GlobalAveragePooling2D

As explained in Deep Learning with Python, Third Edition

A pooling layer that averages each feature map across its spatial dimensions to produce one value per channel.

How Deep Learning with Python, Third Edition covers it

How deep it goes

Explains spatial averaging and resulting shapes, but defers implementation internals and mathematical derivation.

Examples

Uses MNIST digits and dogs-versus-cats models with 3 × 3 or 7 × 7 feature maps before classification.

What it assumes

Assumes familiarity with Conv2D, MaxPooling2D, Dense layers, feature-map shapes, and basic classification outputs.

What you can do after

Build it from scratch in Keras as the transition from a final convolutional block to Dense classification layers.

How it connects

Connects Conv2D, MaxPooling2D, feature maps, Dense layers, and softmax or sigmoid classification.

liveBookmanning.com

Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Related concepts

• neural network layerkind of · A neural network layer is a computational stage or component that transforms input representations into outputs within a neural network.
• convolutional neural networkpart of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
• poolingimplements · Pooling is an operation that aggregates values or representations across regions or axes to produce a reduced or summarized representation.
• max poolingcontrasts with · Max pooling is an aggregation operation that replaces each local or grouped region with its maximum value, often to downsample a representation.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with Python, Third Edition. The section links point to the parts of the book it draws on.