taesungp / swapping-autoencoder-pytorch

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)
Other
516 stars 84 forks source link

Conv2d in stylegan2_layers.py #8

Open ztt1024 opened 3 years ago

ztt1024 commented 3 years ago

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?