Faster R-CNN transformed input

[ptrblck]

@sigma_x

I get empty output if I use the multiplication by 255 in the transform method.

We would still need a code snippet to further debug the issue.

@sigma_x

In the tutorials I’ve found the input image pixels are between 0 and 1, as returned by the ToTensor() transform. So what should they be?

I would recommend to stick to the tutorial and use the train transformation. Note that the normalization will be done in side the model as seen here.