search

xinntao / ESRGAN

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
https://github.com/xinntao/BasicSR
Apache License 2.0
5.86k stars 1.04k forks source link

Why the result is not statisfactory as like the result in paper? #138

Open 1AnXu opened 8 months ago

1AnXu commented 8 months ago

Hello, I used the model provided by this reposity to test datasets, such as set5, set14, BSD100 and so on. However, the result is not goot as described in your paper, which is only 28.5478/0.8150 | 24.7989/0.6689 | 23.9438/0.6221. Can you tell me why? Is there any body who can help me?

d-linlin commented 3 months ago

Hello, I used the model provided by this reposity to test datasets, such as set5, set14, BSD100 and so on. However, the result is not goot as described in your paper, which is only 28.5478/0.8150 | 24.7989/0.6689 | 23.9438/0.6221. Can you tell me why? Is there any body who can help me?

May I ask how you calculated PSNR？