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

About the difference in output when changing input normalisation changes #225

Open t-o509 opened 4 years ago

t-o509 commented 4 years ago

I want to learn about the difference in output when we changed the input normalisation from [0,1] to [-1,1] but I don't know how to change this. Thanks!