You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Of course but you'll need a bigger discriminator and a generator for that. Currently the outputs are 32x32 since we use CIFAR10 for training this GAN. I recommend you to look up about various GAN structures.
Hi, @niffler92
How can I generate bigger than 64x64 with this source?
I want to generate a size of 128x128 or above sized image.
If Spectral Norm is good for safe training of GAN, I think that bigger sized generation is also possible..., Right?
Thanks in advance~
from @bemoregt.
The text was updated successfully, but these errors were encountered: