fyu / drn

Dilated Residual Networks

Home Page:https://www.vis.xyz/pub/drn

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Can I ask why we use 'reflection' mode for padding in image.

visionxyz opened this issue · comments

commented

Can I know the reason? If we use 'reflect mode', for original part, we predict label, but the reflected part, we should predict 255, am I right? I can't understand it. Thank you! Dr. Yu.