swapping-autoencoder-pytorch icon indicating copy to clipboard operation
swapping-autoencoder-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon taesungp

Conv2d in stylegan2_layers.py

Open chez-tozhang opened this issue 4 years ago • 0 comments

Hi, Thanks for sharing your code. Could I ask the reason that why you change the batch size to 1 and make the batch size as the number of groups in your ModulatedConv2d function? Repeating the weights will increase the memory request, can you let me know the advantage of doing that?

chez-tozhang avatar Jul 04 '21 11:07 chez-tozhang