Any complete installation guide for "deepstream_pose_estimation"?


I follow this link and I can get the deep stream working, but I stuck at the trt-pose, export fail. (Not json file something…)

nvidia@nvidia-desktop:~/trt_pose/trt_pose/utils$ sudo python --input_checkpoint resnet18_baseline_att_224x224_A_epoch_249.pth
[sudo] password for nvidia: 
Traceback (most recent call last):
  File "", line 56, in <module>
    import torch                    # Please refer to:
ImportError: No module named torch
nvidia@nvidia-desktop:~/trt_pose/trt_pose/utils$ sudo python3 --input_checkpoint resnet18_baseline_att_224x224_A_epoch_249.pth
Input model is not specified, using resnet18_baseline_att as a default.
Input width/height are not specified, using 224x224 as a default.
Output path is not specified, using resnet18_baseline_att_224x224_A_epoch_249.onnx as a default.
Input topology human_pose.json is not a valid (.json) file.

Is there any tutorial or complete guide of installation?

I saw it can be done, Deepstream_pose_estimation
But I guess may be some library has changed…
Shall I use deepstream 6.0?



ImportError: No module named torch

Sorry that the example also requires PyTorch library.
You can install it with the information below: