Tensorflow Object Detection Walkthrough with Raspberry Pi

The following repository will allow you to leverage Tensorflow Object Detection models that have been converted to TFLite on a Raspberry Pi. This accompanies the Tensorflow Object Detection course on my YouTube channel.

Steps

Step 1. Walk through TFOD tutorial up to step 12 to generate TFLite files: https://github.com/nicknochnack/TFODCourse

Step 2. Clone the current repository onto your Raspberry Pi or copy it from a machine using RDP.

 git clone https://github.com/nicknochnack/TFODRPi

Step 3.Install the required dependencies onto your Raspberry Pi

pip3 install opencv-python 
sudo apt-get install libcblas-dev
sudo apt-get install libhdf5-dev
sudo apt-get install libhdf5-serial-dev
sudo apt-get install libatlas-base-dev
sudo apt-get install libjasper-dev 
sudo apt-get install libqtgui4 
sudo apt-get install libqt4-testv
echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list
curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -
sudo apt-get update
sudo apt-get install python3-tflite-runtime

Step 4. Copy your detect.tflite model into the same repository and update the labels.txt file to represent your labels.

Step 5. Run real time detections using the detect.py script

python3 detect.py