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

FID evaluation #8

Open
kkgoer opened this issue Mar 4, 2024 · 5 comments
Open

FID evaluation #8

kkgoer opened this issue Mar 4, 2024 · 5 comments

Comments

@kkgoer
Copy link

kkgoer commented Mar 4, 2024

Hi, can you provide pre-trained Inception model for Inception score and FID score evaluation? I look forward to your reply, thanks!

@YonghaoXu
Copy link
Owner

Hi, I didn't back up this model. You can easily train it by running pretrain_inception.py in the is_fid_score folder.

@kkgoer
Copy link
Author

kkgoer commented Mar 5, 2024

Hi, I didn't back up this model. You can easily train it by running pretrain_inception.py in the is_fid_score folder.

Thank you for your reply, one more small question, was the data without categories in the dataset not used to train the INCEPTION model, e.g. 00001.jpg?

@YonghaoXu
Copy link
Owner

Yes, those images are not considered for training the Inception model as the class information may be unclear.

@kkgoer
Copy link
Author

kkgoer commented Mar 24, 2024

Yes, those images are not considered for training the Inception model as the class information may be unclear.

Thank you for your reply, and one last small question, the GAN-based methods you compared in your paper, when you tested them, did you pick the last epoch saved model?

@YonghaoXu
Copy link
Owner

Yes, the model at the last epoch after training was used for evaluation.

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

2 participants