search

WuJie1010 / Facial-Expression-Recognition.Pytorch

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
MIT License
1.78k stars 545 forks source link

AvgPool2D #79

Open daredevil6776 opened 4 years ago

daredevil6776 commented 4 years ago

What is the use of AvgPool2D at the end in vgg.py ?

WuJie1010 commented 4 years ago

Transform convolution feature map into vector information

daredevil6776 commented 4 years ago

From last max pool layer we are getting vector as output i.e,(512 x 1 x 1) ,then why to use again AvgPool layer??