alnah005
commented
2 years ago Try decreasing batch size. Sources: https://github.com/pytorch/pytorch/issues/46974 and https://github.com/pytorch/pytorch/issues/21819
Open fantasyfulan opened 3 years ago
alnah005
commented
2 years ago Try decreasing batch size. Sources: https://github.com/pytorch/pytorch/issues/46974 and https://github.com/pytorch/pytorch/issues/21819
我用create_dataset.py处理了自己的训练数据，然后放入CRNN中训练，出现以下错误： /crnn_net/dataset.py:95: UserWarning: torch.range is deprecated in favor of torch.arange and will be removed in 0.5. Note that arange generates values in [start; end), not [start; end]. batch_index = random_start + torch.range(0, self.batch_size - 1) THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCTensorMath.cu line=26 error=77 : an illegal memory access was encountered Traceback (most recent call last): File "train.py", line 201, in
cost = trainBatch(crnn, criterion, optimizer)
File "train.py", line 187, in trainBatch
crnn.zero_grad()
File "/crnn_net/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1114, in zerograd
p.grad.zero()
RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:26
我不知道什么原因导致了这个错误，也不知道怎么处理，望告知，