Closed zhanggengchen closed 1 year ago
I also had the same problem.
I retrain a model when I prepare the release of the code. This may cause a slight performance difference.
I will upload a new model soon.
You can achieve almost the same result by changing the line in test.py from
mean_out = cv2.cvtColor(sr_t.squeeze().permute(1,2,0).cpu().numpy(), cv2.COLOR_BGR2GRAY).mean()
to
mean_out = sr_t.view(sr_t.shape[0],-1).mean(dim=1)
Thanks for your reply, it's helpful for me 😃
Hello, I clone the code and test it on LOL dataset (eval15). I only modify the paths to dataset and pre-trained model in
confs/LOL-pc.yml
and runI got following results (PSNR 25.00) which is slightly different with the results in paper (PSNR 25.19)
I would like to know what causes the problem.