Jaykumaran R

For list device not found ,under utils->general.py change line 903 as prediction = prediction[0][1] for yolov9-c.pt or yolov9-e.pt. However for yolov9-c-converted you can run repo without any change

For list device not found ,under utils->general.py change line 903 as `prediction = prediction[0][1]` for yolov9-c.pt or yolov9-e.pt. However for yolov9-c-converted you can run repo without any change

 Facing new error.Can anyone give a link of your project where this is implemented successfully.

@Wildshire ,Thanks i found reason for my error,I was using HuggingFacePipeline from langchain instead of HuggingFacePipelineCompatible from nemoguardrails.. I hereby attach steps i followed with @Wildshire guidance to successfully work...

https://github.com/Jaykumaran/NemoGuardrails/tree/main my implementations with reference from https://blog.marvik.ai/2023/10/09/enhancing-llama2-conversations-with-nemo-guardrails-a-practical-guide/ https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/docs/user_guides/guardrails-library.md https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/nemoguardrails/library/hallucination/actions.py

Uninstall torchvision and install again worked without modifying or uninstall other packages,

Same issue importing transformers in a conda env with cv2 causes to freeze with the first frame indefinitely, However in the same env cv2.imshow() works when transformers is commented.

Hey Arslan, You can check now, the code should be available now. Thanks brmarkus for taking up this discussion.

Hi @Arslan-Mehmood1 , Can you close this issue, if you feel your query got resolved. Thanks

@zttiannnn The performance is poor. Could it be related to differences between the svla_so100_stacking dataset configs like state and the aloha one? From my understanding, the outreach by so-100 arm...