How To Re-export pruned ETLT?

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

I have the PeopleNet pruned etlt, problem is, in order to use DLA core on Jetson I will have to export using --force_ptq flag. How to?

2

Refer to https://developer.nvidia.com/blog/improving-int8-accuracy-using-quantization-aware-training-and-the-transfer-learning-toolkit/

3

@Morganh, As per your link, I seem to find no way to export without retraining. Can you guide me how to re export without retraining?

4

For how to export a tlt model into an etlt model, please refer to tlt user guide Integrating TAO Models into DeepStream — TAO Toolkit 3.22.05 documentation
Or you can also login the docker to refer to the jupyter notebook.