taokong/RON

Why this implementation is different from the paper?

HiKapok opened this issue · 1 comments

Hello, in your paper, fc7 use 2x2 convolution with stride 2, why this implementation replace fc6 with a large kernel convolution while fc7 just fully-conv? thx!

fc6-conv is the transformation from fully connected op to conv op. You can find the transformation in Net Surgery