I am trying to run the BodyPoseNet model from NVIDIA locally on my MacBook Pro (M1 Pro). However, I cannot find any guide on how to do this. I am new to this field and do not have any experience with NVIDIA models. But I managed to run PoseNet through the MediaPipe package from Google on my Parallels Desktop Ubuntu 22.04 machine. Therefore, I would like to find a way to use the BodyPoseNet model for human skeleton detection. I do not need to train anything, just run the pretrained model. This is a part of my master's thesis, so I need to find a way to do it. Please help.
I tried chatgpt and bard also, but it did not work. On they official nvidia page:
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/bodyposenet they say to use TAO toolkit, but I can not find any guide how to use pretrained models with the toolkit.
