Preprocess question

[andyhahaha]

Hi all,

I try to apply other flownet to DFF. I need to confirm the image preprocess is the same. However, I found the image is convert from BGR to RGB. https://github.com/msracver/Deep-Feature-Flow/blob/9d8ce2080db8e10d9899a57ff1dc947340a45eaf/lib/utils/image.py#L137 I check the KaimingHe resnet repo, their input image is BGR order. So why can use their pertained model but use difference preprocess.

Second question. I wonder what is the input of flownet. Is that (image - pixel_mean)/255 ? Some flownet repo normalize to [0, 1] and normalize again by imagenet mean, std Normalize(mean=[0,0,0], std=[255,255,255]) Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) Why the preprocessing are quite different ?

Really need your help ! Thx !