Giters

cbovar / ConvNetSharp

Deep Learning in C#

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Dropout: Use upcaling at training

cbovar opened this issue · comments

commented

Scale by 1 / (1 - dropProb) to have a magnitude constant accross training (dropProb > 0) and testing (dropProb = 0)