Open BrianPugh opened 2 years ago
so maybe this is actually a misunderstanding of ToTensor
I would have expected it to mirror pytorch's ToTensor
and convert PIL/numpy data into a jittor tensor, but it seems like it doesn't do this. What is the expected work flow then for preprocessing data?
Describe the bug
Numpy
(H, W, 3)
images fed intotransform.ImageNormalize
don't work as expected. Image must be transposed first. Common if usingcv2.imread
instead ofPIL.Image
.Full Log
Minimal Reproduce
Expected behavior
I'd expect numpy images of standard
(H, W, 3)
shape/dimensionality to work. It seems likePIL.Image
are explicitly transposed.