adaptiveAveragePooling2dLayer

Adaptive average pooling 2-D layer

Since R2024a

Description

A 2-D adaptive average pooling layer performs downsampling to give you the desired output size by dividing the input into rectangular pooling regions, then computing the average of each region.

Creation

Syntax

layer = adaptiveAveragePooling2dLayer(outputSize)

layer = adaptiveAveragePooling2dLayer(Name=name)

Description

layer = adaptiveAveragePooling2dLayer(outputSize) creates an adaptive average pooling layer and sets the OutputSize property.

layer = adaptiveAveragePooling2dLayer(Name=name) sets the optional Name property. For example, adaptiveAveragePooling2dLayer(16,Name="adap") creates an adaptive average pooling layer with output size [16 16] and sets the optional Name property.

Properties

Adaptive Average Pooling

OutputSize — Dimensions of the output

vector of two positive integers

Dimensions of the output size, specified as a vector of two positive integers [sz1 sz2]. When creating the layer, you can specify OutputSize as a scalar to use the same value for both dimensions.

Example: [12 14] specifies output size of 12 and 14 for the lengths of first and second dimensions respectively.

Layer

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 layers with the name "".

The AdaptiveAveragePooling2DLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

1 (default)

This property is read-only.

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

Data Types: double

InputNames — Input names

{'in'} (default)

This property is read-only.

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

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

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

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

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

Data Types: cell

Examples

Create Adaptive Average Pooling Layer

Create an adaptive average pooling layer with the output size [12 12] name "adap_avg1".

layer = adaptiveAveragePooling2dLayer(12,Name="adap_avg1")

layer = 
  AdaptiveAveragePooling2DLayer with properties:

          Name: 'adap_avg1'
    OutputSize: [12 12]

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

Use properties method to see a list of all properties.

Include an adaptive average pooling layer with the output size [12 12] in a Layer array. The layer automatically selects the stride and kernel-size to give you the specified output size.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    reluLayer
    adaptiveAveragePooling2dLayer(12)
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  6x1 Layer array with layers:

     1   ''   Image Input                    28x28x1 images with 'zerocenter' normalization
     2   ''   2-D Convolution                20 5x5 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   ReLU                           ReLU
     4   ''   2-D Adaptive Average Pooling   Adaptive average pooling with output size 12x12
     5   ''   Fully Connected                10 fully connected layer
     6   ''   Softmax                        softmax

Algorithms

2-D Adaptive Average Pooling Layer

A 2-D adaptive average pooling layer performs downsampling by dividing the input into rectangular pooling regions, then computing the average of each region.

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.

• For 1-D image sequence input (data with four dimensions corresponding to the pixels in one spatial dimension, the channels, the observations, and the time steps), the layer pools over the spatial and time 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 formats consist of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, 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, can be described 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 AdaptiveAveragePooling2DLayer 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)
"SCBT" (spatial, channel, batch, time)	"SCBT" (spatial, channel, batch, time)
"SSCBT" (spatial, spatial, channel, batch, time)	"SSCBT" (spatial, spatial, channel, batch, time)
"SSB" (spatial, spatial, batch)	"SSB" (spatial, spatial, batch)
"SSC" (spatial, spatial, channel)	"SSC" (spatial, spatial, channel)
"SCT" (spatial, channel, time)	"SCT" (spatial, channel, time)
"SSCT" (spatial, spatial, channel, time)	"SSCT" (spatial, spatial, channel, time)
"SBT" (spatial, batch, time)	"SBT" (spatial, batch, time)
"SSBT" (spatial, spatial, batch, time)	"SSBT" (spatial, spatial, batch, time)

References

[1] Nagi, J., F. Ducatelle, G. A. Di Caro, D. Ciresan, U. Meier, A. Giusti, F. Nagi, J. Schmidhuber, L. M. Gambardella. ''Max-Pooling Convolutional Neural Networks for Vision-based Hand Gesture Recognition''. IEEE International Conference on Signal and Image Processing Applications (ICSIPA2011), 2011.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

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

Version History

Introduced in R2024a