VideoMAE-Action-Detection icon indicating copy to clipboard operation
VideoMAE-Action-Detection copied to clipboard

Published 20 hours ago • verified publisher icon MCG-NJU

Input resolution of train and validation

Open ylz0925 opened this issue 1 year ago • 0 comments

Hi authors,

I found that the input video resolution was set to 16x224x224 while the video resolution used during the validation was 16x256x352.

I might read it wrong, but I wonder how much the video resolution could affect the validation accuracy. Could you please provide results validated with 224x224?

ylz0925 avatar Mar 10 '23 13:03 ylz0925