averagePooling1dLayer

R2026b

1-D average pooling layer

Description

A 1-D average pooling layer performs downsampling by dividing the input into 1-D pooling regions, then computing the average of each region.

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

• For time series and vector sequence input (data with three dimensions corresponding to the "C" (channel), "B" (batch), and "T" (time) dimensions), the layer pools over the "T" (time) dimension.

• For 1-D image input (data with three dimensions corresponding to the "S" (spatial), "C" (channel), and "B" (batch) dimensions), the layer pools over the "S" (spatial) dimension.

• For 1-D image sequence input (data with four dimensions corresponding to the "S" (spatial), "C" (channel), "B" (batch), and "T" (time) dimensions), the layer pools over the "S" (spatial) dimension.

Creation

Syntax

layer = averagePooling1dLayer(poolSize)

layer = averagePooling1dLayer(poolSize,Name=Value)

Description

layer = averagePooling1dLayer(poolSize) creates a 1-D average pooling layer and sets the PoolSize property.

layer = averagePooling1dLayer(poolSize,Name=Value) specifies options using one or more name-value arguments. For example, averagePooling1dLayer(3,Stride=2) creates a 1-D average pooling layer with a pool size of three and a stride of two.

Input Arguments

poolSize — Width of pooling regions

positive integer

Width of the pooling regions, specified as a positive integer.

The width of the pooling regions must be greater than or equal to the PaddingSize values.

This argument sets the PoolSize property.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Example: averagePooling1dLayer(3,Stride=2) creates a 1-D average pooling layer with a pool size of three and a stride of two.

Padding — Padding to apply to input

[0 0] (default) | "same" | nonnegative integer | vector of nonnegative integers

Padding to apply to the input, specified as one of the following:

• "same" — Apply padding such that the output size is ceil(inputSize/stride), where inputSize is the length of the input. When Stride is 1, the output is the same size as the input.

• Nonnegative integer sz — Add padding of size sz to both ends of the input.

• Vector [l r] of nonnegative integers — Add padding of size l to the left and r to the right of the input.

This argument sets the PaddingSize and PaddingMode properties.

Example: Padding=[2 1] adds padding of size 2 to the left and size 1 to the right.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

Stride — Step size for traversing input

1 (default) | positive integer

Step size for traversing the input, specified as a positive integer.

If the stride size is less than the pooling window size, then the pooling regions overlap.

This argument sets the Stride property.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

PaddingValue — Value used to pad input

0 (default) | "mean"

Value used to pad input, specified as one of these:

• 0 — Pad the input with zeros.

• "mean" — Pad the input with the mean of the pooling region.

Specify the padding approach using the Padding name-value argument.

The layer includes the padded areas when it calculates of the average value of the pooling regions along the edges. Using the mean value as the padding value reduces the effect of the padding values on the calculated average values.

This argument sets the PaddingValue property

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

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.

This argument sets the Name property.

Data Types: char | string

Properties

Average Pooling

PoolSize — Width of pooling regions

positive integer

This property is read-only after object creation. To set this property, use the corresponding positional input argument when you create the AveragePooling1DLayer object.

Width of the pooling regions, represented as a positive integer.

The width of the pooling regions must be greater than or equal to the padding dimensions PaddingSize.

Data Types: double

Stride — Step size for traversing input

1 (default) | positive integer

Step size for traversing the input, specified as a positive integer.

If the stride size is less than the pooling window size, then the pooling regions overlap.

Data Types: double

PaddingSize — Size of padding

[0 0] (default) | vector of two nonnegative integers

Size of padding to apply to each side of the input, specified as a vector [l r] of two nonnegative integers, where l is the padding applied to the left and r is the padding applied to the right. To use the same value for both the left and right sizes, you can also specify a scalar value.

When you create a layer, use the Padding name-value argument to specify the padding size.

Data Types: double

PaddingMode — Method to determine padding size

Read-only: 'manual' (default) | 'same'

This property is read-only.

Method to determine padding size, represented as one of these:

• 'manual' – Pad using the integer or vector specified by the Padding name-value argument.

• 'same' – Apply padding such that the output size is ceil(inputSize/Stride), where inputSize is the length of the input. When Stride is 1, the output is the same as the input.

When you create a layer, use the Padding name-value argument to specify the method to determine padding size.

PaddingValue — Value used to pad input

0 (default) | 'mean'

Value used to pad input, specified as one of these:

• 0 — Pad the input with zeros.

• 'mean' — Pad the input with the mean of the pooling region.

Specify the padding approach using the Padding name-value argument.

The layer includes the padded areas when it calculates of the average value of the pooling regions along the edges. Using the mean value as the padding value reduces the effect of the padding values on the calculated average values.

Data Types: double | char

Layer

Name — Layer name

'' (default) | character vector

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

Data Types: char

NumInputs — Number of inputs

Read-only: 1 (default)

This property is read-only.

Number of inputs to the layer, represented as 1. This layer has a single input only.

Data Types: double

InputNames — Input name

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

This property is read-only.

Input name, represented as {'in'}. This layer has a single input only.

NumOutputs — Number of outputs

Read-only: 1 (default)

This property is read-only.

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

Data Types: double

OutputNames — Output name

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

This property is read-only.

Output name, represented as {'out'}. This layer has a single output only.

Examples

Create 1-D Average Pooling Layer

Create a 1-D average pooling layer with a pool size of 3.

layer = averagePooling1dLayer(3)

layer = 
  AveragePooling1DLayer with properties:

            Name: ''

   Hyperparameters
        PoolSize: 3
          Stride: 1
     PaddingMode: 'manual'
     PaddingSize: [0 0]
    PaddingValue: 0

Include a 1-D average pooling layer in a layer array.

layers = [
    sequenceInputLayer(12,MinLength=40)
    convolution1dLayer(11,96)
    reluLayer
    averagePooling1dLayer(3)
    convolution1dLayer(11,96)
    reluLayer
    globalMaxPooling1dLayer
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  9×1 Layer array with layers:

     1   ''   Sequence Input           Sequence input with 12 channels
     2   ''   1-D Convolution          96 11 convolutions with stride 1 and padding [0  0]
     3   ''   ReLU                     ReLU
     4   ''   1-D Average Pooling      Average pooling with pool size 3, stride 1, and padding [0  0]
     5   ''   1-D Convolution          96 11 convolutions with stride 1 and padding [0  0]
     6   ''   ReLU                     ReLU
     7   ''   1-D Global Max Pooling   1-D global max pooling
     8   ''   Fully Connected          Fully connected layer with output size 10
     9   ''   Softmax                  Softmax

Algorithms

1-D Average Pooling Layer

A 1-D average pooling layer performs downsampling by dividing the input into 1-D pooling regions, then computing the average of each region. The layer pools the input by moving the pooling regions along a single dimension.

Most 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 represent vector sequence data as a 3-D array, in which the first dimension corresponds to the channel dimension, the second dimension corresponds to the batch dimension, and the third dimension corresponds to the time dimension. This representation is in the format "CBT" (channel, batch, time).

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

• For time series and vector sequence input (data with three dimensions corresponding to the "C" (channel), "B" (batch), and "T" (time) dimensions), the layer pools over the "T" (time) dimension.

• For 1-D image input (data with three dimensions corresponding to the "S" (spatial), "C" (channel), and "B" (batch) dimensions), the layer pools over the "S" (spatial) dimension.

• For 1-D image sequence input (data with four dimensions corresponding to the "S" (spatial), "C" (channel), "B" (batch), and "T" (time) dimensions), the layer pools over the "S" (spatial) dimension.

Layer Input and Output Formats

Most 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 represent vector sequence data as a 3-D array, in which the first dimension corresponds to the channel dimension, the second dimension corresponds to the batch dimension, and the third dimension corresponds to the time dimension. This representation is in the format "CBT" (channel, batch, time).

You can interact with these dlarray objects in automatic differentiation workflows, such as those for:

• developing a custom layer

• using a functionLayer object

• using the forward and predict functions with dlnetwork objects

This table shows the supported input formats of AveragePooling1DLayer 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 to 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 of the formats that the layer supports. The layer might support additional formats, such as formats with additional "S" (spatial) or "U" (unspecified) dimensions.

Input Format	Output Format
"SCB" (spatial, channel, batch)	"SCB" (spatial, channel, batch)
"CBT" (channel, batch, time)	"CBT" (channel, batch, time)
"SCBT" (spatial, channel, batch, time)	"SCBT" (spatial, channel, batch, time)
"SC" (spatial, channel)	"SC" (spatial, channel)
"CT" (channel, time)	"CT" (channel, time)
"SCT" (spatial, channel, time)	"SCT" (spatial, channel, time)

Extended Capabilities

C/C++ Code Generation

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

Usage notes and limitations:

• You can generate generic C/C++ code that does not depend on third-party libraries and deploy the generated code to hardware platforms.

GPU Code Generation

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

Usage notes and limitations:

• You can generate CUDA code that is independent of deep learning libraries and deploy the generated code to platforms that use NVIDIA^® GPU processors.

Version History

Introduced in R2021b