing: border-box; color: #b58900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">str</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">delimiter</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'</span><span class="se" style="border: 0px; box-sizing: border-box; color: #cb4b16; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">\t</span><span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">order</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">=</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">output</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">argsort</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()[::</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">-</span><span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">1</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">][:</span><span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">6</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">]</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">for</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">i</span> <span class="ow" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">in</span> <span class="nb" style="border: 0px; box-sizing: border-box; color: #b58900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">range</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">0</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">,</span> <span class="mi" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">5</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">):</span>
<span class="k" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">print</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span><span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">'prediction '</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">+</span> <span class="nb" style="border: 0px; box-sizing: border-box; color: #b58900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">str</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">i</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">+</span> <span class="s" style="border: 0px; box-sizing: border-box; color: #2aa198; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">' is '</span> <span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">+</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">labels</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">[</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">order</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">[</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">i</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">]])</span>
<span class="c" style="border: 0px; box-sizing: border-box; color: #586e75; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"># Display the image on which inference was performed</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">skimage</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">io</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">imshow</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">IMAGES_PATH</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">skimage</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">io</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">show</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">(</span> <span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">)</span></code></pre>
</figure><br />
<h4 id="step-5-unload-the-graph-and-close-the-device" style="border: 0px; box-sizing: border-box; color: #666666; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 1.7; margin: 1em 0px 14px; padding: 0px; vertical-align: baseline;">
Step 5: Unload the graph and close the device</h4>
<div style="border: 0px; box-sizing: border-box; color: #333333; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin-bottom: 14px; margin-top: 14px; padding: 0px; vertical-align: baseline;">
In order to avoid memory leaks and/or segmentation faults, we should close any open files or resources and deallocate any used memory.</div>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<figure class="highlight" style="background-color: #263238; border-radius: 3px; border: 3px solid rgb(58, 58, 58); box-sizing: border-box; color: #eaeaea; font-family: Helvetica, Arial, sans-serif; font-size: 18px; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: 18px; margin: 20px 0px; overflow: auto; padding: 7px 7px 7px 10px; vertical-align: baseline;"><pre style="border: 0px; box-sizing: border-box; font: inherit; padding: 0px; vertical-align: baseline;"><code class="language-python" data-lang="python" style="border: 0px; box-sizing: border-box; font-family: "Bitstream Vera Sans Mono", Courier, monospace; font-size: 16.2px; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline;"><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">graph</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">DeallocateGraph</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span>
<span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">device</span><span class="o" style="border: 0px; box-sizing: border-box; color: #859900; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">.</span><span class="n" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">CloseDevice</span><span class="p" style="border: 0px; box-sizing: border-box; color: #93a1a1; font: inherit; margin: 0px; padding: 0px; vertical-align: baseline;">()</span></code></pre>
</figure><br />
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
This code runs GoogLeNet by default, but you can configure it run other pre-trained deep neural networks. Below are some example commands:</div>
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
AlexNet (Caffe)</div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 16px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 image-classifier.py --graph ../../caffe/AlexNet/graph --dim 227 227 --image ../../data/images/pic_053.jpg
</code></pre>
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
SqueezeNet (Caffe)</div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 16px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 image-classifier.py --graph ../../caffe/SqueezeNet/graph --dim 227 227 --image ../../data/images/pic_053.jpg
</code></pre>
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Mobilenet (Tensorflow)</div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 16px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 image-classifier.py --graph ../../tensorflow/mobilenets/model/graph --labels ../../tensorflow/mobilenets/model/labels.txt --mean 127.5 --scale 0.00789 --dim 224 224 --colormode="RGB" --image ../../data/images/pic_053.jpg
</code></pre>
<div style="box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Inception (Tensorflow)</div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 16px; overflow-wrap: normal; overflow: auto; padding: 16px;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 image-classifier.py --graph ../../tensorflow/inception/model/v3/graph --labels ../../tensorflow/inception/model/v3/labels.txt --mean 127.5 --scale 0.00789 --dim 299 299 --colormode="RGB" --image ../../data/images/pic_053.jpg </code></pre>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgT8fGQwGcwA0U7P8VMt9sL_IfM5NvOmadLpm1JQq-8bc-DpTfHkiDD8mNvGLsJNGo86cp_2mAp8bFmPJgLP4OQKnrO0Q_Q0v6heCCTfQHj43d_p6q00Cf7Sb2Twe2Uehbz_AE0BObSi7m0/s1600/tensorflowlogo.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="352" height="170" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgT8fGQwGcwA0U7P8VMt9sL_IfM5NvOmadLpm1JQq-8bc-DpTfHkiDD8mNvGLsJNGo86cp_2mAp8bFmPJgLP4OQKnrO0Q_Q0v6heCCTfQHj43d_p6q00Cf7Sb2Twe2Uehbz_AE0BObSi7m0/s200/tensorflowlogo.png" width="200" /></a></div>
<h3>
<b><span style="color: blue;">Test with TensorFlow Inception Model.</span></b></h3>
Change Directory to <b style="color: #5330e1; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">~/ncappzoo/tensorflow/inception</b><br />
<b style="color: #5330e1; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><br /></b>
<br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b>~/ncappzoo/tensorflow/inception $</b></span><span class="s2"> <span style="background-color: yellow;">make help</span></span></div>
<div class="p2">
<span class="s3"></span><br /></div>
<div class="p3">
<span class="s3"><b>Possible make targets:<span class="Apple-converted-space"> </span></b></span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make help - Shows this message.</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make all - Builds all dependencies, but does not run this program.</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make checkpoint - Downloads pre-trained checkpoint files.;</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make clean - Removes all files created in this project.;</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make export - Export the neural network model for inference.</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make freeze - Freeze the neural network model for inference.</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make compile - Convert the frozen model into Movidius graph file.</span></div>
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make check - Compare inference results with that of TensorFlow running on CPU/GPU.</span></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; min-height: 18.0px}
p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
p.p4 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p4">
<span class="s3"><span class="Apple-converted-space"> </span>make profile - Run the model on NCS and extract complexity, bandwidth and execution time for each layer.</span></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<br />
<br />
<div class="p1">
<span class="s1"><b>pi@raspberrypi</b></span><span class="s2">:</span><span class="s3"><b>~/ncappzoo/tensorflow/inception $</b></span><span class="s2"> <span style="background-color: yellow;">make all</span></span></div>
<div class="p2">
<span class="s3">TF_SRC_PATH not set, making tf_src</span></div>
<div class="p2">
<span class="s3">(cd ../tf_src; make all; cd /home/pi/ncappzoo/tensorflow/inception)</span></div>
<div class="p2">
<span class="s3">make[1]: Entering directory '/home/pi/ncappzoo/tensorflow/tf_src'</span></div>
<div class="p2">
<span class="s3">TF_SRC_PATH not set, will use project directory</span></div>
<div class="p2">
<span class="s3">TF_SRC_PATH is now: /home/pi/ncappzoo/tensorflow/tf_src/tensorflow</span></div>
<div class="p2">
<span class="s3">skipping clone, directory already exists: /home/pi/ncappzoo/tensorflow/tf_src/tensorflow</span></div>
<div class="p2">
<span class="s3">make[1]: Leaving directory '/home/pi/ncappzoo/tensorflow/tf_src'</span></div>
<div class="p2">
<span class="s3">TF_SRC_PATH is /home/pi/ncappzoo/tensorflow/inception/../tf_src/tensorflow</span></div>
<div class="p3">
<span class="s3"></span><br /></div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #5330e1}
p.p2 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo}
p.p3 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; min-height: 18.0px}
p.p4 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
span.s1 {font-variant-ligatures: no-common-ligatures; color: #34bd26}
span.s2 {font-variant-ligatures: no-common-ligatures; color: #000000}
span.s3 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p4">
<span class="s3"><b>Downloading checkpoint files...</b></span></div>
<b style="color: #afad24; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">..</b><br />
<b style="color: #afad24; font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;">...</b><br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1"><b><span style="color: #6aa84f;">Exporting GraphDef file...</span></b></span></div>
<div class="p1">
<span class="s1"><b><span style="color: #6aa84f;">..</span></b></span></div>
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;">...</span></b><br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1"><b><span style="color: #6aa84f;">Freezing model for inference...</span></b></span></div>
<div class="p1">
<span class="s1"><span style="color: #6aa84f;">
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
</span></span></div>
<div class="p1">
<span class="s1"><b><span style="color: #6aa84f;">..</span></b></span></div>
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;">...</span></b><br />
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;">Profiling the model...</span></b><br />
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;">..</span></b><br />
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;">...</span></b><br />
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #6aa84f;"><br /></span></b>
<b style="font-family: Menlo; font-size: 15px; font-variant-ligatures: no-common-ligatures;"><span style="color: #93c47d;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhN4-a6xLmaG95K9MvuHG2mGYKHrvwftBO8o9w38Imj40DSmn8sqrZeuJH3L5I9Hx7G5Z7iYPzBoSM44FaNJH5xq3BFoV3ySkgOoOhfyNxYoCQs5OvZkvNr17jqQoJrh-i5BaGisfZZw4h2/s1600/ncsdk-tensorflow-inception.png" imageanchor="1"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhN4-a6xLmaG95K9MvuHG2mGYKHrvwftBO8o9w38Imj40DSmn8sqrZeuJH3L5I9Hx7G5Z7iYPzBoSM44FaNJH5xq3BFoV3ySkgOoOhfyNxYoCQs5OvZkvNr17jqQoJrh-i5BaGisfZZw4h2/s1600/ncsdk-tensorflow-inception.png" /></a></span></b><br />
<br />
<br />
Run Python Code<br />
<br />
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 14.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1">python3 image-classifier.py -g ../../tensorflow/inception/model/v3/graph -D 299 299 -M 127.5 -S 0.00789<span class="Apple-converted-space"> </span>-l ../../tensorflow/inception/model/v3/labels.txt -i ~/ncappzoo/data/images/cat.jpg</span></div>
<div class="p1">
<span class="s1"><br /></span></div>
<div class="p1">
<span class="s1"><br /></span></div>
<div class="p1">
<span class="s1">==============================================================</span></div>
<div class="p1">
<span class="s1">Top predictions for cat.jpg</span></div>
<div class="p1">
<span class="s1">Execution <span style="background-color: cyan;">time: 317.015ms</span></span></div>
<div class="p1">
<span class="s1">--------------------------------------------------------------</span></div>
<div class="p1">
<span class="s1">54.7%<span class="Apple-tab-span"> </span>286:Egyptian cat</span></div>
<div class="p1">
<span class="s1">21.8%<span class="Apple-tab-span"> </span>282:tabby, tabby cat</span></div>
<div class="p1">
<span class="s1">8.6%<span class="Apple-tab-span"> </span>283:tiger cat</span></div>
<div class="p1">
<span class="s1">3.7%<span class="Apple-tab-span"> </span>288:lynx, catamount</span></div>
<div class="p1">
<span class="s1">2.3%<span class="Apple-tab-span"> </span>285:Siamese cat, Siamese</span></div>
<div class="p1">
<span class="s1">
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 14.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures}
span.Apple-tab-span {white-space:pre}
</style>
</span></div>
<div class="p1">
<span class="s1">==============================================================</span></div>
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjg-WPdQ9pCjS1GEgP8mG3nEfAy1F8MQoOSoHn_mk2RWqGzfqw9ldnJZLm2q4HhbfYvHDdm7iso7Ce6TNcadCCXvWdrbt3mBK3ofNqEFftd4J-SBAHYS2lbbGWErUhx8yoiXXTOrNPiSsro/s1600/rpi-img-tensorflow.png" imageanchor="1"><img border="0" height="246" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjg-WPdQ9pCjS1GEgP8mG3nEfAy1F8MQoOSoHn_mk2RWqGzfqw9ldnJZLm2q4HhbfYvHDdm7iso7Ce6TNcadCCXvWdrbt3mBK3ofNqEFftd4J-SBAHYS2lbbGWErUhx8yoiXXTOrNPiSsro/s400/rpi-img-tensorflow.png" width="400" /></a><br />
<br />
<br />
<b><span style="color: blue;">Reference</span></b><br />
<a href="https://movidius.github.io/blog/ncs-image-classifier/">https://movidius.github.io/blog/ncs-image-classifier/</a><br />
<a href="https://github.com/movidius/ncappzoo/">https://github.com/movidius/ncappzoo/</a><br />
<br />
<br />
<br />
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">
<div style="margin: 0px; position: relative;">
<b><span style="color: red;">My Website</span></b></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="color: #888888; font-family: "arial" , "helvetica" , sans-serif;"><a href="http://softpowergroup.net/" style="color: #888888; text-decoration-line: none;" target="_blank">http://softpowergroup.net/</a></span></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
</div>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 15.0px Menlo; color: #afad24}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com2tag:blogger.com,1999:blog-7853792980726640018.post-47535668933244342972018-11-02T05:23:00.000-07:002018-12-16T19:14:40.216-08:00Raspberry pi TensorFlow Object Detection API<iframe allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/M5Y3lmrWu8w" width="560"></iframe>
<br />
<h2>
<b><span style="color: magenta; font-size: large;">Raspberry pi TensorFlow Object Detection API</span></b></h2>
<br />
<b>What is TensorFlow Object Detection API?</b><br />
<br />
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;">Creating accurate machine learning models capable of localizing and identifying multiple objects in a single image remains a core challenge in computer vision. The TensorFlow Object Detection API is an open source framework built on top of TensorFlow that makes it easy to construct, train and deploy object detection models. At Google we’ve certainly found this codebase to be useful for our computer vision needs, and we hope that you will as well.</span><br />
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzZvNIV0Ab8QBwMCTiEP9jjO2MmPjT2lR9_dQIhFAeHu1otYdE8hYewJNG2gqu4xmncbcGxNBb_ppv_7A7DHZBlfvnBBslamDo-bqOo1c_48dF3Uy4sz0CXKn7GGWBxmV7-o-fIO5rQi8l/s1600/rpi3b%252B.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="319" data-original-width="512" height="124" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzZvNIV0Ab8QBwMCTiEP9jjO2MmPjT2lR9_dQIhFAeHu1otYdE8hYewJNG2gqu4xmncbcGxNBb_ppv_7A7DHZBlfvnBBslamDo-bqOo1c_48dF3Uy4sz0CXKn7GGWBxmV7-o-fIO5rQi8l/s200/rpi3b%252B.jpeg" width="200" /></a></div>
<span style="background-color: white; color: rgba(0 , 0 , 0 , 0.84); letter-spacing: -0.015em;"><b>Why Raspberry Pi?</b></span><br />
<div class="graf graf--p graf-after--h3" id="4185" name="4185" style="background-color: white; line-height: 1.58; margin-top: 8px;">
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
The raspberry pi is a neat piece of hardware that has captured the hearts of a generation with ~15M devices sold, with hackers building even <a class="markup--anchor markup--p-anchor" data-href="http://www.trustedreviews.com/opinion/best-raspberry-pi-projects-pi-3-pi-zero-2949390" href="http://www.trustedreviews.com/opinion/best-raspberry-pi-projects-pi-3-pi-zero-2949390" rel="noopener nofollow" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0.54); background-color: transparent; background-image: linear-gradient(rgba(0, 0, 0, 0.68) 50%, rgba(0, 0, 0, 0) 50%); background-position: 0px 1.07em; background-repeat: repeat-x; background-size: 2px 0.1em; text-decoration-line: none;" target="_blank">cooler projects</a> on it. Given the popularity of Deep Learning and the <a class="markup--anchor markup--p-anchor" data-href="https://www.raspberrypi.org/products/camera-module-v2/" href="https://www.raspberrypi.org/products/camera-module-v2/" rel="noopener nofollow" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0.54); background-color: transparent; background-image: linear-gradient(rgba(0, 0, 0, 0.68) 50%, rgba(0, 0, 0, 0) 50%); background-position: 0px 1.07em; background-repeat: repeat-x; background-size: 2px 0.1em; text-decoration-line: none;" target="_blank">Raspberry Pi Camera</a> we thought it would be nice if we could detect any object using Deep Learning on the Pi.</div>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<br /></div>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<b>Steps</b></div>
<div style="letter-spacing: -0.003em;">
<b><span style="color: blue;">Install OpenCV</span></b></div>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><a href="http://raspberrypi4u.blogspot.com/2018/08/raspberry-pi-install-opencv.html" target="_blank">http://raspberrypi4u.blogspot.com/2018/08/raspberry-pi-install-opencv.html</a></span></span><br />
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<br /></div>
<div style="letter-spacing: -0.003em;">
<b><span style="color: blue;">Install TensorFlow</span></b></div>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><a href="https://www.tensorflow.org/install/" target="_blank">https://www.tensorflow.org/install/</a></span></span><br />
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<br /></div>
<div style="letter-spacing: -0.003em;">
<b><span style="color: blue;">Install Protobuf</span></b></div>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md" target="_blank">https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md</a></span></span><br />
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><br /></span></span>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">get the packages needed</span></span></span><br />
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"></span></span><br />
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">sudo apt-get install autoconf automake libtool curl</code></pre>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">download the protobuf </span><br />
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">wget https://github.com/google/protobuf/releases/download/v3.5.1/protobuf-all-3.5.1.tar.gz</code></pre>
</div>
<div style="letter-spacing: -0.003em;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">tar -zxvf protobuf-all-3.5.1.tar.gz
cd protobuf-3.5.1</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Configure the build</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">./configure</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Build the package</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">make -j4</code></pre>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">sudo make install</code></pre>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">cd python
export LD_LIBRARY_PATH=../src/.libs</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">python setup</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 setup.py build --cpp_implementation
python3 setup.py test --cpp_implementation
sudo python3 setup.py install --cpp_implementation</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">path commands</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=cpp
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION_VERSION=3</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Finally</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">sudo ldconfig</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<b>Test</b></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">protoc</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjfeI0J52A9h362qkbL2HRK_K5KZx4D6m78oohfED9hnt_QqO1uoCZmZftWTCStPEJMAcTmPwYDJoURh2AxlWMw42qlQ5tGKOecO1aaWCxnMAYv5e4hiea5IomRlp8fTxVSNihzkewr6VfB/s1600/tensorflowlogo.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="352" height="170" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjfeI0J52A9h362qkbL2HRK_K5KZx4D6m78oohfED9hnt_QqO1uoCZmZftWTCStPEJMAcTmPwYDJoURh2AxlWMw42qlQ5tGKOecO1aaWCxnMAYv5e4hiea5IomRlp8fTxVSNihzkewr6VfB/s200/tensorflowlogo.png" width="200" /></a></div>
</div>
<b><span style="color: blue;">Setup TensorFlow Directory </span></b></div>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<br /></div>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">mkdir tensorflow1
cd tensorflow1</code></pre>
</div>
<div style="color: rgba(0, 0, 0, 0.84); letter-spacing: -0.003em;">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Download the tensorflow repository</span><br />
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">git clone --recurse-submodules https://github.com/tensorflow/models.git</code></pre>
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">we need to modify the PYTHONPATH environment</span><br />
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">sudo nano ~/.bashrc</code></pre>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">export PYTHONPATH=$PYTHONPATH:/home/pi/tensorflow1/models/research:/home/pi/tensorflow1/models/research/slim</code></pre>
</div>
<div style="letter-spacing: -0.003em;">
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
<div style="color: rgba(0, 0, 0, 0.84);">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjrqX_HAMjNdsKeNWIyIgDCcea2Rbii9nJaLMfrhmGK8XJm-P60uuwVtHfDkLVQuV7ofdrInLyt-MX9XgoI6aMWegvPKQb7xrxy_jvzntf2mvL99msfC4wpwyXJss4AU-kzSQptq05Cx9ZV/s1600/bashrc.png" imageanchor="1"><img border="0" height="230" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjrqX_HAMjNdsKeNWIyIgDCcea2Rbii9nJaLMfrhmGK8XJm-P60uuwVtHfDkLVQuV7ofdrInLyt-MX9XgoI6aMWegvPKQb7xrxy_jvzntf2mvL99msfC4wpwyXJss4AU-kzSQptq05Cx9ZV/s400/bashrc.png" width="400" /></a></div>
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">cd /home/pi/tensorflow1/models/research
protoc object_detection/protos/*.proto --python_out=.</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">cd /home/pi/tensorflow1/models/research/object_detection</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Download the SSDLite-MobileNet model</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">wget http://download.tensorflow.org/models/object_detection/ssdlite_mobilenet_v2_coco_2018_05_09.tar.gz
tar -xzvf ssdlite_mobilenet_v2_coco_2018_05_09.tar.gz</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEivtGRExc10s82-v_vWOZqIAP6aMOV-vfz7A5Nx33JmcqfRcMj_nbGj4WP29WP0qcD_7Zw2hBCiLTM9Ulm3QpS4L5C3103Y7H0p42MQ9ZMZK0sreZzljTjNp-hcHLgfyPFpXKfJOZfOUshy/s1600/Screen+Shot+2018-11-02+at+8.39.29+PM.png" imageanchor="1"><img border="0" height="317" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEivtGRExc10s82-v_vWOZqIAP6aMOV-vfz7A5Nx33JmcqfRcMj_nbGj4WP29WP0qcD_7Zw2hBCiLTM9Ulm3QpS4L5C3103Y7H0p42MQ9ZMZK0sreZzljTjNp-hcHLgfyPFpXKfJOZfOUshy/s400/Screen+Shot+2018-11-02+at+8.39.29+PM.png" width="400" /></a></div>
<h3>
<b><span style="color: blue;">RUN Code</span></b></h3>
<div>
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px; letter-spacing: normal;">Download the code</span></div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">wget https://raw.githubusercontent.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi/master/Object_detection_picamera.py</code></pre>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 Object_detection_picamera.py --usbcam</code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
<div style="color: rgba(0, 0, 0, 0.84);">
if you use picam</div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; letter-spacing: normal; line-height: 1.45; margin-bottom: 1pc; overflow-wrap: normal; overflow: auto; padding: 1pc;"><code style="background: initial; border-radius: 3px; border: 0px; box-sizing: border-box; display: inline; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: inherit; margin: 0px; overflow-wrap: normal; overflow: visible; padding: 0px; word-break: normal;">python3 Object_detection_picamera.py </code></pre>
<div style="color: rgba(0, 0, 0, 0.84);">
<br /></div>
</div>
<div style="letter-spacing: -0.003em;">
<b><span style="color: blue;">Reference</span></b></div>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><span style="letter-spacing: -0.048px;"><a href="https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi" target="_blank">https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi</a></span></span><br />
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><br /></span>
<span style="color: #000027;"><a href="https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md">https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md</a></span><br />
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><br /></span>
<span style="color: rgba(0 , 0 , 0 , 0.83921568627451);"><br /></span>
<br />
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">
<div style="margin: 0px; position: relative;">
<b><span style="color: red;">My Website</span></b></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="color: #888888; font-family: "arial" , "helvetica" , sans-serif;"><a href="http://softpowergroup.net/" style="color: #888888; text-decoration-line: none;" target="_blank">http://softpowergroup.net/</a></span></div>
</div>
<div style="color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com3tag:blogger.com,1999:blog-7853792980726640018.post-5763724615568735872018-10-28T02:49:00.000-07:002018-11-01T21:00:56.217-07:00Raspberry pi YOLO Real-time Object Detection<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/HCDuSIUF7P0" width="560"></iframe>
<br />
<br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/M1047O5i5-g" width="560"></iframe>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 13.0px Menlo}
span.s1 {font-variant-ligatures: no-common-ligatures}
</style>
<br />
<div class="p1">
<span class="s1"><br /></span></div>
<div class="p1">
<h2>
<span class="s1" style="color: blue;">Raspberry pi YOLO Real-time Object Detection</span></h2>
</div>
<div class="p1">
<span class="s1"><span style="background-color: white; color: #444444; font-family: "roboto" , "arial" , sans-serif; font-size: 16px; letter-spacing: 1px;">You only look once (YOLO) is a state-of-the-art, real-time object detection system.</span></span></div>
<div class="p1">
<span class="s1" style="background-color: white; color: #444444;"><br /></span></div>
<h2 style="font-family: "roboto slab", serif; font-weight: 300;">
<span style="background-color: white;"><span style="color: blue;">
How It Works</span></span></h2>
<div style="font-family: roboto, arial, sans-serif; font-size: 16px; letter-spacing: 1px; margin-top: 0.5em;">
<span style="background-color: white;"><span style="color: #444444;">Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.</span></span></div>
<div style="font-family: roboto, arial, sans-serif; font-size: 16px; letter-spacing: 1px; margin-top: 0.5em;">
<span style="background-color: white;"><span style="color: #444444;">We use a totally different approach. We apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.</span></span></div>
<div style="font-family: roboto, arial, sans-serif; font-size: 16px; letter-spacing: 1px; margin-top: 0.5em;">
<img alt="" src="https://pjreddie.com/media/image/model2.png" style="display: block; margin-left: auto; margin-right: auto; max-width: 100%;" /></div>
<div style="font-family: roboto, arial, sans-serif; font-size: 16px; letter-spacing: 1px; margin-top: 0.5em;">
<span style="background-color: white;"><span style="color: #444444;">Our model has several advantages over classifier-based systems. It looks at the whole image at test time so its predictions are informed by global context in the image. It also makes predictions with a single network evaluation unlike systems like <a href="https://github.com/rbgirshick/rcnn">R-CNN</a> which require thousands for a single image. This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than <a href="https://github.com/rbgirshick/fast-rcnn">Fast R-CNN</a>. See our <a href="https://arxiv.org/abs/1612.08242">paper</a> for more details on the full system.</span></span></div>
<h3 style="font-family: "roboto slab", serif; font-weight: 300;">
<span style="background-color: white;"><span style="color: blue;">
What's New in Version 2?</span></span></h3>
<div class="p1">
<span style="background-color: white;"><span class="s1" style="color: #444444;"></span></span></div>
<div style="font-family: roboto, arial, sans-serif; font-size: 16px; letter-spacing: 1px; margin-top: 0.5em;">
<span style="background-color: white;"><span style="color: #444444;">YOLOv2 uses a few tricks to improve training and increase performance. Like Overfeat and SSD we use a fully-convolutional model, but we still train on whole images, not hard negatives. Like Faster R-CNN we adjust priors on bounding boxes instead of predicting the width and height outright. However, we still predict the <code style="font-family: "ubuntu mono", monospace;">x</code> and <code style="font-family: "ubuntu mono", monospace;">y</code> coordinates directly. The full details are in our <a href="https://arxiv.org/abs/1612.08242">paper</a>.!</span></span><br />
<span style="background-color: white;"><span style="color: #444444;"><br /></span></span>
<span style="background-color: white;"><span style="color: #444444;"><br /></span></span>
<b><span style="color: blue;"><span style="background-color: white;"><span style="color: #444444;">So,we've test run Yolov2 </span></span><span style="background-color: white;">on</span></span><span style="background-color: white; color: #444444;"> </span></b><br />
<br />
<ol>
<li><b>Raspberry pi only </b></li>
<li><b>Raspberry pi with intel movidius </b>( Neural Compute Stick )</li>
</ol>
<br />
<span style="background-color: white;"><span style="color: #444444;"><br /></span></span>
<span style="background-color: white;"><span style="color: #444444;"><br /></span></span></div>
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzZvNIV0Ab8QBwMCTiEP9jjO2MmPjT2lR9_dQIhFAeHu1otYdE8hYewJNG2gqu4xmncbcGxNBb_ppv_7A7DHZBlfvnBBslamDo-bqOo1c_48dF3Uy4sz0CXKn7GGWBxmV7-o-fIO5rQi8l/s1600/rpi3b%252B.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="319" data-original-width="512" height="199" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzZvNIV0Ab8QBwMCTiEP9jjO2MmPjT2lR9_dQIhFAeHu1otYdE8hYewJNG2gqu4xmncbcGxNBb_ppv_7A7DHZBlfvnBBslamDo-bqOo1c_48dF3Uy4sz0CXKn7GGWBxmV7-o-fIO5rQi8l/s320/rpi3b%252B.jpeg" width="320" /></a></div>
<div class="p1">
<h3>
<span class="s1" style="color: magenta;"><b>Run on Raspberry pi</b></span></h3>
<span class="s1"><br /></span>
<span class="s1"><b>Install darknet yolov2</b></span><br />
<span class="s1"></span>
<br />
<pre style="background-color: #220055; color: cyan; font-family: "Ubuntu Mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;"><code style="color: lime; font-family: "Ubuntu Mono", monospace;">git clone https://github.com/pjreddie/darknet
cd darknet
make</code></pre>
</div>
<div class="p1">
<span class="s1"><br /></span></div>
<div class="p1">
<span class="s1"><br /></span>
<span class="s1"><b>Download tiny-yolov2 weights</b></span><br />
<span class="s1"></span>
<br />
<pre style="background-color: #220055; color: cyan; font-family: "Ubuntu Mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;"><code style="color: lime; font-family: "Ubuntu Mono", monospace;">wget https://pjreddie.com/media/files/yolov2-tiny-voc.weights</code></pre>
<span class="s1"><br /></span>
<br />
<span class="s1"><b>Run Code</b></span><br />
<pre style="background-color: #220055; color: cyan; font-family: "Ubuntu Mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;"><code style="color: lime; font-family: "Ubuntu Mono", monospace;">./darknet detector test cfg/voc.data cfg/yolov2-tiny-voc.cfg yolov2-tiny-voc.weights data/dog.jpg</code></pre>
<span class="s1"><br /></span>
<span class="s1" style="background-color: yellow;">./darknet detector test cfg/voc.data cfg/yolov2-tiny-voc.cfg yolov2-tiny-voc.weights data/dog.jpg</span></div>
<br />
<b>Result</b><br />
<b><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhMjwjIoYjqZL68Ndh7EAYagE7Zpka6qZAvZXWU6QooHThRV3c4_8BACADzFUp9ltV5-KxiX9ai1giGLWzHpLoYKsIemtdeNI6xfWiPKuF3J6thAx0ZjyqYw2uP8I7BBR2QZIPEhcyatcFx/s1600/predictions.jpg" imageanchor="1"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhMjwjIoYjqZL68Ndh7EAYagE7Zpka6qZAvZXWU6QooHThRV3c4_8BACADzFUp9ltV5-KxiX9ai1giGLWzHpLoYKsIemtdeNI6xfWiPKuF3J6thAx0ZjyqYw2uP8I7BBR2QZIPEhcyatcFx/s320/predictions.jpg" width="320" /></a></b><br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhZSC29MAAqGYTlrXJQTLziTZEcd3qKiB51HHGu9v9VF6WBSpYla1W1CmHU7-olXPZD0ea-tUDKlmg2rZqbJ-1Ydm0iwBNiAIPBEMFKu2hYy7qCVLXC9Ecu7bzXsm8Zs8bWEPWclvJqJwwT/s1600/rpi-yolo-time.png" imageanchor="1"><img border="0" height="372" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhZSC29MAAqGYTlrXJQTLziTZEcd3qKiB51HHGu9v9VF6WBSpYla1W1CmHU7-olXPZD0ea-tUDKlmg2rZqbJ-1Ydm0iwBNiAIPBEMFKu2hYy7qCVLXC9Ecu7bzXsm8Zs8bWEPWclvJqJwwT/s640/rpi-yolo-time.png" width="640" /></a><br />
<br />
<b><span style="color: #e06666;">Process time = 32.36 sec.</span></b><br />
<br />
<br />
<br />
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA2EHbSwTCMKup1FjefB6w32p0xFNl-itzknhLlLd7WH89cMHgjdjv3CxMaQ9v8_TFzyrsENoXllMMAFAaXkVsVSOivYcfFDL7ptyx_YoNBAqoK6KX-3Cb5T9FLrNLnFisxEAl8NEmxFBR/s1600/raspberrypi-intel-movidius.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="752" data-original-width="1600" height="299" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiA2EHbSwTCMKup1FjefB6w32p0xFNl-itzknhLlLd7WH89cMHgjdjv3CxMaQ9v8_TFzyrsENoXllMMAFAaXkVsVSOivYcfFDL7ptyx_YoNBAqoK6KX-3Cb5T9FLrNLnFisxEAl8NEmxFBR/s640/raspberrypi-intel-movidius.png" width="640" /></a></div>
<h3>
<span style="color: magenta;">Run on Raspberry pi with Intel Movidius ( Neural Compute Stick )</span></h3>
<div>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
<em style="box-sizing: border-box;">This project shows how to run tiny yolov2 (20 classes) with movidius stick:</em></div>
<ul style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px; margin-top: 0px; padding-left: 2em;">
<li style="box-sizing: border-box;">A python convertor from yolo to caffe</li>
<li style="box-sizing: border-box; margin-top: 0.25em;">A c/c++ implementation and python wrapper for region layer of yolov2</li>
<li style="box-sizing: border-box; margin-top: 0.25em;">A sample for running yolov2 with movidius stick in images or videos</li>
</ul>
</div>
<b><br /></b>
<b>Install NCSDK 2.0 </b>( <a href="https://raspberrypi4u.blogspot.com/2018/10/install-intel-movidius-neural-compute-sdk.html" target="_blank">see this</a> )<br />
<a href="https://raspberrypi4u.blogspot.com/2018/10/install-intel-movidius-neural-compute-sdk.html">https://raspberrypi4u.blogspot.com/2018/10/install-intel-movidius-neural-compute-sdk.html</a><br />
<br />
<br />
<b>Install YOLOv2NCS</b><br />
<pre style="background-color: #220055; color: cyan; font-family: "ubuntu mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;">git clone https://github.com/duangenquan/YoloV2NCS.git</pre>
<br />
<b>then make</b><br />
<pre style="background-color: #220055; font-family: "ubuntu mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;"><code style="font-family: "ubuntu mono", monospace;"><span style="color: cyan;">cd YoloV2NCS
make</span></code></pre>
<br />
<b>Convert Caffe to NCS</b><br />
<pre style="background-color: #220055; color: cyan; font-family: "ubuntu mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;">mvNCCompile ./models/caffemodels/yoloV2Tiny20.prototxt -w ./models/caffemodels/yoloV2Tiny20.caffemodel -s 12</pre>
<br />
<b>Run Python Code</b><br />
<pre style="background-color: #220055; color: cyan; font-family: "ubuntu mono", monospace; font-size: 16px; overflow: scroll; padding: 1em;">python3 ./detectionExample/Main.py --image ./data/dog.jpg</pre>
<div>
<br /></div>
<div>
<b>Result</b></div>
<div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEijmRLOhF_mCgoPvoTcMeJcws5CRN5MUHK9rFFrYayUEcxXH9ZT6TZacUMn89Fq-EoZuhCK7iHV9SBa5gV_1aosu-lUkmliSBpRwzAi-BvkG-v94SMU5mg-Q4RBp3tdK-AD3sFGek7Zn0wK/s1600/yolo_dog.jpg" imageanchor="1"><img border="0" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEijmRLOhF_mCgoPvoTcMeJcws5CRN5MUHK9rFFrYayUEcxXH9ZT6TZacUMn89Fq-EoZuhCK7iHV9SBa5gV_1aosu-lUkmliSBpRwzAi-BvkG-v94SMU5mg-Q4RBp3tdK-AD3sFGek7Zn0wK/s320/yolo_dog.jpg" width="320" /></a></div>
<div>
<br /></div>
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoSuPLeFfJC_TSZUb4q9xfErw4imPD826VBL8rfqmdU38lrkBBX-2KV9LV69gOetwHoyv9TewkHIp01bH2uscnmwbekVdGqxdjyGW7Guj9HTKSvqN51veBBGFvjzMrlmxAps6dKHHVZIF4/s1600/rpi-ncs-yolo-time.png" imageanchor="1"><img border="0" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgoSuPLeFfJC_TSZUb4q9xfErw4imPD826VBL8rfqmdU38lrkBBX-2KV9LV69gOetwHoyv9TewkHIp01bH2uscnmwbekVdGqxdjyGW7Guj9HTKSvqN51veBBGFvjzMrlmxAps6dKHHVZIF4/s640/rpi-ncs-yolo-time.png" width="640" /></a><br />
<br />
<b><span style="color: #cc0000;">Process time = 571 ms.</span></b><br />
<br />
<br />
<h3>
<b>Reference</b></h3>
<a href="https://pjreddie.com/darknet/yolov2/">https://pjreddie.com/darknet/yolov2/</a><br />
<a href="https://github.com/duangenquan/YoloV2NCS">https://github.com/duangenquan/YoloV2NCS</a><br />
<br />
<h1 class="title style-scope ytd-video-primary-info-renderer" style="background: rgb(255, 255, 255); border: 0px; color: var(--ytd-video-primary-info-renderer-title-color, var(--yt-primary-text-color)); font-family: Roboto, Arial, sans-serif; font-weight: 400; line-height: 2.4rem; margin: 0px; max-height: 4.8rem; overflow: hidden; padding: 0px; text-shadow: var(--ytd-video-primary-info-renderer-title-text-shadow, none); transform: var(--ytd-video-primary-info-renderer-title-transform, none);">
<yt-formatted-string class="style-scope ytd-video-primary-info-renderer" style="--yt-endpoint-color: hsl(206.1, 79.3%, 52.7%);"><span style="font-size: small;">How computers learn to recognize objects instantly | Joseph Redmon</span></yt-formatted-string></h1>
<a href="https://www.youtube.com/watch?v=Cgxsv1riJhI">https://www.youtube.com/watch?v=Cgxsv1riJhI</a><br />
<br />
<h1 class="title style-scope ytd-video-primary-info-renderer" style="background: rgb(255, 255, 255); border: 0px; color: var(--ytd-video-primary-info-renderer-title-color, var(--yt-primary-text-color)); font-family: Roboto, Arial, sans-serif; font-weight: 400; line-height: 2.4rem; margin: 0px; max-height: 4.8rem; overflow: hidden; padding: 0px; text-shadow: var(--ytd-video-primary-info-renderer-title-text-shadow, none); transform: var(--ytd-video-primary-info-renderer-title-transform, none);">
<yt-formatted-string class="style-scope ytd-video-primary-info-renderer" style="--yt-endpoint-color: hsl(206.1, 79.3%, 52.7%);"><span style="font-size: x-small;">YOLO Object Detection (TensorFlow tutorial)</span></yt-formatted-string></h1>
<a href="https://www.youtube.com/watch?v=4eIBisqx9_g">https://www.youtube.com/watch?v=4eIBisqx9_g</a><br />
<br />
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">
<div style="margin: 0px; position: relative;">
<b><span style="color: red;"><br class="Apple-interchange-newline" />My Website</span></b></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<a href="http://softpowergroup.net/" style="color: #888888; text-decoration-line: none;"><span style="font-family: "arial" , "helvetica" , sans-serif;">http://softpowergroup.net/</span></a></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
<br />
<br />Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com1tag:blogger.com,1999:blog-7853792980726640018.post-46441903782407089902018-10-23T19:12:00.000-07:002018-10-26T19:46:35.319-07:00 Intel® Movidius™ Neural Compute SDK Example Code on Raspberry pi<h2>
<span style="font-size: large;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiYej-jgHsLgEl-4GHe22dbm6BjM5tyFal1b_nUZVSoLUPVHtAqMiM85WgkOUGKilbE5OizeSlZqxonP36at_0BGQrcEn142NDO3wRZatODNdOan1Em18lwNfSRIuo0a-GvnTr0I0UhB_HC/s1600/ncs-workflow-768x431.png" imageanchor="1"><img border="0" height="356" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiYej-jgHsLgEl-4GHe22dbm6BjM5tyFal1b_nUZVSoLUPVHtAqMiM85WgkOUGKilbE5OizeSlZqxonP36at_0BGQrcEn142NDO3wRZatODNdOan1Em18lwNfSRIuo0a-GvnTr0I0UhB_HC/s640/ncs-workflow-768x431.png" width="640" /></a></span></h2>
<h2>
<span style="color: magenta; font-size: large;">Intel® Movidius™ Neural Compute SDK Example code on Raspberry pi</span></h2>
<br />
<br />
<h3 style="background-color: white; border-bottom: 1px solid rgb(234 , 236 , 239); box-sizing: border-box; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; line-height: 1.25; margin-bottom: 16px; margin-left: 0px; margin-right: 0px; margin-top: 0px; padding-bottom: 0.3em;">
<span style="font-size: small;">
Neural Compute Application Zoo (NC App Zoo)</span></h3>
<div>
<br /></div>
<div>
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;">The NC App Zoo is a community repository with many content owners and maintainers. All NC App Zoo content is being made available here in a central location for others to download, experiment with, modify, build upon, and learn from.</span></div>
<div>
<span style="background-color: white; color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: 16px;"><br /></span></div>
<div>
<pre style="background-color: #f6f8fa; border-radius: 3px; box-sizing: border-box; color: #24292e; font-family: SFMono-Regular, Consolas, "Liberation Mono", Menlo, Courier, monospace; font-size: 13.6px; line-height: 1.45; overflow-wrap: normal; overflow: auto; padding: 16px; word-break: normal;">git clone -b ncsdk2 https://github.com/movidius/ncappzoo.git</pre>
</div>
<br />
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
The NC App Zoo contains the following top-level directories. See the README file in each of these directory or just click on the links below to explore the contents of the NC App Zoo.</div>
<ul style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px; margin-top: 0px; padding-left: 2em;">
<li style="box-sizing: border-box;"><span style="box-sizing: border-box; font-weight: 600;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">apps</a></span> : Applications built to use the Intel Movidius NCS. <span style="box-sizing: border-box; font-weight: 600;">This is a great place to start in the NC App Zoo!</span></li>
<li style="box-sizing: border-box; margin-top: 0.25em;"><span style="box-sizing: border-box; font-weight: 600;"><a href="https://github.com/movidius/ncappzoo/blob/master/caffe/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">caffe</a></span> : Scripts to download caffe models and compile graphs for use with the NCS</li>
<li style="box-sizing: border-box; margin-top: 0.25em;"><span style="box-sizing: border-box; font-weight: 600;"><a href="https://github.com/movidius/ncappzoo/blob/master/tensorflow/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">tensorflow</a></span> : Scripts to download TensorFlow™ models and compile graphs for use with the NCS</li>
<li style="box-sizing: border-box; margin-top: 0.25em;"><span style="box-sizing: border-box; font-weight: 600;">data</span> : Data and scripts to download data for use with models and applications that use the NCS</li>
</ul>
<div>
<span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol";"><br /></span></div>
<div>
<h2 style="background-color: white; border-bottom: 1px solid rgb(234, 236, 239); box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; line-height: 1.25; margin-bottom: 16px; margin-top: 24px; padding-bottom: 0.3em;">
Image Classification Applications</h2>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Image classification applications typically use one of the image classification networks in the repository to classify an image as to it's likeliness to be in each of the classes on which a network was trained. For a step by step tutorial on how to build an image classification network look at <a href="https://movidius.github.io/blog/ncs-image-classifier/" rel="nofollow" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">Build an Image Classifier in 5 steps</a> at the Intel® Movidius™ Neural Compute Stick Blog</div>
<table style="background-color: white; border-collapse: collapse; border-spacing: 0px; box-sizing: border-box; color: #24292e; display: block; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px; margin-top: 0px; overflow: auto; width: 898px;"><thead style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Image Classification Application</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Description</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">++++++Thumbnail++++++</th></tr>
</thead><tbody style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/image-classifier/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">image-classifier</a><br />
<br style="box-sizing: border-box;" />
*Canonical Image Classification Example</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Networks<br />
Project that accompanies the blog <a href="https://movidius.github.io/blog/ncs-image-classifier" rel="nofollow" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">https://movidius.github.io/blog/ncs-image-classifier/.</a>. If you are getting started with image classification this is a good first stop.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/image-classifier/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/image-classifier/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/MultiStick_GoogLeNet/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">MultiStick_GoogLeNet</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe GoogLeNet<br />
Image classification on multiple devices. Shows scalability by using one GUI window to show inferences on a single stick and another window to show multiple sticks</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/MultiStick_GoogLeNet/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/MultiStick_GoogLeNet/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/MultiStick_TF_Inception/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">MultiStick_TF_Inception</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
TensorFlow Inception<br />
Image classification on multiple devices.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/MultiStick_TF_Inception/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/MultiStick_TF_Inception/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/classifier-gui/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">classifier-gui</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Network<br />
GUI to select network and image to classify.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/classifier-gui/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/classifier-gui/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/gender_age_lbp/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">gender_age_lbp</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">C++<br />
Caffe AgeNet, GenderNet<br />
Uses AgeNet and GenderNet to predict age and gender of people in a live camera feed. The camera feed is displayed with a box overlayed around the faces and a label for age and gender of the person. The face detection is done with OpenCV.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/gender_age_lbp/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/gender_age_lbp/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/live-image-classifier/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">live-image-classifier</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Networks<br />
Performs image classification on a live camera feed. This project was used to build a battery powered, RPi based, portable inference device (although RPi isn't required.) You can read more about this project at this NCS developer blog <a href="https://movidius.github.io/blog/battery-powered-dl-engine/" rel="nofollow" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">https://movidius.github.io/blog/battery-powered-dl-engine/</a>.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/live-image-classifier/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/live-image-classifier/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/log-image-classifier/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">log-image-classifier</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Networks<br />
Application logs results of an image classifier into a comma-separated values (CSV) file. Run inferences sequentially (and recursively) on all images within a folder.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/log-image-classifier/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/log-image-classifier/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/rapid-image-classifier/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">rapid-image-classifier</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Networks<br />
Performs image classification on a large number of images. This sample code was used to validate a Dogs vs Cats classifier built using a customized version of GoogLeNet. You can read more about this project (and a step-by-step guide) here <a href="https://movidius.github.io/blog/deploying-custom-caffe-models/" rel="nofollow" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">https://movidius.github.io/blog/deploying-custom-caffe-models/</a>.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/rapid-image-classifier/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/rapid-image-classifier/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_infer/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">stream_infer</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe SqueezeNet<br />
Uses gstreamer to grab frames from a live camera stream and run inferences on them while displaying top results in real time.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_infer/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/stream_infer/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_face_matcher/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">video_face_matcher</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
TensorFlow FaceNet<br />
Uses the tensorflow/FaceNet network to identify faces in a camera video stream. A single face image is used as the key and when a face in the video stream matches the key, a green frame is overlayed on the video feed.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_face_matcher/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/video_face_matcher/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_face_matcher_multipleFace/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">video_face_matcher_multipleFace</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
TensorFlow FaceNet<br />
Similar to the video_face_matcher application but supports matching multiple faces</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_face_matcher_multipleFace/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/video_face_matcher_multipleFace/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/topcoder_example/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">topcoder_example</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Networks<br />
Contains all supporting files needed to generate submissions.zip file, which would then be uploaded to the TopCoder leaderboard for automatic scoring of the NCS competition described here: <a href="https://developer.movidius.com/competition" rel="nofollow" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">https://developer.movidius.com/competition</a>. This program may be useful as a reference for doing accuracy calculations.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/topcoder_example/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/topcoder_example/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
</tbody></table>
<h2 style="background-color: white; border-bottom: 1px solid rgb(234, 236, 239); box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; line-height: 1.25; margin-bottom: 16px; margin-top: 24px; padding-bottom: 0.3em;">
<a aria-hidden="true" class="anchor" href="https://github.com/movidius/ncappzoo/tree/master/apps#object-detection-applications" id="user-content-object-detection-applications" style="background-color: initial; box-sizing: border-box; color: #0366d6; float: left; line-height: 1; margin-left: -20px; padding-right: 4px; text-decoration-line: none;"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewbox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z" fill-rule="evenodd"></path></svg></a>Object Detection Applications</h2>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Object detection appliations make use of one of the <a href="https://github.com/movidius/ncappzoo/blob/master/apps/TODO" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">object detection networks</a> in the repository to detect objects within an image. The object detection networks typically determine where objects are within the image as well as what type of objects they are.</div>
<table style="background-color: white; border-collapse: collapse; border-spacing: 0px; box-sizing: border-box; color: #24292e; display: block; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px; margin-top: 0px; overflow: auto; width: 898px;"><thead style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Object Detection Application</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Description</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">+++++Thumbnail+++++</th></tr>
</thead><tbody style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/birds/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">birds</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe Tiny Yolo, GoogLeNet<br />
Detects and identifies birds in photos by using Yolo Tiny to identify birds in general and then GoogLeNet to further classify them. Displays images with overlayed rectangles bird classification.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/birds/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/birds/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_ty_gn/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">stream_ty_gn</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe Tiny Yolo, GoogLeNet<br />
Sends frames of live camera stream to Tiny Yolo for object detection and then crops each object and sends that to GoogLeNet for further classification. This application requires two NCS devices, one for each network. Look at this example for straight forward example, but look at the threaded version if you are interested in better performance.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_ty_gn/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/stream_ty_gn/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_ty_gn_threaded/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">stream_ty_gn_threaded</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe Tiny Yolo, GoogLeNet<br />
Sends frames of live camera stream to Tiny Yolo for object detection and then crops each object and sends that to GoogLeNet for further classification. This application requires two NCS devices, one for each network. This is a threaded, better performing, and slightly more complex version of the stream_ty_gn application.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/stream_ty_gn_threaded/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/stream_ty_gn_threaded/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/street_cam/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">street_cam</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe TinyYolo, GoogLeNet<br />
Processes a video file (presumably produced by a street camera) and overlays boxes and labels around the objects detected. Objects are detected by Tiny Yolo and then further classified by GoogLeNet. This requires two NCS devices. Look at this example for straight forward example, but look at the threaded version if you are interested in better performance.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/street_cam/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/street_cam/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/street_cam_threaded/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">street_cam_threaded</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe TinyYolo, GoogLeNet<br />
Processes a video file (presumably produced by a street camera) and overlays boxes and labels around the objects detected. Objects are detected by Tiny Yolo and then further classified by GoogLeNet. This requires two NCS devices. This is a threaded, better performing, and more complex version of the street_cam application.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/street_cam/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/street_cam/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_objects/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">video_objects</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe SSD MobileNet<br />
Processes a video file and overlays boxes and labels around the objects detected and displays results in a GUI as frames are available.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/video_objects/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/video_objects/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
</tbody></table>
<h2 style="background-color: white; border-bottom: 1px solid rgb(234, 236, 239); box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; line-height: 1.25; margin-bottom: 16px; margin-top: 24px; padding-bottom: 0.3em;">
<a aria-hidden="true" class="anchor" href="https://github.com/movidius/ncappzoo/tree/master/apps#misc-applications" id="user-content-misc-applications" style="background-color: initial; box-sizing: border-box; color: #0366d6; float: left; line-height: 1; margin-left: -20px; padding-right: 4px; text-decoration-line: none;"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewbox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z" fill-rule="evenodd"></path></svg></a>Misc Applications</h2>
<div style="background-color: white; box-sizing: border-box; color: #24292e; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 16px;">
Miscellaneous applications use the NCSDK in various ways that don't fit into any of the above categories but can still be interesting.</div>
<table style="background-color: white; border-collapse: collapse; border-spacing: 0px; box-sizing: border-box; color: #24292e; display: block; font-family: -apple-system, system-ui, "Segoe UI", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 16px; margin-bottom: 0px !important; margin-top: 0px; overflow: auto; width: 898px;"><thead style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Misc Application</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Description</th><th style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">+++++Thumbnail+++++</th></tr>
</thead><tbody style="box-sizing: border-box;">
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/benchmarkncs/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">benchmarkncs</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Multiple Network<br />
Outputs FPS numbers for networks in the repository that take images as input. If multiple NCS devices are plugged in will give numbers for one device and for multiple.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/benchmarkncs/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/benchmarkncs/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/hello_ncs_cpp/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">hello_ncs_cpp</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">C++<br />
No Networks<br />
Simple example demonstrating how compile, run, as well as open and close a device in C++ application.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/hello_ncs_cpp/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/hello_ncs_cpp/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/hello_ncs_py/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">hello_ncs_py</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
No Networks<br />
Simple example demonstrating how open and close a device in Python and run the program.</td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/hello_ncs_py/screen_shot.jpg" rel="noopener noreferrer" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;" target="_blank"><img alt="" src="https://github.com/movidius/ncappzoo/raw/master/apps/hello_ncs_py/screen_shot.jpg" style="background-color: initial; border-style: none; box-sizing: initial; max-width: 100%;" /></a></td></tr>
<tr style="background-color: #f6f8fa; border-top: 1px solid rgb(198, 203, 209); box-sizing: border-box;"><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;"><a href="https://github.com/movidius/ncappzoo/blob/master/apps/multistick_cpp/README.md" style="background-color: initial; box-sizing: border-box; color: #0366d6; text-decoration-line: none;">multistick_cpp</a></td><td style="border: 1px solid rgb(223, 226, 229); box-sizing: border-box; padding: 6px 13px;">Python<br />
Caffe SqueezeNet, GoogLeNet<br />
Simple example demonstrating how to use multiple devices and networks in a C++ application.</td></tr>
</tbody></table>
</div>
<br />
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<b><span style="color: orange;">Run Demo</span></b></h3>
<div style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;">
<span style="color: blue;"><b>Image Classifier</b></span></div>
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/HHECMCueHeE" style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" width="560"></iframe><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" />
<br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" />
<b style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;"><span style="color: blue;">Image Classifier with Python GUI </span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/H7C68Yk8AoM" style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" width="560"></iframe><br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" />
<br style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" />
<b style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;"><span style="color: blue;">Video Objects Detection</span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/mFsekNAS7iE" style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;" width="560"></iframe><br />
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<b><br /></b></h3>
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<b><br /></b></h3>
<h3 style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; margin: 0px; position: relative;">
<b>Reference</b></h3>
<div style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif; font-size: 13.2px;">
<a href="https://software.intel.com/en-us/neural-compute-stick/get-started" style="color: #888888; text-decoration-line: none;">https://software.intel.com/en-us/neural-compute-stick/get-started</a><br />
<a href="https://github.com/movidius/ncappzoo/" style="color: #888888; text-decoration-line: none;">https://github.com/movidius/ncappzoo/</a></div>
<br />
<div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">
<div style="margin: 0px; position: relative;">
<b><span style="color: red;"><br class="Apple-interchange-newline" />My Website</span></b></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<a href="http://softpowergroup.net/" style="color: #888888;"><span style="font-family: "arial" , "helvetica" , sans-serif;">http://softpowergroup.net/</span></a></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span><br />
<div>
<span style="font-family: "arial" , "helvetica" , sans-serif;"><br /></span></div>
</div>
</div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-12272166594918970612018-10-12T03:28:00.004-07:002018-10-30T21:03:54.996-07:00Install intel® Movidius™ Neural Compute SDK on Raspberry pi<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNA7-WMjkAoBsCFXp-W720U8rqPK6GFY9gYlTvTHZXCDpir-rFezPgL_szgNBowBp5qDcJba21tT-5Biii0tPWh_WfQs0TRUPWQOK9D-L0BVAaPGubcg3y9FCouhptJr3alRhZKT09Ls9n/s1600/raspberrypi-intel-movidius.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="752" data-original-width="1600" height="297" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNA7-WMjkAoBsCFXp-W720U8rqPK6GFY9gYlTvTHZXCDpir-rFezPgL_szgNBowBp5qDcJba21tT-5Biii0tPWh_WfQs0TRUPWQOK9D-L0BVAaPGubcg3y9FCouhptJr3alRhZKT09Ls9n/s640/raspberrypi-intel-movidius.png" width="640" /></a></div>
<span style="color: magenta; font-family: "helvetica neue"; font-size: 18.0pt;">Install intel®
Movidius™ Neural Compute SDK on Raspberry pi</span><br />
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s1600/NCS-banner-MovStick-500w-300h.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="500" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhor65iKjvGNuT9FzfUsV-EJerOn4AqRTC5cHSPsJOP84LXH3tmIAdzfn46EHLYyQrnggrD1_-IOd4WXFuy7rDCCPuvlUz2StoScVJYkHO8R7AWkhJsNO5Q_1Xs1N0b6m-gLx8bBMObYki5/s200/NCS-banner-MovStick-500w-300h.png" width="200" /></a></div>
<h4>
<span style="background-color: white;"><span style="color: blue;"><a href="https://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html" target="_blank">What is Intel Movidius Neural Compute Stick?</a></span></span></h4>
<div>
<span style="background-color: white;"><a href="https://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html">https://raspberrypi4u.blogspot.com/2018/10/raspberry-pi-movidius-neural-compute-stick.html</a></span></div>
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18.0pt;"><br /></span>
<br />
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18.0pt;"><br /></span>
<br />
<h3>
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18.0pt;">Before Install</span></h3>
<!--[if gte mso 9]><xml>
<o:OfficeDocumentSettings>
<o:RelyOnVML/>
<o:AllowPNG/>
<o:PixelsPerInch>96</o:PixelsPerInch>
</o:OfficeDocumentSettings>
</xml><![endif]-->
<!--[if gte mso 9]><xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves/>
<w:TrackFormatting/>
<w:PunctuationKerning/>
<w:ValidateAgainstSchemas/>
<w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
<w:IgnoreMixedContent>false</w:IgnoreMixedContent>
<w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
<w:DoNotPromoteQF/>
<w:LidThemeOther>EN-US</w:LidThemeOther>
<w:LidThemeAsian>X-NONE</w:LidThemeAsian>
<w:LidThemeComplexScript>TH</w:LidThemeComplexScript>
<w:Compatibility>
<w:BreakWrappedTables/>
<w:SnapToGridInCell/>
<w:ApplyBreakingRules/>
<w:WrapTextWithPunct/>
<w:UseAsianBreakRules/>
<w:DontGrowAutofit/>
<w:SplitPgBreakAndParaMark/>
<w:EnableOpenTypeKerning/>
<w:DontFlipMirrorIndents/>
<w:OverrideTableStyleHps/>
</w:Compatibility>
<m:mathPr>
<m:mathFont m:val="Cambria Math"/>
<m:brkBin m:val="before"/>
<m:brkBinSub m:val="--"/>
<m:smallFrac m:val="off"/>
<m:dispDef/>
<m:lMargin m:val="0"/>
<m:rMargin m:val="0"/>
<m:defJc m:val="centerGroup"/>
<m:wrapIndent m:val="1440"/>
<m:intLim m:val="subSup"/>
<m:naryLim m:val="undOvr"/>
</m:mathPr></w:WordDocument>
</xml><![endif]--><!--[if gte mso 9]><xml>
<w:LatentStyles DefLockedState="false" DefUnhideWhenUsed="false"
DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="382">
<w:LsdException Locked="false" Priority="0" QFormat="true" Name="Normal"/>
<w:LsdException Locked="false" Priority="9" QFormat="true" Name="heading 1"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 9"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 1"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 2"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 3"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 4"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 5"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 6"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 7"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 8"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="header"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footer"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index heading"/>
<w:LsdException Locked="false" Priority="35" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of figures"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope return"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="line number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="page number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of authorities"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="macro"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="toa heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 5"/>
<w:LsdException Locked="false" Priority="10" QFormat="true" Name="Title"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Closing"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Signature"/>
<w:LsdException Locked="false" Priority="1" SemiHidden="true"
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Message Header"/>
<w:LsdException Locked="false" Priority="11" QFormat="true" Name="Subtitle"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Salutation"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Date"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Block Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Hyperlink"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="FollowedHyperlink"/>
<w:LsdException Locked="false" Priority="22" QFormat="true" Name="Strong"/>
<w:LsdException Locked="false" Priority="20" QFormat="true" Name="Emphasis"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Document Map"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Plain Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="E-mail Signature"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Top of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Bottom of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal (Web)"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Acronym"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Cite"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Code"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Definition"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Keyboard"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Preformatted"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Sample"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Typewriter"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Variable"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Table"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation subject"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="No List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Contemporary"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Elegant"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Professional"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Balloon Text"/>
<w:LsdException Locked="false" Priority="39" Name="Table Grid"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Theme"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 9"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Placeholder Text"/>
<w:LsdException Locked="false" Priority="1" QFormat="true" Name="No Spacing"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading"/>
<w:LsdException Locked="false" Priority="61" Name="Light List"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 1"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 1"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 1"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 1"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 1"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Revision"/>
<w:LsdException Locked="false" Priority="34" QFormat="true"
Name="List Paragraph"/>
<w:LsdException Locked="false" Priority="29" QFormat="true" Name="Quote"/>
<w:LsdException Locked="false" Priority="30" QFormat="true"
Name="Intense Quote"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 1"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 1"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 1"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 1"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 1"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 1"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 1"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 2"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 2"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 2"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 2"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 2"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 2"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 2"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 2"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 2"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 2"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 2"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 3"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 3"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 3"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 3"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 3"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 3"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 3"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 3"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 3"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 3"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 3"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 3"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 3"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 4"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 4"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 4"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 4"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 4"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 4"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 4"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 4"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 4"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 4"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 4"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 4"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 4"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 4"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 5"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 5"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 5"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 5"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 5"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 5"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 5"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 5"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 5"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 5"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 5"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 5"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 5"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 5"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 6"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 6"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 6"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 6"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 6"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 6"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 6"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 6"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 6"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 6"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 6"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 6"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 6"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 6"/>
<w:LsdException Locked="false" Priority="19" QFormat="true"
Name="Subtle Emphasis"/>
<w:LsdException Locked="false" Priority="21" QFormat="true"
Name="Intense Emphasis"/>
<w:LsdException Locked="false" Priority="31" QFormat="true"
Name="Subtle Reference"/>
<w:LsdException Locked="false" Priority="32" QFormat="true"
Name="Intense Reference"/>
<w:LsdException Locked="false" Priority="33" QFormat="true" Name="Book Title"/>
<w:LsdException Locked="false" Priority="37" SemiHidden="true"
UnhideWhenUsed="true" Name="Bibliography"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>
<w:LsdException Locked="false" Priority="41" Name="Plain Table 1"/>
<w:LsdException Locked="false" Priority="42" Name="Plain Table 2"/>
<w:LsdException Locked="false" Priority="43" Name="Plain Table 3"/>
<w:LsdException Locked="false" Priority="44" Name="Plain Table 4"/>
<w:LsdException Locked="false" Priority="45" Name="Plain Table 5"/>
<w:LsdException Locked="false" Priority="40" Name="Grid Table Light"/>
<w:LsdException Locked="false" Priority="46" Name="Grid Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="Grid Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="Grid Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="46" Name="List Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="List Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="List Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Mention"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Smart Hyperlink"/>
</w:LatentStyles>
</xml><![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
@font-face
{font-family:"Helvetica Neue";
panose-1:2 0 5 3 0 0 0 2 0 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-452984065 1342208475 16 0 1 0;}
@font-face
{font-family:Menlo;
panose-1:2 11 6 9 3 8 4 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-436198657 -771687941 33554472 0 479 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style>
<!--[if gte mso 10]>
<style>
/* Style Definitions */
table.MsoNormalTable
{mso-style-name:"Table Normal";
mso-tstyle-rowband-size:0;
mso-tstyle-colband-size:0;
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-parent:"";
mso-padding-alt:0in 5.4pt 0in 5.4pt;
mso-para-margin:0in;
mso-para-margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-language:AR-SA;}
</style>
<![endif]-->
<!--StartFragment-->
<br />
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;">You will likely need to increase the swapfile size on the
Raspberry Pi in order to successfully complete NCSDK and/or OpenCV
installation. To increase the swapfile size, edit the value of CONF_SWAPSIZE in
/etc/dphys-swapfile:<o:p></o:p></span></div>
<div style="background: white; border: solid #CCCCCC 1.0pt; mso-border-alt: solid #CCCCCC .75pt; mso-element: para-border-div; padding: 7.0pt 7.0pt 7.0pt 7.0pt;">
<div class="MsoNormal" style="background: white; border: none; margin-bottom: 18.75pt; margin-left: 0in; margin-right: 0in; margin-top: 18.75pt; mso-border-alt: solid #CCCCCC .75pt; mso-padding-alt: 7.0pt 7.0pt 7.0pt 7.0pt; padding: 0in; tab-stops: 45.8pt 91.6pt 137.4pt 183.2pt 229.0pt 274.8pt 320.6pt 366.4pt 412.2pt 458.0pt 503.8pt 549.6pt 595.4pt 641.2pt 687.0pt 732.8pt; word-break: break-all;">
<span style="color: #0086b3; font-family: "menlo"; font-size: 10.0pt;">sudo </span><span style="color: #333333; font-family: "menlo"; font-size: 10.0pt;">nano /etc/dphys-swapfile<o:p></o:p></span></div>
</div>
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;">The default value is 100 (MB). We recommend that you change this
to 1024 (MB) or greater.<o:p></o:p></span></div>
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;">Then restart the swapfile service:<o:p></o:p></span></div>
<div style="background: white; border: solid #CCCCCC 1.0pt; mso-border-alt: solid #CCCCCC .75pt; mso-element: para-border-div; padding: 7.0pt 7.0pt 7.0pt 7.0pt;">
<div class="MsoNormal" style="background: white; border: none; margin-bottom: 18.75pt; margin-left: 0in; margin-right: 0in; margin-top: 18.75pt; mso-border-alt: solid #CCCCCC .75pt; mso-padding-alt: 7.0pt 7.0pt 7.0pt 7.0pt; padding: 0in; tab-stops: 45.8pt 91.6pt 137.4pt 183.2pt 229.0pt 274.8pt 320.6pt 366.4pt 412.2pt 458.0pt 503.8pt 549.6pt 595.4pt 641.2pt 687.0pt 732.8pt; word-break: break-all;">
<span style="color: #0086b3; font-family: "menlo"; font-size: 10.0pt;">sudo</span><span style="color: #333333; font-family: "menlo"; font-size: 10.0pt;"> /etc/init.d/dphys-swapfile restart<o:p></o:p></span></div>
</div>
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;">Proceed with installation as shown above. After you have
installed the NCSDK (and optionally OpenCV), you should change the swapfile
size back to 100 MB.<o:p></o:p></span></div>
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;"><br /></span>
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEil6xAMlQsTzHezpXsmJplOhokajHLGxiLUIkOYCoMYO2KSW8ifaGXd9PAG0jEfYP5Cfwv3xvvV2Bp1F09AgClqBps_i9LCqIYRhQQ6_rQUWnlI26kO90fRX3o04RPxsNn37_3LS_luo2TU/s1600/ncsdk.png" imageanchor="1"><img border="0" height="215" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEil6xAMlQsTzHezpXsmJplOhokajHLGxiLUIkOYCoMYO2KSW8ifaGXd9PAG0jEfYP5Cfwv3xvvV2Bp1F09AgClqBps_i9LCqIYRhQQ6_rQUWnlI26kO90fRX3o04RPxsNn37_3LS_luo2TU/s400/ncsdk.png" width="400" /></a></span></div>
<h3 style="font-family: Times;">
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18pt;">Install</span></h3>
<div style="background: white; margin-bottom: 7.5pt; margin-left: 0in; margin-right: 0in; margin-top: 0in;">
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;">To perform the typical installation of the NCSDK, use the
following commands on your host machine:<o:p></o:p></span><br />
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;"><br /></span>
<span style="color: #333333; font-family: "helvetica neue";"><span style="font-size: 15.3333px;">ncsdk2 (lasted </span></span><span style="color: #24292e; font-family: , , "segoe ui" , "helvetica" , "arial" , sans-serif , "apple color emoji" , "segoe ui emoji" , "segoe ui symbol"; font-size: xx-small;"><span style="color: #24292e; font-size: x-small;">V2.08.01 2018-10-04 ) </span><b><span style="color: red;">Newest Version!!!</span></b></span><br />
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;"></span><br />
<pre class="highlight" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-radius: 4px; border: 1px solid rgb(204, 204, 204); box-sizing: border-box; color: #333333; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: 13px; line-height: 1.42857; margin-bottom: 25px; margin-top: 25px; overflow-wrap: break-word; overflow: auto; padding: 9.5px; white-space: pre-wrap; word-break: break-all;"><code style="background-color: transparent; border-radius: 0px; box-sizing: border-box; color: inherit; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: inherit; padding: 0px;">git clone <span class="nt" style="box-sizing: border-box; color: navy;">-b</span> ncsdk2 http://github.com/Movidius/ncsdk</code></pre>
<pre class="highlight" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-radius: 4px; border: 1px solid rgb(204, 204, 204); box-sizing: border-box; color: #333333; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: 13px; line-height: 1.42857; margin-bottom: 25px; margin-top: 25px; overflow-wrap: break-word; overflow: auto; padding: 9.5px; white-space: pre-wrap; word-break: break-all;"><code style="background-color: transparent; border-radius: 0px; box-sizing: border-box; color: inherit; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: inherit; padding: 0px;">cd ncsdk</code></pre>
<pre class="highlight" style="background-attachment: initial; background-clip: initial; background-image: initial; background-origin: initial; background-position: initial; background-repeat: initial; background-size: initial; border-radius: 4px; border: 1px solid rgb(204, 204, 204); box-sizing: border-box; color: #333333; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: 13px; line-height: 1.42857; margin-bottom: 25px; margin-top: 25px; overflow-wrap: break-word; overflow: auto; padding: 9.5px; white-space: pre-wrap; word-break: break-all;"><code style="background-color: transparent; border-radius: 0px; box-sizing: border-box; color: inherit; font-family: Menlo, Monaco, Consolas, "Courier New", monospace; font-size: inherit; padding: 0px;">make install</code></pre>
<br />
<span style="color: #333333; font-family: "helvetica neue"; font-size: 11.5pt;"><br /></span>
<span style="font-family: "helvetica neue"; font-size: 11.5pt;"><span style="color: #333333;">ncsdk 2 ( 09 2018 ) </span><b><span style="color: red;">Old Version !!!</span></b></span></div>
<div class="MsoNormal" style="background: white; margin-bottom: 7.5pt;">
<!--[if gte mso 9]><xml>
<o:OfficeDocumentSettings>
<o:RelyOnVML/>
<o:AllowPNG/>
<o:PixelsPerInch>96</o:PixelsPerInch>
</o:OfficeDocumentSettings>
</xml><![endif]-->
<!--[if gte mso 9]><xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves/>
<w:TrackFormatting/>
<w:PunctuationKerning/>
<w:ValidateAgainstSchemas/>
<w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
<w:IgnoreMixedContent>false</w:IgnoreMixedContent>
<w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
<w:DoNotPromoteQF/>
<w:LidThemeOther>EN-US</w:LidThemeOther>
<w:LidThemeAsian>X-NONE</w:LidThemeAsian>
<w:LidThemeComplexScript>TH</w:LidThemeComplexScript>
<w:Compatibility>
<w:BreakWrappedTables/>
<w:SnapToGridInCell/>
<w:ApplyBreakingRules/>
<w:WrapTextWithPunct/>
<w:UseAsianBreakRules/>
<w:DontGrowAutofit/>
<w:SplitPgBreakAndParaMark/>
<w:EnableOpenTypeKerning/>
<w:DontFlipMirrorIndents/>
<w:OverrideTableStyleHps/>
</w:Compatibility>
<m:mathPr>
<m:mathFont m:val="Cambria Math"/>
<m:brkBin m:val="before"/>
<m:brkBinSub m:val="--"/>
<m:smallFrac m:val="off"/>
<m:dispDef/>
<m:lMargin m:val="0"/>
<m:rMargin m:val="0"/>
<m:defJc m:val="centerGroup"/>
<m:wrapIndent m:val="1440"/>
<m:intLim m:val="subSup"/>
<m:naryLim m:val="undOvr"/>
</m:mathPr></w:WordDocument>
</xml><![endif]--><!--[if gte mso 9]><xml>
<w:LatentStyles DefLockedState="false" DefUnhideWhenUsed="false"
DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="382">
<w:LsdException Locked="false" Priority="0" QFormat="true" Name="Normal"/>
<w:LsdException Locked="false" Priority="9" QFormat="true" Name="heading 1"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 9"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 1"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 2"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 3"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 4"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 5"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 6"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 7"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 8"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="header"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footer"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index heading"/>
<w:LsdException Locked="false" Priority="35" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of figures"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope return"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="line number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="page number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of authorities"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="macro"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="toa heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 5"/>
<w:LsdException Locked="false" Priority="10" QFormat="true" Name="Title"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Closing"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Signature"/>
<w:LsdException Locked="false" Priority="1" SemiHidden="true"
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Message Header"/>
<w:LsdException Locked="false" Priority="11" QFormat="true" Name="Subtitle"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Salutation"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Date"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Block Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Hyperlink"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="FollowedHyperlink"/>
<w:LsdException Locked="false" Priority="22" QFormat="true" Name="Strong"/>
<w:LsdException Locked="false" Priority="20" QFormat="true" Name="Emphasis"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Document Map"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Plain Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="E-mail Signature"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Top of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Bottom of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal (Web)"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Acronym"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Cite"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Code"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Definition"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Keyboard"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Preformatted"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Sample"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Typewriter"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Variable"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Table"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation subject"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="No List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Contemporary"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Elegant"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Professional"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Balloon Text"/>
<w:LsdException Locked="false" Priority="39" Name="Table Grid"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Theme"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 9"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Placeholder Text"/>
<w:LsdException Locked="false" Priority="1" QFormat="true" Name="No Spacing"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading"/>
<w:LsdException Locked="false" Priority="61" Name="Light List"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 1"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 1"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 1"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 1"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 1"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Revision"/>
<w:LsdException Locked="false" Priority="34" QFormat="true"
Name="List Paragraph"/>
<w:LsdException Locked="false" Priority="29" QFormat="true" Name="Quote"/>
<w:LsdException Locked="false" Priority="30" QFormat="true"
Name="Intense Quote"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 1"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 1"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 1"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 1"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 1"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 1"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 1"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 2"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 2"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 2"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 2"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 2"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 2"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 2"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 2"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 2"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 2"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 2"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 3"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 3"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 3"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 3"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 3"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 3"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 3"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 3"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 3"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 3"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 3"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 3"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 3"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 4"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 4"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 4"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 4"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 4"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 4"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 4"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 4"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 4"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 4"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 4"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 4"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 4"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 4"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 5"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 5"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 5"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 5"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 5"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 5"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 5"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 5"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 5"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 5"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 5"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 5"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 5"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 5"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 6"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 6"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 6"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 6"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 6"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 6"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 6"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 6"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 6"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 6"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 6"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 6"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 6"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 6"/>
<w:LsdException Locked="false" Priority="19" QFormat="true"
Name="Subtle Emphasis"/>
<w:LsdException Locked="false" Priority="21" QFormat="true"
Name="Intense Emphasis"/>
<w:LsdException Locked="false" Priority="31" QFormat="true"
Name="Subtle Reference"/>
<w:LsdException Locked="false" Priority="32" QFormat="true"
Name="Intense Reference"/>
<w:LsdException Locked="false" Priority="33" QFormat="true" Name="Book Title"/>
<w:LsdException Locked="false" Priority="37" SemiHidden="true"
UnhideWhenUsed="true" Name="Bibliography"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>
<w:LsdException Locked="false" Priority="41" Name="Plain Table 1"/>
<w:LsdException Locked="false" Priority="42" Name="Plain Table 2"/>
<w:LsdException Locked="false" Priority="43" Name="Plain Table 3"/>
<w:LsdException Locked="false" Priority="44" Name="Plain Table 4"/>
<w:LsdException Locked="false" Priority="45" Name="Plain Table 5"/>
<w:LsdException Locked="false" Priority="40" Name="Grid Table Light"/>
<w:LsdException Locked="false" Priority="46" Name="Grid Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="Grid Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="Grid Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="46" Name="List Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="List Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="List Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Mention"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Smart Hyperlink"/>
</w:LatentStyles>
</xml><![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Courier New";
panose-1:2 7 3 9 2 2 5 2 4 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536859905 -1073711037 9 0 511 0;}
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
@font-face
{font-family:"Helvetica Neue";
panose-1:2 0 5 3 0 0 0 2 0 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-452984065 1342208475 16 0 1 0;}
@font-face
{font-family:Menlo;
panose-1:2 11 6 9 3 8 4 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-436198657 -771687941 33554472 0 479 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
h2
{mso-style-noshow:yes;
mso-style-priority:9;
mso-style-qformat:yes;
mso-style-link:"Heading 2 Char";
mso-style-next:Normal;
margin-top:2.0pt;
margin-right:0in;
margin-bottom:0in;
margin-left:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan lines-together;
page-break-after:avoid;
mso-outline-level:2;
font-size:13.0pt;
font-family:"Calibri Light";
mso-ascii-font-family:"Calibri Light";
mso-ascii-theme-font:major-latin;
mso-fareast-font-family:"Times New Roman";
mso-fareast-theme-font:major-fareast;
mso-hansi-font-family:"Calibri Light";
mso-hansi-theme-font:major-latin;
mso-bidi-font-family:"Angsana New";
mso-bidi-theme-font:major-bidi;
color:#2E74B5;
mso-themecolor:accent1;
mso-themeshade:191;
mso-bidi-language:AR-SA;
font-weight:normal;}
p
{mso-style-noshow:yes;
mso-style-priority:99;
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Times New Roman";}
code
{mso-style-noshow:yes;
mso-style-priority:99;
font-family:"Courier New";
mso-ascii-font-family:"Courier New";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:"Courier New";
mso-bidi-font-family:Courier;}
pre
{mso-style-noshow:yes;
mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
tab-stops:45.8pt 91.6pt 137.4pt 183.2pt 229.0pt 274.8pt 320.6pt 366.4pt 412.2pt 458.0pt 503.8pt 549.6pt 595.4pt 641.2pt 687.0pt 732.8pt;
font-size:10.0pt;
font-family:"Courier New";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:Courier;}
span.Heading2Char
{mso-style-name:"Heading 2 Char";
mso-style-noshow:yes;
mso-style-priority:9;
mso-style-unhide:no;
mso-style-locked:yes;
mso-style-link:"Heading 2";
mso-ansi-font-size:13.0pt;
mso-bidi-font-size:13.0pt;
font-family:"Calibri Light";
mso-ascii-font-family:"Calibri Light";
mso-ascii-theme-font:major-latin;
mso-fareast-font-family:"Times New Roman";
mso-fareast-theme-font:major-fareast;
mso-hansi-font-family:"Calibri Light";
mso-hansi-theme-font:major-latin;
mso-bidi-font-family:"Angsana New";
mso-bidi-theme-font:major-bidi;
color:#2E74B5;
mso-themecolor:accent1;
mso-themeshade:191;}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-unhide:no;
mso-style-locked:yes;
mso-style-link:"HTML Preformatted";
mso-ansi-font-size:10.0pt;
mso-bidi-font-size:10.0pt;
font-family:"Courier New";
mso-ascii-font-family:"Courier New";
mso-hansi-font-family:"Courier New";
mso-bidi-font-family:Courier;
mso-bidi-language:TH;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style>
<!--[if gte mso 10]>
<style>
/* Style Definitions */
table.MsoNormalTable
{mso-style-name:"Table Normal";
mso-tstyle-rowband-size:0;
mso-tstyle-colband-size:0;
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-parent:"";
mso-padding-alt:0in 5.4pt 0in 5.4pt;
mso-para-margin:0in;
mso-para-margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-language:AR-SA;}
</style>
<![endif]-->
<!--StartFragment-->
<!--EndFragment--></div>
<div style="background: white; border: solid #CCCCCC 1.0pt; mso-border-alt: solid #CCCCCC .75pt; mso-element: para-border-div; padding: 7.0pt 7.0pt 7.0pt 7.0pt;">
<pre style="background: white; border: none; margin-bottom: 18.75pt; margin-left: 0in; margin-right: 0in; margin-top: 18.75pt; mso-border-alt: solid #CCCCCC .75pt; mso-padding-alt: 7.0pt 7.0pt 7.0pt 7.0pt; padding: 0in; word-break: break-all;"><code><span style="color: #333333; font-family: "menlo";">wget https://ncs-forum-uploads.s3.amazonaws.com/ncsdk/ncsdk-02_05_00_02-full/ncsdk-2.05.00.02.tar.gz</span></code><span style="color: #333333; font-family: "menlo";">
<code><span style="font-family: "menlo";">tar xvf ncsdk-2.05.00.02.tar.gz</span></code>
<code><span style="font-family: "menlo";">cd ncsdk-2.05.00.02</span></code>
<code><span style="font-family: "menlo";">make install</span></code>
<code><span style="font-family: "menlo";">make examples</span></code><o:p></o:p></span></pre>
</div>
<br />
<br />
<div style="font-family: times;">
<b><span style="color: blue;">Install Done</span></b></div>
<div style="font-family: times;">
<b><span style="color: blue;"><br /></span></b></div>
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhUk08sb2xnZhxc7sL3zqfEMdRc3ZeOYaaNjc3egJigdBDs_fG9FIAZU4PATERANdrgakeMhA5YLE1O9ZfJSX_bpmmtn6ujljL3oPm3xzk9K7a4rBVsyRzzYLBOIJUUDseE5vHnTqIkrgxd/s1600/ncsdk2+edit+rpi+ok.png" imageanchor="1" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="274" data-original-width="937" height="187" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhUk08sb2xnZhxc7sL3zqfEMdRc3ZeOYaaNjc3egJigdBDs_fG9FIAZU4PATERANdrgakeMhA5YLE1O9ZfJSX_bpmmtn6ujljL3oPm3xzk9K7a4rBVsyRzzYLBOIJUUDseE5vHnTqIkrgxd/s640/ncsdk2+edit+rpi+ok.png" width="640" /></a></div>
<div>
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18pt;"><br /></span></div>
<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<br />
<div class="MsoNormal">
<br /></div>
<h3 style="font-family: Times;">
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18pt;">Set Python path</span> </h3>
<div class="MsoNormal">
<span style="color: #9fa01c; font-family: "menlo"; mso-bidi-font-family: Menlo;">export
PYTHONPATH="${PYTHONPATH}:/opt/movidius/caffe/python"</span><span style="font-size: 10.5pt;"><o:p></o:p></span></div>
<div class="MsoNormal">
<br /></div>
<div class="MsoNormal">
<span style="font-family: "menlo";">source ~/.bashrc<o:p></o:p></span></div>
<div class="MsoNormal">
<br /></div>
<div class="MsoNormal">
<span style="font-family: "menlo";">echo $PYTHONPATH<o:p></o:p></span></div>
<div class="MsoNormal">
<span style="color: #9fa01c; font-family: "menlo"; mso-bidi-font-family: Menlo;">:/opt/movidius/caffe/python<o:p></o:p></span></div>
<!--EndFragment--><br />
<div class="MsoNormal">
<br /></div>
<div class="MsoNormal">
<span style="mso-no-proof: yes;"><v:shapetype coordsize="21600,21600" filled="f" id="_x0000_t75" o:preferrelative="t" o:spt="75" path="m@4@5l@4@11@9@11@9@5xe" stroked="f">
<v:stroke joinstyle="miter">
<v:formulas>
<v:f eqn="if lineDrawn pixelLineWidth 0">
<v:f eqn="sum @0 1 0">
<v:f eqn="sum 0 0 @1">
<v:f eqn="prod @2 1 2">
<v:f eqn="prod @3 21600 pixelWidth">
<v:f eqn="prod @3 21600 pixelHeight">
<v:f eqn="sum @0 0 1">
<v:f eqn="prod @6 1 2">
<v:f eqn="prod @7 21600 pixelWidth">
<v:f eqn="sum @8 21600 0">
<v:f eqn="prod @7 21600 pixelHeight">
<v:f eqn="sum @10 21600 0">
</v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:f></v:formulas>
<v:path gradientshapeok="t" o:connecttype="rect" o:extrusionok="f">
<o:lock aspectratio="t" v:ext="edit">
</o:lock></v:path></v:stroke></v:shapetype><v:shape alt="../../Desktop/intel%20NCS/ncsdk2%20rpi%20ok.pn" id="Picture_x0020_2" o:spid="_x0000_i1025" style="height: 137pt; mso-wrap-style: square; visibility: visible; width: 469pt;" type="#_x0000_t75">
<v:imagedata o:title="../../Desktop/intel%20NCS/ncsdk2%20rpi%20ok.pn" src="file://localhost/Users/mac/Library/Group%20Containers/UBF8T346G9.Office/msoclip1/01/clip_image001.png">
</v:imagedata></v:shape></span><o:p></o:p></div>
<div class="MsoNormal">
<br /></div>
<div class="MsoNormal">
<o:p></o:p></div>
<h3 style="font-family: Times;">
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18pt;">Example Code</span> </h3>
<br />
<div style="background: white; border: solid #CCCCCC 1.0pt; mso-border-alt: solid #CCCCCC .75pt; mso-element: para-border-div; padding: 7.0pt 7.0pt 7.0pt 7.0pt;">
<pre style="background: white; border: none; margin-bottom: 18.75pt; margin-left: 0in; margin-right: 0in; margin-top: 18.75pt; mso-border-alt: solid #CCCCCC .75pt; mso-padding-alt: 7.0pt 7.0pt 7.0pt 7.0pt; padding: 0in; word-break: break-all;"><code><span style="color: #333333; font-family: "menlo";">make examples</span></code><span style="color: #333333; font-family: "menlo";"><o:p></o:p></span></pre>
</div>
<div class="MsoNormal">
<o:p>
<!--[if gte mso 9]><xml>
<o:OfficeDocumentSettings>
<o:RelyOnVML/>
<o:AllowPNG/>
<o:PixelsPerInch>96</o:PixelsPerInch>
</o:OfficeDocumentSettings>
</xml><![endif]-->
<!--[if gte mso 9]><xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves/>
<w:TrackFormatting/>
<w:PunctuationKerning/>
<w:ValidateAgainstSchemas/>
<w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
<w:IgnoreMixedContent>false</w:IgnoreMixedContent>
<w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
<w:DoNotPromoteQF/>
<w:LidThemeOther>EN-US</w:LidThemeOther>
<w:LidThemeAsian>X-NONE</w:LidThemeAsian>
<w:LidThemeComplexScript>TH</w:LidThemeComplexScript>
<w:Compatibility>
<w:BreakWrappedTables/>
<w:SnapToGridInCell/>
<w:ApplyBreakingRules/>
<w:WrapTextWithPunct/>
<w:UseAsianBreakRules/>
<w:DontGrowAutofit/>
<w:SplitPgBreakAndParaMark/>
<w:EnableOpenTypeKerning/>
<w:DontFlipMirrorIndents/>
<w:OverrideTableStyleHps/>
</w:Compatibility>
<m:mathPr>
<m:mathFont m:val="Cambria Math"/>
<m:brkBin m:val="before"/>
<m:brkBinSub m:val="--"/>
<m:smallFrac m:val="off"/>
<m:dispDef/>
<m:lMargin m:val="0"/>
<m:rMargin m:val="0"/>
<m:defJc m:val="centerGroup"/>
<m:wrapIndent m:val="1440"/>
<m:intLim m:val="subSup"/>
<m:naryLim m:val="undOvr"/>
</m:mathPr></w:WordDocument>
</xml><![endif]--><!--[if gte mso 9]><xml>
<w:LatentStyles DefLockedState="false" DefUnhideWhenUsed="false"
DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="382">
<w:LsdException Locked="false" Priority="0" QFormat="true" Name="Normal"/>
<w:LsdException Locked="false" Priority="9" QFormat="true" Name="heading 1"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
<w:LsdException Locked="false" Priority="9" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index 9"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 1"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 2"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 3"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 4"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 5"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 6"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 7"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 8"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" Name="toc 9"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="header"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footer"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="index heading"/>
<w:LsdException Locked="false" Priority="35" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of figures"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="envelope return"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="footnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="line number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="page number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote reference"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="endnote text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="table of authorities"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="macro"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="toa heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Bullet 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Number 5"/>
<w:LsdException Locked="false" Priority="10" QFormat="true" Name="Title"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Closing"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Signature"/>
<w:LsdException Locked="false" Priority="1" SemiHidden="true"
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="List Continue 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Message Header"/>
<w:LsdException Locked="false" Priority="11" QFormat="true" Name="Subtitle"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Salutation"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Date"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text First Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Heading"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Body Text Indent 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Block Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Hyperlink"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="FollowedHyperlink"/>
<w:LsdException Locked="false" Priority="22" QFormat="true" Name="Strong"/>
<w:LsdException Locked="false" Priority="20" QFormat="true" Name="Emphasis"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Document Map"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Plain Text"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="E-mail Signature"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Top of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Bottom of Form"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal (Web)"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Acronym"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Address"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Cite"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Code"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Definition"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Keyboard"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Preformatted"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Sample"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Typewriter"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="HTML Variable"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Normal Table"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="annotation subject"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="No List"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Outline List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Simple 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Classic 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Colorful 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Columns 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Grid 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table List 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table 3D effects 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Contemporary"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Elegant"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Professional"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Subtle 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Web 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Balloon Text"/>
<w:LsdException Locked="false" Priority="39" Name="Table Grid"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Table Theme"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 1"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 2"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 3"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 4"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 5"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 7"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 8"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Note Level 9"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Placeholder Text"/>
<w:LsdException Locked="false" Priority="1" QFormat="true" Name="No Spacing"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading"/>
<w:LsdException Locked="false" Priority="61" Name="Light List"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 1"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 1"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 1"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 1"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 1"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 1"/>
<w:LsdException Locked="false" SemiHidden="true" Name="Revision"/>
<w:LsdException Locked="false" Priority="34" QFormat="true"
Name="List Paragraph"/>
<w:LsdException Locked="false" Priority="29" QFormat="true" Name="Quote"/>
<w:LsdException Locked="false" Priority="30" QFormat="true"
Name="Intense Quote"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 1"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 1"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 1"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 1"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 1"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 1"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 1"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 1"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 2"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 2"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 2"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 2"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 2"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 2"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 2"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 2"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 2"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 2"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 2"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 2"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 2"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 2"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 3"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 3"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 3"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 3"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 3"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 3"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 3"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 3"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 3"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 3"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 3"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 3"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 3"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 3"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 4"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 4"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 4"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 4"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 4"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 4"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 4"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 4"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 4"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 4"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 4"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 4"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 4"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 4"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 5"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 5"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 5"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 5"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 5"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 5"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 5"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 5"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 5"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 5"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 5"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 5"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 5"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 5"/>
<w:LsdException Locked="false" Priority="60" Name="Light Shading Accent 6"/>
<w:LsdException Locked="false" Priority="61" Name="Light List Accent 6"/>
<w:LsdException Locked="false" Priority="62" Name="Light Grid Accent 6"/>
<w:LsdException Locked="false" Priority="63" Name="Medium Shading 1 Accent 6"/>
<w:LsdException Locked="false" Priority="64" Name="Medium Shading 2 Accent 6"/>
<w:LsdException Locked="false" Priority="65" Name="Medium List 1 Accent 6"/>
<w:LsdException Locked="false" Priority="66" Name="Medium List 2 Accent 6"/>
<w:LsdException Locked="false" Priority="67" Name="Medium Grid 1 Accent 6"/>
<w:LsdException Locked="false" Priority="68" Name="Medium Grid 2 Accent 6"/>
<w:LsdException Locked="false" Priority="69" Name="Medium Grid 3 Accent 6"/>
<w:LsdException Locked="false" Priority="70" Name="Dark List Accent 6"/>
<w:LsdException Locked="false" Priority="71" Name="Colorful Shading Accent 6"/>
<w:LsdException Locked="false" Priority="72" Name="Colorful List Accent 6"/>
<w:LsdException Locked="false" Priority="73" Name="Colorful Grid Accent 6"/>
<w:LsdException Locked="false" Priority="19" QFormat="true"
Name="Subtle Emphasis"/>
<w:LsdException Locked="false" Priority="21" QFormat="true"
Name="Intense Emphasis"/>
<w:LsdException Locked="false" Priority="31" QFormat="true"
Name="Subtle Reference"/>
<w:LsdException Locked="false" Priority="32" QFormat="true"
Name="Intense Reference"/>
<w:LsdException Locked="false" Priority="33" QFormat="true" Name="Book Title"/>
<w:LsdException Locked="false" Priority="37" SemiHidden="true"
UnhideWhenUsed="true" Name="Bibliography"/>
<w:LsdException Locked="false" Priority="39" SemiHidden="true"
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>
<w:LsdException Locked="false" Priority="41" Name="Plain Table 1"/>
<w:LsdException Locked="false" Priority="42" Name="Plain Table 2"/>
<w:LsdException Locked="false" Priority="43" Name="Plain Table 3"/>
<w:LsdException Locked="false" Priority="44" Name="Plain Table 4"/>
<w:LsdException Locked="false" Priority="45" Name="Plain Table 5"/>
<w:LsdException Locked="false" Priority="40" Name="Grid Table Light"/>
<w:LsdException Locked="false" Priority="46" Name="Grid Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="Grid Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="Grid Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="Grid Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="Grid Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="Grid Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="Grid Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="Grid Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="Grid Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="Grid Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="46" Name="List Table 1 Light"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark"/>
<w:LsdException Locked="false" Priority="51" Name="List Table 6 Colorful"/>
<w:LsdException Locked="false" Priority="52" Name="List Table 7 Colorful"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 1"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 1"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 1"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 1"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 1"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 1"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 2"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 2"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 2"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 2"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 2"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 2"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 3"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 3"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 3"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 3"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 3"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 3"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 4"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 4"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 4"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 4"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 4"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 4"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 5"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 5"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 5"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 5"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 5"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 5"/>
<w:LsdException Locked="false" Priority="46"
Name="List Table 1 Light Accent 6"/>
<w:LsdException Locked="false" Priority="47" Name="List Table 2 Accent 6"/>
<w:LsdException Locked="false" Priority="48" Name="List Table 3 Accent 6"/>
<w:LsdException Locked="false" Priority="49" Name="List Table 4 Accent 6"/>
<w:LsdException Locked="false" Priority="50" Name="List Table 5 Dark Accent 6"/>
<w:LsdException Locked="false" Priority="51"
Name="List Table 6 Colorful Accent 6"/>
<w:LsdException Locked="false" Priority="52"
Name="List Table 7 Colorful Accent 6"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Mention"/>
<w:LsdException Locked="false" SemiHidden="true" UnhideWhenUsed="true"
Name="Smart Hyperlink"/>
</w:LatentStyles>
</xml><![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Courier New";
panose-1:2 7 3 9 2 2 5 2 4 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536859905 -1073711037 9 0 511 0;}
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
@font-face
{font-family:Menlo;
panose-1:2 11 6 9 3 8 4 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-436198657 -771687941 33554472 0 479 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
code
{mso-style-noshow:yes;
mso-style-priority:99;
font-family:"Courier New";
mso-ascii-font-family:"Courier New";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:"Courier New";
mso-bidi-font-family:Courier;}
pre
{mso-style-noshow:yes;
mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:10.0pt;
font-family:"Courier New";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:Courier;}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-unhide:no;
mso-style-locked:yes;
mso-style-link:"HTML Preformatted";
mso-ansi-font-size:10.0pt;
mso-bidi-font-size:10.0pt;
font-family:"Courier New";
mso-ascii-font-family:"Courier New";
mso-hansi-font-family:"Courier New";
mso-bidi-font-family:Courier;
mso-bidi-language:TH;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style>
<!--[if gte mso 10]>
<style>
/* Style Definitions */
table.MsoNormalTable
{mso-style-name:"Table Normal";
mso-tstyle-rowband-size:0;
mso-tstyle-colband-size:0;
mso-style-noshow:yes;
mso-style-priority:99;
mso-style-parent:"";
mso-padding-alt:0in 5.4pt 0in 5.4pt;
mso-para-margin:0in;
mso-para-margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-language:AR-SA;}
</style>
<![endif]-->
<!--StartFragment-->
<!--EndFragment--></o:p></div>
<div class="MsoNormal">
<span style="font-size: 10.5pt;"><b><span style="color: #e06666;">It take 2-3 Hours</span></b></span><br />
<span style="font-size: 10.5pt;"><b><span style="color: #e06666;"><br /></span></b></span></div>
<b><span style="color: blue;">make examples OK ( no any errors )</span></b><br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgqd7MlH6LFX2oh7jNElu5mRuQDcSauieb00-2C8J8pKWlQpuPQEWmrN7R4odrvV_TfLUnuSG3OA42qFQQLd6utmxfrmIgFUKMi66dQhwR9KHzCTMcsrjq_xFfioYFAQo4QhNKxh6uUDRpZ/s1600/ncsdk2-example-ok.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: left;"><img border="0" data-original-height="668" data-original-width="963" height="443" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgqd7MlH6LFX2oh7jNElu5mRuQDcSauieb00-2C8J8pKWlQpuPQEWmrN7R4odrvV_TfLUnuSG3OA42qFQQLd6utmxfrmIgFUKMi66dQhwR9KHzCTMcsrjq_xFfioYFAQo4QhNKxh6uUDRpZ/s640/ncsdk2-example-ok.png" width="640" /></a></div>
<br />
<h3 style="font-family: Times;">
<span style="color: #00b0f0; font-family: "helvetica neue"; font-size: 18pt;">Test Python Example Code</span> </h3>
<div>
Run Python code <b><span style="color: blue;">hello_ncs.py</span></b></div>
<div>
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIB3IxUKSwU_b6D4ha9FvMI2rQnzde-laF4-h9y27ENnnGsKNcf5OC50u2ZL5fn3pX-6nzTtvwwwePUxpDFxLsCUHkX2D02-05TUhDh9z9zTeODjEiFFNs-7nn8zsVhUpf8jydoYEPMZS-/s1600/ncs-hello-ncs.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="652" data-original-width="825" height="504" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhIB3IxUKSwU_b6D4ha9FvMI2rQnzde-laF4-h9y27ENnnGsKNcf5OC50u2ZL5fn3pX-6nzTtvwwwePUxpDFxLsCUHkX2D02-05TUhDh9z9zTeODjEiFFNs-7nn8zsVhUpf8jydoYEPMZS-/s640/ncs-hello-ncs.png" width="640" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
<h3>
<b><span style="color: orange;">Run Demo</span></b></h3>
<div>
<span style="color: blue;"><b>Image Classification</b></span></div>
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/HHECMCueHeE" width="560"></iframe><br />
<br />
<b><span style="color: blue;">Image Classifier with Python GUI </span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/H7C68Yk8AoM" width="560"></iframe><br />
<br />
<b><span style="color: blue;">Video Objects Detection</span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/mFsekNAS7iE" width="560"></iframe><br />
<h3>
<b>Reference</b></h3>
<div>
<a href="https://software.intel.com/en-us/neural-compute-stick/get-started">https://software.intel.com/en-us/neural-compute-stick/get-started</a><br />
<a href="https://github.com/movidius/ncappzoo/">https://github.com/movidius/ncappzoo/</a><br />
<br />
<br />
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif;">
<div style="margin: 0px; position: relative;">
<b><span style="color: red;">My Website</span></b></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<a href="http://softpowergroup.net/" style="color: #888888;"><span style="font-family: "arial" , "helvetica" , sans-serif;">http://softpowergroup.net/</span></a></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
</div>
<br />
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style><style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
@font-face
{font-family:Menlo;
panose-1:2 11 6 9 3 8 4 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-436198657 -771687941 33554472 0 479 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style><style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cordia New";
panose-1:2 11 3 4 2 2 2 2 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-2130706429 0 0 0 65537 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1107305727 0 0 415 0;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;
mso-font-charset:0;
mso-generic-font-family:auto;
mso-font-pitch:variable;
mso-font-signature:-536870145 1073786111 1 0 415 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{mso-style-unhide:no;
mso-style-qformat:yes;
mso-style-parent:"";
margin:0in;
margin-bottom:.0001pt;
mso-pagination:widow-orphan;
font-size:12.0pt;
font-family:"Times New Roman";
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;}
.MsoChpDefault
{mso-style-type:export-only;
mso-default-props:yes;
mso-bidi-font-size:12.0pt;
font-family:Calibri;
mso-ascii-font-family:Calibri;
mso-ascii-theme-font:minor-latin;
mso-fareast-font-family:Calibri;
mso-fareast-theme-font:minor-latin;
mso-hansi-font-family:Calibri;
mso-hansi-theme-font:minor-latin;
mso-bidi-font-family:"Cordia New";
mso-bidi-theme-font:minor-bidi;
mso-bidi-language:AR-SA;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;
mso-header-margin:.5in;
mso-footer-margin:.5in;
mso-paper-source:0;}
div.WordSection1
{page:WordSection1;}
-->
</style>Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0tag:blogger.com,1999:blog-7853792980726640018.post-67813585854667890752018-10-09T04:36:00.004-07:002018-10-12T22:19:59.291-07:00Raspberry pi Machine Learning with Intel Movidius Neural Compute Stick<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/Gu50DoEWmQg" width="560"></iframe><br />
<h2>
<span style="color: magenta; font-family: "times" , "times new roman" , serif; font-size: large;">Raspberry pi Machine Learning <span style="font-weight: normal;">with</span> </span><span style="color: magenta; font-family: "times" , "times new roman" , serif; font-size: large;">Intel Movidius Neural Compute Stick</span><span style="font-family: "times" , "times new roman" , serif; font-size: large;"> </span><span style="font-family: "times" , "times new roman" , serif; font-size: small; font-weight: normal;">( Myriad2 VPU ) </span></h2>
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhwp-QvsIz2utfcDzYUDvNru44TqEblYjpXBIBog-5his0C7Z3qj0GL8KzqPjb6YH_aMyp7PvXu5Gy5dqC5LZ1VWTmKbknUIVvA1TdqlutzZo1UoofPkGjQGotDFN4zP2-WMkjgDnnuwYOW/s1600/ml_course.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="550" data-original-width="624" height="176" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhwp-QvsIz2utfcDzYUDvNru44TqEblYjpXBIBog-5his0C7Z3qj0GL8KzqPjb6YH_aMyp7PvXu5Gy5dqC5LZ1VWTmKbknUIVvA1TdqlutzZo1UoofPkGjQGotDFN4zP2-WMkjgDnnuwYOW/s200/ml_course.png" width="200" /></a></div>
<h3>
<span style="color: blue;">What is Machine Learning?</span></h3>
<style type="text/css">
p.p1 {margin: 0.0px 0.0px 20.0px 0.0px; line-height: 21.0px; font: 14.0px Arial; color: #373a3c; background-color: #fafafa}
span.s1 {font-kerning: none}
</style>
<br />
<div class="p1">
<span class="s1" style="background-color: white;">Arthur Samuel described it as: "the field of study that gives computers the ability to learn without being explicitly programmed."</span></div>
<span style="background-color: white;"><br /></span>
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi1cIYk7daOaRqqXVsl5M7t2vtVnkS2TAAwX2oL-9tzu7kMP-QXQAQjQ_4Upw5yj5raqw6z63HMwFRisO7ylFIEOaylYrEaDmUGtQD1zsSBDy0S1UOjG1IhDvxybl4FcbyiuF7I41w9x2eP/s1600/NCS-banner-MovStick-500w-300h.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="500" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi1cIYk7daOaRqqXVsl5M7t2vtVnkS2TAAwX2oL-9tzu7kMP-QXQAQjQ_4Upw5yj5raqw6z63HMwFRisO7ylFIEOaylYrEaDmUGtQD1zsSBDy0S1UOjG1IhDvxybl4FcbyiuF7I41w9x2eP/s200/NCS-banner-MovStick-500w-300h.png" width="200" /></a></div>
<h3>
<span style="background-color: white;"><span style="color: blue;">What is Intel Movidius Neural Compute Stick?</span></span></h3>
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">The Intel® Movidius™ Neural Compute Stick (NCS) is a tiny fanless deep learning device that you can use to learn AI programming at the edge. NCS is powered by the same low power high performance Intel Movidius Vision Processing Unit (VPU) that can be found in millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, and more.</span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"><br /></span></span>
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"><b>Technical Specifications</b></span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Processor Intel® Movidius™ 2 VPU ( Vision Processing Unit )</span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Supported Frameworks TensorFlow™, Caffe</span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Connectivity USB 3.0 Type-A</span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Dimensions USB stick (72.5mm X 27mm X 14mm)</span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Operating Temp0° - 40° C</span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"><br /></span></span>
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;"><b>Minimum system requirements</b></span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">x86_64 computer running Ubuntu* 16.04 or </span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">Raspberry Pi 3 Model B running Stretch desktop or </span></span><span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">Ubuntu* 16.04 VirtualBox instance, </span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">USB 2.0 Type-A port (Recommend USB 3.0), </span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">1GB RAM, </span></span><span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif; font-size: 15px;">4GB free storage space</span><br />
<br />
<span style="font-size: 15px;"><span style="background-color: white; color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"></span></span><br />
<span style="color: #555555; font-family: "helvetica neue" , "helvetica" , "arial" , sans-serif;"><span style="font-size: 15px;">The Intel® Movidius™ Neural Compute Stick (Intel® Movidius™ NCS) is an embedded machine intelligence platform from Movidius, an Intel company. Through software and hardware tools, the Intel Movidius NCS brings machine intelligence and AI out of the data centers and into end-user devices. The Intel Movidius NCS is designed to help democratize the machine intelligence space, and accelerate an age of ubiquitous intelligence devices and systems.</span></span><br />
<br />
<br />
<div class="separator" style="clear: both; text-align: left;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiqYZq7ncPQaJJSJewnFYhKvZlW4rKOUqKwM_shU6XomLQk90JnsqC2TawdZSs3BTtQqDNzt76ONyXBNV9GZaK8uDAhNgPOIhX4cd4b5arpEk6_HBhJZHeZf5wWW-apdZ_3-LXsjUKHhUiQ/s1600/rpi3b%252B.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="319" data-original-width="512" height="124" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiqYZq7ncPQaJJSJewnFYhKvZlW4rKOUqKwM_shU6XomLQk90JnsqC2TawdZSs3BTtQqDNzt76ONyXBNV9GZaK8uDAhNgPOIhX4cd4b5arpEk6_HBhJZHeZf5wWW-apdZ_3-LXsjUKHhUiQ/s200/rpi3b%252B.jpeg" width="200" /></a> <a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWpRIxc8lOrP3SatObAzZVf1yqo34okAR0eDCdY1BQ1Y5yNsy444NO4SHRPYz4Vdh94cAnRy4r-rBCuvV-wVutGkiwn1F3Dq17HYNtE39C6Zfv0EBXj0FivNZoERorILlZGnLlr0NCb-N0/s1600/Raspberry-Pi-Logo.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em; text-align: center;"><img border="0" data-original-height="350" data-original-width="620" height="112" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWpRIxc8lOrP3SatObAzZVf1yqo34okAR0eDCdY1BQ1Y5yNsy444NO4SHRPYz4Vdh94cAnRy4r-rBCuvV-wVutGkiwn1F3Dq17HYNtE39C6Zfv0EBXj0FivNZoERorILlZGnLlr0NCb-N0/s200/Raspberry-Pi-Logo.png" width="200" /></a></div>
<br />
<h3 style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; margin: 0px; position: relative;">
<span style="color: blue;">Hardware</span></h3>
<ul style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; line-height: 1.4; margin: 0.5em 0px; padding: 0px 2.5em;">
<li style="margin: 0px 0px 0.25em; padding: 0px;">Raspberry Pi 3B Board with SD card and accessories.</li>
<li style="margin: 0px 0px 0.25em; padding: 0px;">Intel Movidius Neural Compute Stick</li>
<li style="margin: 0px 0px 0.25em; padding: 0px;">USB Camera </li>
</ul>
<h3 style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; margin: 0px; position: relative;">
<span style="color: blue;">Software and Library</span></h3>
<ul style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; line-height: 1.4; margin: 0.5em 0px; padding: 0px 2.5em;">
<li style="margin: 0px 0px 0.25em; padding: 0px;">Raspbien Stretch OS</li>
<li style="margin: 0px 0px 0.25em; padding: 0px;">OpenCV 3.3.0</li>
<li style="margin: 0px 0px 0.25em; padding: 0px;">Python 3.x</li>
<li style="margin: 0px 0px 0.25em; padding: 0px;">Intel® Movidius™ NCSDK</li>
</ul>
<br />
<h3>
<b><span style="color: orange;">Run Demo</span></b></h3>
<div>
<span style="color: blue;"><b>Image Classification</b></span></div>
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/HHECMCueHeE" width="560"></iframe>
<br />
<br />
<b><span style="color: blue;">Image Classifier with Python GUI </span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/H7C68Yk8AoM" width="560"></iframe>
<br />
<br />
<b><span style="color: blue;">Video Objects Detection</span></b><br />
<iframe allow="autoplay; encrypted-media" allowfullscreen="" frameborder="0" height="315" src="https://www.youtube.com/embed/mFsekNAS7iE" width="560"></iframe>
<br />
<h3>
<b>Reference</b></h3>
<a href="https://software.intel.com/en-us/neural-compute-stick/get-started">https://software.intel.com/en-us/neural-compute-stick/get-started</a><br />
<a href="https://github.com/movidius/ncappzoo/">https://github.com/movidius/ncappzoo/</a><br />
<br />
<br />
<div style="background-color: white; color: #666666; font-family: "Trebuchet MS", Trebuchet, Verdana, sans-serif;">
<div style="font-family: "trebuchet ms", trebuchet, verdana, sans-serif; margin: 0px; position: relative;">
<b><span style="color: red;">My Website</span></b></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<a href="http://softpowergroup.net/" style="color: #888888; text-decoration-line: none;"><span style="font-family: "arial" , "helvetica" , sans-serif;">http://softpowergroup.net/</span></a></div>
</div>
<div style="background-color: white; color: #666666; font-family: "trebuchet ms", trebuchet, verdana, sans-serif; font-size: 13.2px; font-weight: bold;">
<div style="margin: 0px;">
<span style="font-family: "arial" , "helvetica" , sans-serif;">email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400</span></div>
</div>
Android Arduinohttp://www.blogger.com/profile/11270818808943834694noreply@blogger.com0