search

rmattson1008 / ornet

Organellar segmentation, tracking, and network modeling.
MIT License
0 stars 0 forks source link

Getting properly set up on server #1

Closed rmattson1008 closed 1 year ago

rmattson1008 commented 1 year ago

Need some help understanding why cuda is no longer working for me on logan.

This is the error message I get when I call torch.cuda.is_available().

"UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW (Triggered internally at /opt/conda/conda-bld/pytorch_1646756402876/work/c10/cuda/CUDAFunctions.cpp:112.) return torch._C._cuda_getDeviceCount() > 0 False"

rmattson1008 commented 1 year ago

Cuda is pretty well under control, using nvidia-smi to monitor GPU usage and pytorch lightning to use as many GPUs as is available