Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PSNR calculation #5

Open
chensteven opened this issue May 17, 2020 · 4 comments
Open

PSNR calculation #5

chensteven opened this issue May 17, 2020 · 4 comments

Comments

@chensteven
Copy link

Hi,

How come you are calculating PSNR between the bicubic image and predicted image? Shouldn't it be the PSNR between ground truth and predicted?

@junwoo091400
Copy link

Exactly, I agree with this!

@GaryL36
Copy link

GaryL36 commented Apr 12, 2022

I modified the program code and calculating PSNR between ground truth and predicted image. Then I used the best results of 400 training epoch. The reconstruction results seems OK, but the PSNR is very low(about 5dB). What's the problem?

@xiaolinstar
Copy link

I encountered the same problem. I trained on my dataset and directly trained RGB images. The effect was very poor, worse than Bicubic. Have you solved this problem?

@Liiiiaictx
Copy link

I modified the program code and calculating PSNR between ground truth and predicted image. Then I used the best results of 400 training epoch. The reconstruction results seems OK, but the PSNR is very low(about 5dB). What's the problem?

大佬,你是怎么修改的?将GT图像转换为YCBCR空间再提取Y通道吗?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants