Open davvvy opened 7 months ago
Hi, I encountered the same issue.
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.
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?
Yes, we trained the model at three resolutions.
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?