逗比学长
双三次扩大后叠加进去
@windmaple @CauchyHu I've done several experiments recently, I think the key points is the about: 1. Data augmentation method. It seems that the large size of patches is very hard...
 My result using data augmentation is as above. Please let me know if reproducing a better result :)
 My result using pretrain model of celebA....
I meet this problem too...
@haolin512900 Have you solved this error??
> Happened to me too and it was caused by a color channel overflow (I have been scaling pixel vales from [0, 1] to [0, 255] and due to some...
I think the result is not precise. The Set5 dataset from the download link seems to have a higher (BICUBIC) PSNR than other sources where pictures isRGB instead of y...
I found the similar from here(https://github.com/alexzhou907/vae_ebm/blob/559e4645465b73f1987e19a197bdf05dad30cad0/data.py)
嗯....我依稀记得当时跑数字较小的程序的时候确实有bug没有解决