WHAT SHOULD BE DONE

tf to trt convert cqn only be done on other linux mqchine : tensorflow is not available for ARM

get sample model from nvidia sample support page for the relevant sample
use convert_to_uff located at /usr/lib/python2.7/dist-packages/uff/bin/convert_to_uff.py

sudo apt-get install python3-pip
sudo pip3 install protobuf numpy
sudo pip3 install tensorflow==2.0.0-alpha0


COPY THE MODEL

ON THE TEGRA
sudo python3.6 /usr/lib/python3.6/dist-packages/uff/bin/convert_to_uff.py frozen_inference_graph.pb -O NMS -p config.py