Why don't you use Sigmoid fucntion as the last activation function?
MengHao666 opened this issue · comments
As sigmodd fucntion could naturally limit output into [0,1], would it be better for the last activation function?
This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919
MengHao666 opened this issue · comments
As sigmodd fucntion could naturally limit output into [0,1], would it be better for the last activation function?