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.

Sign up for GitHub

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

Jump to bottom

How many pictures did you use to calculate the FID value of different datasets in the paper？ #37

Open
wasdzzzzzz opened this issue Feb 22, 2022 · 1 comment
Open

How many pictures did you use to calculate the FID value of different datasets in the paper？ #37

wasdzzzzzz opened this issue Feb 22, 2022 · 1 comment

Comments

@wasdzzzzzz
Copy link

How many pictures did you use to calculate the FID value of different datasets in the paper？
Thanks a lot in advance.
@zzhuolun
Copy link

zzhuolun commented Mar 8, 2022 •
edited
Loading

I think the default setting of FID computation is: 8000 original images and 2048 generated images.
Check the following source code:
sample 8000 images from training set
generate 2048 images
compute fid

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zzhuolun @wasdzzzzzz