search

OpenGVLab / VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
https://arxiv.org/abs/2303.16727
MIT License
524 stars 63 forks source link

on the tad features extraction, is image normalization required? #62

Open auzxb opened 5 months ago

auzxb commented 5 months ago

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？

hywang66 commented 3 months ago

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

oooolga commented 2 months ago

Same question 👀

songweige commented 2 months ago

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