Jetson Nano CUDA device not found

I’m using Ultralytics YOLOv8 trained model to make real-time predictions with OpenCV. When I run the script it says:

torch.cuda.is_available(): False
torch.cuda.device_count(): 0
os.environ[‘CUDA_VISIBLE_DEVICES’]: None
See Start Locally | PyTorch for up-to-date torch install instructions if no CUDA devices are seen by torch.

I tried export CUDA_HOME=/usr/local/cuda-10.0/
export LD_LIBRARY_PATH=/usr/local/cuda-10.0/lib64:$LD_LIBRARY_PATH

and I also tried the link given in the error, but nothing gets solved.

Can anyone help?

Can Any one please help???


Please share how you install the PyTorch package.
Is the package built with CUDA support?

It’s recommended to try our PyTorch prebuilt below:

More, for the latest JetPack 4.6.3, the CUDA version should be 10.2 rather than 10.0.

export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64:$LD_LIBRARY_PATH


This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.