CNN convolutional neural network pooling layer Pooling hands-on deep learning v2 pytorch

Pooling pooling layer

insert image description here
insert image description here

insert image description here
insert image description here
insert image description here
Common pooling layers

  • max pooling layer
  • Average pooling layer

insert image description here
insert image description here

2. Code implementation

insert image description here
insert image description here

insert image description here
insert image description here

insert image description here

The main effect of the pooling layer is to reduce the position sensitivity through stride. In the later implementation, Pooling is used less and less, because adding stride in the channel can also achieve the same effect, and adding various transpositions and offsets to the picture, the effect will be better.

reference

https://www.bilibili.com/video/BV1EV411j7nX/?p=1

Guess you like

Origin blog.csdn.net/zgpeace/article/details/124072099