Giters

MCG-NJU / VideoMAE-Action-Detection

[NeurIPS 2022 Spotlight] VideoMAE for Action Detection

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Input resolution of train and validation

ylz0925 opened this issue · comments

commented

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?