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 carried over a habit from fastai notebooks which may not necessarily be great for this case which is that you have to run some cells carefully before doing the repeat. Namely- you'll need to make sure data_gen is initialized under 64px again. That part is dumb and I know it.
-
-
If I recall correctly it was that when I switched that part from 0 to 1 it wasn’t finding the 0 checkpoint it had tried to save.
-
I’ll check again to make sure I re-ran the 64px part. I think I had; but it had run out of GPU memory on the very final save images step so I had to restart the notebook.
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