pytorch/vision
Voir sur GitHubtransforms.ToTensor() for numpy float array in the range of [0.0, 255.0]
Open
#546 ouverte le 13 juil. 2018
enhancementhelp wantedmodule: transforms
Métriques du dépôt
- Stars
- (15 050 stars)
- Métriques de merge PR
- (Merge moyen 12j 8h) (14 PRs mergées en 30 j)
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?