-
-
Notifications
You must be signed in to change notification settings - Fork 5.3k
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
[BUG] StyleGAN2: latent vector is ignored #107
Comments
Thanks. Will look into it. |
This comment was marked as abuse.
This comment was marked as abuse.
Sorry for commenting on a rather old issue, but I've recently implemented StyleGAN2 (being helped by the code from this repository too) and experienced a similar issue - however, in my case, it wasn't due to My models were actually experiencing mode collapse, and no matter what the input was, a pretrained model would always generate the same image. I managed to overcome this issue by playing around with the learning rates and number of gradient accumulation steps. |
The implementation of StyleGAN2 does not learn a mapping for the latent vector
z
. The vectorz
is completely ignored, and a variety of generated images is provided bynoise
. To demonstrate the issue, I created a google colab with a pre-trained model that I trained for 55400 iterations.Images genertd with a random
![image](https://user-images.githubusercontent.com/1911342/152770077-f4d96a1c-9e7c-47ec-bb6a-721d4f4ae282.png)
z
and a fixednoise
:Images generated with a fixed
![image](https://user-images.githubusercontent.com/1911342/152770292-ae25a2e3-863e-4a18-a24f-87e19df2aedf.png)
z
and randomnoise
The text was updated successfully, but these errors were encountered: