search

bcmi / DCI-VTON-Virtual-Try-On

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.
https://arxiv.org/abs/2308.06101
MIT License
378 stars 55 forks source link

poor evaluation metrics score #37

Open davvvy opened 7 months ago

davvvy commented 7 months ago

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 commented 7 months ago

Hi, I encountered the same issue.

Limbor commented 7 months ago

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 commented 7 months ago

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?

Limbor commented 7 months ago

Yes, we trained the model at three resolutions.