pytorch/vision
Auf GitHub ansehentransforms.ToTensor() for numpy float array in the range of [0.0, 255.0]
Open
#546 geöffnet am 13. Juli 2018
enhancementhelp wantedmodule: transforms
Repository-Metriken
- Stars
- (15.050 Stars)
- PR-Merge-Metriken
- (Durchschn. Merge 12T 8h) (14 gemergte PRs in 30 T)
Beschreibung
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?