About test results

[Young-Zzz]

Hi,DAN is very cool and thanks you for releasing the code! When I run the test.py in DANv1,I didn't run the generate_mod_blur_LR_bic.py and create_lmdb.py,just set the LR and HR images in options/setting1/xx.yml,such as in setting1_x2.yml:

 test1:
    name: Set5
    mode: LQGT
    dataroot_GT: /datasets/Set5/LR/x2
    dataroot_LQ: /datasets/Set5/HR/x2

But the result of PSNR/SSIM is 35.59dB/0.938,is lower than the results in your paper."37.34/0.9526" May I ask is that the different setting of the .yml file contribute to the non-ideal results？

[greatlog]

The results are reported on datasets generated according to setting1. You need to re-generate the test datasets by yourserlf.

[greatlog]

Since one HR image has 8 corresponding degraded LR images in the test datasets, you may need to create 8 copies for each HR image to match the number of HRs and LRs.

You can just uncomment this line and re-generate the datasets again. The copies will be automatically saved under 'HR/x2/'.

[Young-Zzz]

I uncomment that line,and I ran the generate_mod_blur_LR_bic.py, I got /HR/x2 folder with 40 images and /LR/x2 folder with 5 images..... :(

[greatlog]

LRs are saved in 'LRBlur/'

[Young-Zzz]

I am so sorry to bothering you..I set up HR/x2 and LRblur/x2 folder path in x2.yml,but my result PSNR=28.4887dB,SSIM=0.8132,more lower..

[greatlog]

I have never met similar problem. It is hard to determine which step has a problem.