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

Pretrained model psnr is 28.6136, less than result in paper 28.88 #120

Open
alg-leon opened this issue Jan 19, 2023 · 0 comments
Open

Pretrained model psnr is 28.6136, less than result in paper 28.88 #120

alg-leon opened this issue Jan 19, 2023 · 0 comments

Comments

@alg-leon
Copy link

I test the output png generate by your pretrained model.

But psnr is 28.615,less than the result in paper 28.88. Could you provide your eval code. Thanks a lot!!

folder = '.\sid\Sony';

path_list = dir(fullfile(folder,'\*_out.png'));
img_num = length(path_list);
%calculate psnr
total_ssim = 0;
if img_num > 0 
   for j = 1:img_num 
       image_name = path_list(j).name;
       input = imread(fullfile(folder,image_name));
       gt = imread(fullfile(folder,[image_name(1:end-8), '_gt.png']));
       psnr_val = psnr(im2double(input), im2double(gt));
       total_psnr = total_psnr + psnr_val;       
   end
end
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

1 participant