globalMaxPooling2dLayer

Global max pooling layer

Description

A 2-D global max pooling layer performs downsampling by computing the maximum of the height and width dimensions of the input.

Creation

Syntax

layer = globalMaxPooling2dLayer

layer = globalMaxPooling2dLayer('Name',name)

Description

layer = globalMaxPooling2dLayer creates a global max pooling layer.

layer = globalMaxPooling2dLayer('Name',name) sets the optional Name property.

Properties

Name — Layer name

'' (default) | character vector | string scalar

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to unnamed layers.

The GlobalMaxPooling2DLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

Read-only: 1 (default)

This property is read-only.

Number of inputs to the layer, stored as 1. This layer accepts a single input only.

Data Types: double

InputNames — Input names

Read-only: {'in'} (default)

This property is read-only.

Input names, stored as {'in'}. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

Read-only: 1 (default)

This property is read-only.

Number of outputs from the layer, stored as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

Read-only: {'out'} (default)

This property is read-only.

Output names, stored as {'out'}. This layer has a single output only.

Data Types: cell

Object Functions

Examples

Create Global Max Pooling Layer

Create a global max pooling layer with the name 'gmp1'.

layer = globalMaxPooling2dLayer('Name','gmp1')

layer = 
  GlobalMaxPooling2DLayer with properties:

    Name: 'gmp1'

Include a global max pooling layer in a Layer array.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    reluLayer
    globalMaxPooling2dLayer
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  6×1 Layer array with layers:

     1   ''   Image Input              28×28×1 images with 'zerocenter' normalization
     2   ''   2-D Convolution          20 5×5 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   ReLU                     ReLU
     4   ''   2-D Global Max Pooling   2-D global max pooling
     5   ''   Fully Connected          10 fully connected layer
     6   ''   Softmax                  softmax

Tips

• In an image classification network, you can use a globalMaxPooling2dLayer before the final fully connected layer to reduce the size of the activations without sacrificing performance. The reduced size of the activations means that the downstream fully connected layers will have fewer weights, reducing the size of your network.

• You can use a globalMaxPooling2dLayer towards the end of a classification network instead of a fullyConnectedLayer. Since global pooling layers have no learnable parameters, they can be less prone to overfitting and can reduce the size of the network. These networks can also be more robust to spatial translations of input data. You can also replace a fully connected layer with a globalAveragePooling2dLayer instead. Whether a globalAveragePooling2dLayer or a globalMaxPooling2dLayer is more appropriate depends on your data set.

  To use a global average pooling layer instead of a fully connected layer, the size of the input to globalMaxPooling2dLayer must match the number of classes in the classification problem

Algorithms

2-D Global Max Pooling Layer

A 2-D global max pooling layer performs downsampling by computing the maximum of the height and width dimensions of the input.

The dimensions that the layer pools over depends on the layer input:

• For 2-D image input (data with four dimensions corresponding to pixels in two spatial dimensions, the channels, and the observations), the layer pools over the spatial dimensions.

• For 2-D image sequence input (data with five dimensions corresponding to the pixels in two spatial dimensions, the channels, the observations, and the time steps), the layer pools over the spatial dimensions.

Layer Input and Output Formats

Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters in which each character describes the corresponding dimension of the data. The format consists of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, you can describe 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, as having the format "SSCB" (spatial, spatial, channel, batch).

You can interact with these dlarray objects in automatic differentiation workflows, such as those for developing a custom layer, using a functionLayer object, or using the forward and predict functions with dlnetwork objects.

This table shows the supported input formats of GlobalMaxPooling2DLayer objects and the corresponding output format. If the software passes the output of the layer to a custom layer that does not inherit from the nnet.layer.Formattable class, or a FunctionLayer object with the Formattable property set to 0 (false), then the layer receives an unformatted dlarray object with dimensions ordered according to the formats in this table. The formats listed here are only a subset. The layer may support additional formats such as formats with additional "S" (spatial) or "U" (unspecified) dimensions.

Input Format	Output Format
"SSCB" (spatial, spatial, channel, batch)	"SSCB" (spatial, spatial, channel, batch)
"SSC" (spatial, spatial, channel)	"SSC" (spatial, spatial, channel)

In dlnetwork objects, GlobalMaxPooling2DLayer objects also support these input and output format combinations.

Input Format	Output Format
"SSCBT" (spatial, spatial, channel, batch, time)	"SSCBT" (spatial, spatial, channel, batch, time)
"SSCT" (spatial, spatial, channel, time)	"SSCT" (spatial, spatial, channel, time)

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

• Code generation does not support passing dlarray objects with unspecified (U) dimensions to this layer.

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Refer to the usage notes and limitations in the C/C++ Code Generation section. The same limitations apply to GPU code generation.

Version History

Introduced in R2020a