About nvidia:jetson-pose container

Hello,

Can I use an NGC container below in jetpack4.5 ?

https://ngc.nvidia.com/catalog/containers/nvidia:jetson-pose

Thank you.

Hi,

Sorry that this container is only available for JetPack4.4 DP.
You can use Deepstream docker instead:
https://ngc.nvidia.com/catalog/containers/nvidia:deepstream-l4t

Thanks

1 Like

Hello,

Can I run jetson-pose on nano with jetpack 4.5 installed just by running docker image?

Thank you.

Hello,

Even in the deepstream docker image, I can’t find a sample for jetson-pose. How can I run jetson-pose?

Thank you.

Hi @Hodu, recommend you check out these projects:

1 Like

Hello,

dlinano@dlinano-desktop:~/Downloads$ sudo python3 ./export_for_isaac.py --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.

Can you tell me how can I solve this error?

Thank you.

Hi @Hodu, it appears to not be finding the trt_pose/tasks/human_pose.json file. Manually specify the path to it with the --input_topology argument to the script. If you have further questions, I would post them to the trt_pose GitHub Issues so that the project maintainers can get back to you.

1 Like

Hi @dusty_nv ,

Thank you very much