How to train/fine-tune PeopleNet on 10 classes?

[anshola]

DeepStream Version - 7.0
Docker Image - nvcr.io/nvidia/deepstream:7.0-gc-triton-devel
GPU - RTX A6000
NVIDIA GPU Driver - 535.183.01

Is it possible to train/fine-tune PeopleNet on 10 classes instead of 3 which is default using TAO toolkit?

[yingliu]

Moving to TAO forum.

[Morganh]

Yes, but it is suggested to use YOLO_v4_tiny network instead to finetune so many classes. It will get much better result then detecnet_v2 network.