I swear there will be a proper pdf with math galore for NoGAN eventually. I do think it has a lot of potential for to make training better so for now we can at least tweet and blog about it!https://twitter.com/remykarem/status/1135183936227749888 …
-
-
I’ve been having trouble getting the repeatable GAN process to run the second time. Still working on investigating. But I’ll follow later this week.
-
One thing I can tell you that may be throwing you off: Make sure to change old_checkpoint_num to the next increment for each repeat. So first repeat would be 1, second would be 2, etc.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
NoGAN - a transfer learning technique in GANs:
G - generator
D - discriminator
1. Pretrain G using perceptual loss
2. Save generated imgs from pretrained G
3. Pretrain D as binary classifier
4. Train both G & D in a normal GAN setting