Giters

liuzhuang13 / DenseNet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Is there a pad=1 in pool1 ?

xmyqsh opened this issue · comments

commented

I got it.
The pool of torch use floor((imsize + 2*pad - kernel) / stride) + 1