Raspberry pi TensorFlow Object Detection API

Raspberry pi TensorFlow Object Detection API

What is TensorFlow Object Detection API?

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.

Why Raspberry Pi?

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 cooler projects on it. Given the popularity of Deep Learning and the Raspberry Pi Camera we thought it would be nice if we could detect any object using Deep Learning on the Pi.

Steps

Install OpenCV

http://raspberrypi4u.blogspot.com/2018/08/raspberry-pi-install-opencv.html

Install TensorFlow

https://www.tensorflow.org/install/

Install Protobuf

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md

get the packages needed

sudo apt-get install autoconf automake libtool curl

download the protobuf 

wget https://github.com/google/protobuf/releases/download/v3.5.1/protobuf-all-3.5.1.tar.gz

tar -zxvf protobuf-all-3.5.1.tar.gz
cd protobuf-3.5.1

Configure the build

./configure

Build the package

make -j4

sudo make install

cd python
export LD_LIBRARY_PATH=../src/.libs

python setup

python3 setup.py build --cpp_implementation 
python3 setup.py test --cpp_implementation
sudo python3 setup.py install --cpp_implementation

path commands

export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=cpp
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION_VERSION=3

Finally

sudo ldconfig

Test

protoc

Setup TensorFlow Directory 

mkdir tensorflow1
cd tensorflow1

Download the tensorflow repository

git clone --recurse-submodules https://github.com/tensorflow/models.git

we need to modify the PYTHONPATH environment

sudo nano ~/.bashrc

export PYTHONPATH=$PYTHONPATH:/home/pi/tensorflow1/models/research:/home/pi/tensorflow1/models/research/slim

cd /home/pi/tensorflow1/models/research
protoc object_detection/protos/*.proto --python_out=.

cd /home/pi/tensorflow1/models/research/object_detection

Download the SSDLite-MobileNet model

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

RUN Code

Download the code

wget https://raw.githubusercontent.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi/master/Object_detection_picamera.py

python3 Object_detection_picamera.py --usbcam

if you use picam

python3 Object_detection_picamera.py 

Reference

https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

My Website

http://softpowergroup.net/

email : info@softpowergroup.net  ,amphancm@gmail.com  Tel .+6681-6452400