train 오류

안녕하세요 교수님.

실습 코드(python3 train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --nosave) 수행 중 아래와 같은 오류가 발생햬습니다. 어떻게 하면 오류를 해결 할 수 있을지 궁금합니다.

현재 코랩 환경이 아닌 우둔투 local 환경에서 수행하고 있습니다.

RuntimeError: Unable to find a valid cuDNN algorithm to run convolution
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7f22b6b32588>>
Traceback (most recent call last):
  File "/home/haneul/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1328, in __del__
  File "/home/haneul/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1262, in _shutdown_workers
AttributeError: 'NoneType' object has no attribute 'python_exit_status'
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7f235350fc18>>
Traceback (most recent call last):
  File "/home/haneul/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1328, in __del__
  File "/home/haneul/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1262, in _shutdown_workers
AttributeError: 'NoneType' object has no attribute 'python_exit_status