What's the usage of dividing input image by 255?

meetps / pytorch-semseg

Semantic Segmentation Architectures Implemented in PyTorch

https://meetshah.dev/semantic-segmentation/deep-learning/pytorch/visdom/2017/06/01/semantic-segmentation-over-the-years.html

MIT License

3.39k stars 796 forks source link

What's the usage of dividing input image by 255? #204

Open sjytker opened 5 years ago

sjytker commented 5 years ago

I see you guys set img_norm to False in train and val. However, we can usually see others' code normalize input image to [0,1].  
 So what's the difference?  In what circumstances should we normalize?