Raspberry Pi Projects: Raspberry Pi Android Things TensorFlow Machine Learning

วันพฤหัสบดีที่ 13 เมษายน พ.ศ. 2560

Raspberry Pi Android Things TensorFlow Machine Learning

Image Classifier Example Code Demo
This example source code are from https://github.com/androidthings . In the details of example code use external GPIO button.but we don't use it. So,we use computer keyboard instead.

This project is based on the TensorFlow Android Camera Demo TF_Classify app. The TensorFlow training was done using Google inception model and the trained data set is used to run inference and generate classification labels via TensorFlow Android Inference APIs.

Hardware

Raspberry Pi 3 Board + 16GB SD card
Pi camera module
Computer keyboard
Speaker or ear phone
HDMI display or TFT LED display

Software

Android Things Raspberry pi Image ( Develop Preview3 ) androidthings_rpi3_devpreview_3.zip
Android Things TensorFlow image classifier sample-tensorflow-imageclassifier
Android Studio 2.3

How to Run Code

First Flash Android Things image onto your Raspberry Pi SD card.

Connect Raspberry Pi to your network using the TCP/IP (LAN) Cable and use adb tool.

use this command to connect Raspberry Pi

```
$ adb connect Android.local
```

use this command to check connection and found android thing device.

```
$ adb devices
```

Now you can run code on Android Studio.

If you have everything work correctly.

Press ENTER button on keyboard.The current image is captured from attached camera.
The captured image is shown on the screen.Also the result is spoken out on speaker.if any.