Issue in data/common.py while training on 16 bit, 1 channel tiff images

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

Issue in data/common.py while training on 16 bit, 1 channel tiff images #256

Open ahanagemini opened 4 years ago

ahanagemini commented 4 years ago

In src/data/common.py: Line 53 might have a bug. Why do we want to multiply by (rgb_range/255)? Do we want to convert to a range of 0-255. If so, should we not be dividing by (rgb_range/255)?