Closed T5eng closed 4 years ago
have you fixed this problem ? I find fsrcnn can not work when i set the upscale factor to 8.
I think we need to adjust the "outpadding" argument according to different upscale factor. you can check out the pytorch document about ConvTranspose2d.
optimizer should be SGD instead of Adam learning rate of fsrcnn should be 0.001 weight init is not proper. Hyper parameter in Transposed Conv layer is not correct, causing error when changing upscale factor.