FID on coco about frido HOT 2 CLOSED

Hi @davidhalladay, thank you very much for your help!

I downloaded again the coco dataset and run the scripts.
I got FID=38.58 ... up to some randomness it should be ok, right?

from frido.

Hello helia95,

Thanks for using our code! You used the commands correctly.
Yet, I tested the evaluation code on aother server again and got the correct FID results (37.41) today, so I'm not sure which part might cause the error.
Could you check that the number of generated results is 2048? Since the number of results may largely effects the FID scores, I'm concerned that the evaluation could be terminated, and not all images were generated.

As for the issue of 2,048 val images, thanks for pointing it out (same issue in here.). I have added the setting for 2048 val image ids in the new config and have it updated. But, I think it should not effect the score that much. For qualitative results, I provide some randomly selected results below for reference. Also, you can turn on classifier-free guidance to further improve the generated quality, please refer to the bash script of text-to-image evaluation.

Thanks!

from frido.