Seems some file missed
RouChan opened this issue · 3 comments
RouChan commented
RouChan commented
And for those under Pytorch1.5.1, you may need to add a line of code as follows at the beginning of train.py
.
torch.backends.cudnn.enabled = False
Xiangyu-Gao commented
Hi Rouchan, thanks for reporting the bug. I fixed it and pushed the new-version code. Please take a look and let me know if doesn't work.
RouChan commented
The code goes well now.
Thanks so much.