OpenGVLab/VideoMAEv2

on the tad features extraction, is image normalization required?

auzxb opened this issue · 3 comments

on the train stage,the images have to be loaded in to a range of [0, 1] and then normalized using mean = [0.485, 0.456, 0.406] and std = [0.229, 0.224, 0.225],is image normalization required when extracting tad features?

I have the same question here. Can anyone answer it?

Same question 👀

I have the same question here. Seems that there is a discrepancy in the preprocessing code between the training and inference.