Skip to content
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

The quality of generated images for FFHQ #31

Closed
enisimsar opened this issue Apr 7, 2022 · 6 comments
Closed

The quality of generated images for FFHQ #31

enisimsar opened this issue Apr 7, 2022 · 6 comments

Comments

@enisimsar
Copy link

Hello,

Thanks for sharing your source code and pre-trained weights. I am trying to generate high-quality images from FFHQ pre-trained model. However, the quality of generated images is not as good enough as stated in the paper. I could not reproduce the results.

I am using the pre-trained weights from here https://github.com/PeterouZh/CIPS-3D/releases/tag/v0.0.2

The command I tried:
python exp/cips3d/scripts/sample_images.py --tl_config_file exp/cips3d/configs/ffhq_exp.yaml --tl_command sample_images

Generated images:
0048220334 0038712131 0002215104

Do you have any idea regarding the problem?

@enisimsar enisimsar changed the title Generated image qualities The quality of generated images for FFHQ Apr 7, 2022
@xuyanwu
Copy link

xuyanwu commented Apr 8, 2022

I got the same question

@PeterouZh
Copy link
Owner

Hi,

Thank you for your attention.
You can tune the truncation hyperparameter of GANs.

By the way, one way to improve generation quality is to regularize 3D shapes. I am currently training new models and will release code and models when the effect is stable.

@PeterouZh
Copy link
Owner

I got the same question

I think the reason for the poor generation effect is the poor quality of the underlying 3D shape. I am working to solve this problem.

@zhywanna zhywanna mentioned this issue Apr 8, 2022
@enisimsar
Copy link
Author

Does truncation correspond to psi? @PeterouZh

@PeterouZh
Copy link
Owner

Does truncation correspond to psi? @PeterouZh

Yes.

@enisimsar
Copy link
Author

It's better now, psi=0.45

0023813720 0015039847 0002215104

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants