WY_CAS

> > > @VainF Yeah it works, thank you! So the input must be a torch.Tensor but without limit on its channel number. I have some grayscale images,when i input...

Input :a = torch.randint(0, 255, size=( 256, 256), dtype=torch.float32).cuda() / 255. b = a * 0.5 ValueError: Input images should be 4-d or 5-d tensors, but got torch.Size([256, 256]) Input:a...

thanks , It works!

when i run python setup.py install it show "TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType" can you help me

Hello,I got the same problem.Have you sovled this problem? thx !!!