Error #1
Description
I use the train.py to train my dataset ,i got the error:
loss.backward()
File "C:\Program Files\Anaconda\envs\torch\lib\site-packages\torch\tensor.py", line 221, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "C:\Program Files\Anaconda\envs\torch\lib\site-packages\torch\autograd_init_.py", line 132, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: Expected grad_output->is_contiguous(grad_output->suggest_memory_format()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
why?
How can I fix it?