Install CNN Vision related Software

Instructions

to use CNN based vision, i.e. inference based object detection against some pretrained object detector network, one must first install ``ftlite-runtime andlibedgetpu` to the PIs. They make it possible for the PIs to map tensor operations to a connected Google Coral EdgeTPU USB Accelerator device. The version numbers here are absolutely crucial, and therefore only specific builds are accepted.

to install tflite-runtime use the following AFTER you are in a pipenv shell of the project:

pip install https://github.com/google-coral/pycoral/releases/download/v1.0.1/tflite_runtime-2.5.0-cp37-cp37m-linux_armv7l.whl

to install libedgetpudo the following:

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 libedgetpu1-std