search

sanghyun-son / EDSR-PyTorch

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
MIT License
2.43k stars 669 forks source link

Dataset size #234

Closed Siamw closed 4 years ago

Siamw commented 4 years ago

during training, (DIV2K) does your model crop or resize the images? or just use raw images just with filp and rotate ?

I mean do training images have same size or not??

thanks.

Siamw commented 4 years ago

oh, 96,, thanks