I am working on implementing GAN to generate high-resolution CelebA image.
There are two questions as below.
-
Can i use
nn.Conv2d
andnn.Conv2dTranspose2d
with non-zero padding (e.g. reflection padding)? Is the following method the most desirable?padded_images = nn.functional.pad(images, pad=(...), mode='reflect') outputs = nn.Conv2d(padded_images, ..., padding=0)
-
What’s the recommended padding for
nn.Conv2d
andnn.Conv2dTranspose
to reduce the artifacts in GAN? (zero, reflect or replicate)
Thanks.