pytorch/vision
Ver no GitHubtransforms.ToTensor() for numpy float array in the range of [0.0, 255.0]
Open
#546 aberto em 13 de jul. de 2018
enhancementhelp wantedmodule: transforms
Métricas do repositório
- Stars
- (15.050 stars)
- Métricas de merge de PR
- (Mesclagem média 12d 8h) (14 fundiu PRs em 30d)
Description
I had come across a debugging scenario where the ToTensor() didn't convert the numpy float array in the range of [0.0, 255.0] to the range [0.0 to 1.0] due to following lines: https://github.com/pytorch/vision/blob/master/torchvision/transforms/functional.py#L50-L53
Basically, this API assumes that all the float arrays will already be in range [0.0 to 1.0]. Do you think we have to change this behavior?