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

Is it normal for inception score to be different? #36

Open
yxchng opened this issue Aug 7, 2023 · 1 comment
Open

Is it normal for inception score to be different? #36

yxchng opened this issue Aug 7, 2023 · 1 comment

Comments

@yxchng
Copy link

yxchng commented Aug 7, 2023

Creating feature extractor "inception-v3-compat" with features ['logits_unbiased', '2048']
Extracting features from input1
Looking for samples non-recursivelty in "generation_outputs/mage_vitb_imagenet_val_256x256/temp6.0-iter20" with extensions png,jpg,jpeg
Found 50000 samples
Processing samples                                                                                                                      
Extracting features from input2
Looking for samples non-recursivelty in "generation_outputs/imagenet_val_256x256" with extensions png,jpg,jpeg
Found 50000 samples
Processing samples                                                                                                                      
Inception Score: 80.50368455204321 ± 1.095018840712601
Frechet Inception Distance: 11.180833805524912
inception_score_mean: 80.50368
inception_score_std: 1.095019
frechet_inception_distance: 11.18083

The inception score I get for mage-b is 80.5. But your inception score is 81.2. Is it normal?

@LTH14
Copy link
Owner

LTH14 commented Aug 30, 2023

Yes, Inception Score can typically vary a bit. A 1-2 standard deviation is expected.

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