poor evaluation metrics score

[davvvy]

Hi,

Thanks for your work first!

I run inference by your checkpoint and evaluate all the metrics you mentioned in the paper but I got very poor results. Could you please provide the code for evaluating the performance?

[Jerome-Young]

Hi, I encountered the same issue.

[Junhong Gou]

Hi, we tested the SSIM and LPIPS according to hr-vton’s evaluate.py, and the FID and KID metrics were obtained through the torch-fidelity library.

[davvvy]

Hi, we tested the SSIM and LPIPS according to hr-vton’s evaluate.py, and the FID and KID metrics were obtained through the torch-fidelity library.

Thanks for your reply! Also, I'm wondering how you evaluate the metrics at different image sizes. Do you train at different image sizes?

[Junhong Gou]

Yes, we trained the model at three resolutions.