Dilated Residual Networks
Home Page:https://www.vis.xyz/pub/drn
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
visionxyz opened this issue 6 years ago · comments
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.