-
Notifications
You must be signed in to change notification settings - Fork 1.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Has anyone succeeded in reproducing the results? #44
Comments
The loss goes up with the default parameters/set up very early in the training even before the discriminator kicked in. I am puzzled by this. |
The same, using discriminator loss makes my result worse. |
once the discriminator kicks in everything goes crazy, does somebody have an advice? |
Perhaps because the discriminator is not trained at all until the taming-transformers/taming/modules/losses/vqperceptual.py Lines 106 to 107 in 3ba01b2
taming-transformers/taming/modules/losses/vqperceptual.py Lines 129 to 130 in 3ba01b2
|
I am still struggling with training VQ-GAN in the first stage, not even the conditional transformer which is a second stage.
The result looks fine before the discriminator loss is injected. BUT using the discriminator loss suddenly ruins the reconstructed images. disc_loss remains 1.0 during the training. Why??
The text was updated successfully, but these errors were encountered: