[Python] Pytorch got CUDA error: device-side assert triggered while building a audio-video...

I'm building a project related to audio-video deepfake detection system. But while running the code im encountering the following error message:

CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

So I need some suggestion as to why am I encountering this error message and also how can I resolve the same

Git hub link(if needed): https://github.com/Arnav9923386924/Audio-Video-Deepfake-detection/tree/main

This is the second time it is showing the error. Before that there were some path errors which were handled by me. I can try switching back to cpu but the dataset folder contains video clips and to process those clips on cpu would be way more time consuming.

Continue reading...