jb2020-super
jb2020-super
> did u solve this problem? the psnr of my bicubic image on SET5 is only 27.27db(for scale x4), while 28.42 in the paper. and that in my srcnn image...
The key point is that you should use the _imresize_ of MatLab as the paper said both for training and testing. Good luck!
Any plan to release the code and model?