VITA-Group/DeblurGANv2

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 384, 1, 1])

yjdqk opened this issue · 1 comments

yjdqk commented

when predict an image,this problem occurs. Anyone hava solved the problem?

I found this error when I tried to use my own image. The problem occurs when I use very small images (like maybe 90 x 90). If this happens to you, try using the images provided from the dataset or try images with the same size.