TengdaHan / DPC

Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

gray scale performance

YuqiHUO opened this issue · comments

Hi, I find that you actually don't perform grayscale, but the channel split in .augmentation.py

Do you know the performances between these two kinds of augmentation methods? Thanks!

For implementation efficiency, we use channel splitting. Grayscale is just a linear combination of there channels and I don't think they have a big difference in the representation performance.
I haven't compared the difference between the two.