Here are 3 videos that walk through using the TLT Dectnet_V2 example to produce a model that runs on the Jetson Nano.
Part 1 covers startup of TLT through the first training.
Part 2 covers retraining after pruning to getting files ready to deploy to Nano
Part 3 covers converting the files to a .trt engine on nano and tweaking files to get best performance
Good Luck
And don’t forget to comment if you have an idea to improve tutorial.