averagePooling3dLayer

R2026b

3-D average pooling layer

Description

A 3-D average pooling layer performs downsampling by dividing three-dimensional input into cuboidal pooling regions, then computing the average values of each region.

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

For 3-D image input (data with five dimensions corresponding to pixels in three spatial dimensions, the channels, and the observations), the layer pools over the spatial dimensions.
For 3-D image sequence input (data with six dimensions corresponding to the pixels in three spatial dimensions, the channels, the observations, and the time steps), 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 and time dimensions.

Creation

Syntax

layer = averagePooling3dLayer(poolSize)

layer = averagePooling3dLayer(poolSize,Name=Value)

Description

layer = averagePooling3dLayer(poolSize) creates an average pooling layer and sets the PoolSize property.

layer = averagePooling3dLayer(poolSize,Name=Value) specifies options using one or more name-value arguments. For example, averagePooling3dLayer(2,Stride=2) creates a 3-D average pooling layer with a pool size of two and a stride of two.

example

Input Arguments

expand all

`poolSize` — Size of pooling regions
positive integer | vector of three positive integers

Size of pooling regions, specified as one of these:

Positive integer sz — Use sz-by-sz-by-sz pooling regions.
Vector of three positive integers [h w d] — Use h-by-w-by-d pooling regions.

If the stride sizes Stride are less than the respective pooling sizes, then the pooling regions overlap.

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

This argument sets the PoolSize property.

Example: [2 1 1] specifies pooling regions of height 2, width 1, and depth 1.

Name-Value Arguments

expand all

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.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: averagePooling3dLayer(2,Stride=2) creates a 3-D average pooling layer with a pool size of two and a stride of two.

`Padding` — Input edge padding
`0` (default) | array of nonnegative integers | `"same"`

Input edge padding, specified as one of these values:

"same" — Add padding of size calculated by the software at training or prediction time so that the output has the same size as the input when the stride equals 1. If the stride is larger than 1, then the output size is ceil(inputSize/stride), where inputSize is the height, width, or depth of the input and stride is the stride in the corresponding dimension. The software adds the same amount of padding to the top and bottom, to the left and right, and to the front and back, if possible. If the padding in a given dimension has an odd value, then the software adds the extra padding to the input as postpadding. In other words, the software adds extra vertical padding to the bottom, extra horizontal padding to the right, and extra depth padding to the back of the input.
Nonnegative integer p — Add padding of size p to all the edges of the input.
Three-element vector [a b c] of nonnegative integers — Add padding of size a to the top and bottom, padding of size b to the left and right, and padding of size c to the front and back of the input.
2-by-3 matrix [t l f;b r k] of nonnegative integers — Add padding of size t to the top, b to the bottom, l to the left, r to the right, f to the front, and k to the back of the input. In other words, the top row specifies the prepadding and the second row defines the postpadding in the three dimensions.

Example: Padding=1 adds one row of padding to the top and bottom, one column of padding to the left and right, and one plane of padding to the front and back of the input.

Example: Padding="same" adds padding so that the output has the same size as the input (if the stride equals 1).

`Stride` — Step size for traversing input
`l` (default) | positive integer | vector of three positive integers

Step size for traversing the input, specified as one of these:

positive integer sz — Traverse input with a step size of sz in the vertical, horizontal, and depth dimensions.
vector of three positive integers [a b c] — Traverse input with a vertical step size of a, a horizontal step size of b, and c is the step size along the depth dimension.

If the stride dimensions Stride are less than the respective pooling dimensions, then the pooling regions overlap.

This argument sets the Stride property.

Example: [2 3 1] specifies a vertical step size of 2, a horizontal step size of 3, and a step size along the depth of 1.

Properties

expand all

Average Pooling

`PoolSize` — Size of pooling regions
vector of three positive integers

This property is read-only after object creation. To set this property, use the corresponding positional input argument when you create the AveragePooling3DLayer object.

Size of the pooling regions, specified as a vector of three positive integers [h w d], where h is the height, w is the width, and d is the depth.

If the stride dimensions Stride are less than the respective pooling dimensions, then the pooling regions overlap.

Example: [2 1 1] specifies pooling regions of height 2, width 1, and depth 1.

`Stride` — Step size for traversing input
`[1 1 1]` (default) | vector of three positive integers

Step size for traversing the input in three dimensions, specified as a vector [a b c] of three positive integers, where a is the vertical step size, b is the horizontal step size, and c is the step size along the depth direction.

When you set this property, you can also specify a scalar value to use the same value for all dimensions.

If the stride sizes are less than the corresponding pooling window sizes, then the pooling regions overlap.

Example: [2 3 1] specifies a vertical step size of 2, a horizontal step size of 3, and a step size along the depth of 1.

Data Types: double

`PaddingSize` — Size of padding
`[0 0 0;0 0 0]` (default) | 2-by-3 matrix of nonnegative integers

Size of padding to apply to input borders, specified as 2-by-3 matrix [t l f;b r k] of nonnegative integers, where t and b are the padding applied to the top and bottom in the vertical direction, l and r are the padding applied to the left and right in the horizontal direction, and f and k are the padding applied to the front and back along the depth.

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

Example: [1 2 4; 1 2 4] adds one row of padding to the top and bottom, two columns of padding to the left and right, and four planes of padding to the front and back of the input.

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 has the same size as the input for a stride of one. If the stride is larger than 1, then the output size is ceil(inputSize/stride), where inputSize is the height, width, or depth of the input and stride is the stride in the corresponding dimension. The software adds the same amount of padding to the top and bottom, to the left and right, and to the front and back, if possible. If the padding in a given dimension has an odd value, then the software adds the extra padding to the input as postpadding. In other words, the software adds extra vertical padding to the bottom, extra horizontal padding to the right, and extra depth padding to the back of 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

collapse all

Create 3-D Average Pooling Layer

Open Live Script

Create a 3-D average pooling layer with nonoverlapping pooling regions that downsamples by a factor of 2.

layer = averagePooling3dLayer(2,Stride=2)

layer = 
  AveragePooling3DLayer with properties:

            Name: ''

   Hyperparameters
        PoolSize: [2 2 2]
          Stride: [2 2 2]
     PaddingMode: 'manual'
     PaddingSize: [2×3 double]
    PaddingValue: 0

Include a 3-D average pooling layer in a Layer array.

layers = [ ...
    image3dInputLayer([28 28 28 3])
    convolution3dLayer(5,20)
    reluLayer
    averagePooling3dLayer(2,Stride=2)
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  6×1 Layer array with layers:

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

Create 3-D Average Pooling Layer with Overlapping Pooling Regions

Open Live Script

Create a 3-D average pooling layer with overlapping pooling regions and padding for the top and bottom of the input.

layer = averagePooling3dLayer([3 2 2],Stride=2,Padding=[1 0 0])

layer = 
  AveragePooling3DLayer with properties:

            Name: ''

   Hyperparameters
        PoolSize: [3 2 2]
          Stride: [2 2 2]
     PaddingMode: 'manual'
     PaddingSize: [2×3 double]
    PaddingValue: 0

This layer creates pooling regions of size 3-by-2-by-2 and takes the average of the twelve elements in each region. The stride is 2 in all dimensions. The pooling regions overlap because there are stride dimensions Stride that are less than the respective pooling dimensions PoolSize.

Algorithms

expand all

3-D Average Pooling Layer

A 3-D average pooling layer extends the functionality of an average pooling layer to a third dimension, depth. An average pooling layer performs down-sampling by dividing the input into rectangular or cuboidal pooling regions, and computing the average of each region. To learn more, see the 2-D Average Pooling Layer section of the averagePooling2dLayer reference page.

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

For 3-D image input (data with five dimensions corresponding to pixels in three spatial dimensions, the channels, and the observations), the layer pools over the spatial dimensions.
For 3-D image sequence input (data with six dimensions corresponding to the pixels in three spatial dimensions, the channels, the observations, and the time steps), 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 and time dimensions.

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 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
using the forward and predict functions with dlnetwork objects

This table shows the supported input formats of AveragePooling3DLayer 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
`"SSSCB"` (spatial, spatial, spatial, channel, batch)	`"SSSCB"` (spatial, spatial, spatial, channel, batch)
`"SSCBT"` (spatial, spatial, channel, batch, time)	`"SSCBT"` (spatial, spatial, channel, batch, time)
`"SSSCBT"` (spatial, spatial, spatial, channel, batch, time)	`"SSSCBT"` (spatial, spatial, spatial, channel, batch, time)
`"SSSB"` (spatial, spatial, spatial, batch)	`"SSSB"` (spatial, spatial, spatial, batch)

In dlnetwork objects, AveragePooling3DLayer objects also support these input and output format combinations.

Input Format	Output Format
`"SSSC"` (spatial, spatial, spatial, channel)	`"SSSC"` (spatial, spatial, spatial, channel)
`"SSCT"` (spatial, spatial, channel, time)	`"SSCT"` (spatial, spatial, channel, time)
`"SSSCT"` (spatial, spatial, spatial, channel, time)	`"SSSCT"` (spatial, spatial, spatial, channel, time)
`"SSBT"` (spatial, spatial, batch, time)	`"SSBT"` (spatial, spatial, batch, time)
`"SSSBT"` (spatial, spatial, spatial, batch, time)	`"SSSBT"` (spatial, spatial, spatial, batch, time)

Version History

Introduced in R2019a

averagePooling3dLayer

Description

Creation

Syntax

Description

Input Arguments

`poolSize` — Size of pooling regions
positive integer | vector of three positive integers

Name-Value Arguments

`Padding` — Input edge padding
`0` (default) | array of nonnegative integers | `"same"`

`Stride` — Step size for traversing input
`l` (default) | positive integer | vector of three positive integers

Properties

Average Pooling

`PoolSize` — Size of pooling regions
vector of three positive integers

`Stride` — Step size for traversing input
`[1 1 1]` (default) | vector of three positive integers

`PaddingSize` — Size of padding
`[0 0 0;0 0 0]` (default) | 2-by-3 matrix of nonnegative integers

`PaddingMode` — Method to determine padding size
Read-only: `'manual'` (default) | `'same'`

`PaddingValue` — Value used to pad input
`0` (default) | `'mean'`

Layer

`Name` — Layer name
`''` (default) | character vector

`NumInputs` — Number of inputs
Read-only: `1` (default)

`InputNames` — Input name
Read-only: `{'in'}` (default)

`NumOutputs` — Number of outputs
Read-only: `1` (default)

`OutputNames` — Output name
Read-only: `{'out'}` (default)

Examples

Create 3-D Average Pooling Layer

Create 3-D Average Pooling Layer with Overlapping Pooling Regions

Algorithms

3-D Average Pooling Layer

Layer Input and Output Formats

Version History

See Also

Topics

averagePooling3dLayer

Description

Creation

Syntax

Description

Input Arguments

poolSize — Size of pooling regions positive integer | vector of three positive integers

Name-Value Arguments

Padding — Input edge padding 0 (default) | array of nonnegative integers | "same"

Stride — Step size for traversing input l (default) | positive integer | vector of three positive integers

Properties

Average Pooling

PoolSize — Size of pooling regions vector of three positive integers

Stride — Step size for traversing input [1 1 1] (default) | vector of three positive integers

PaddingSize — Size of padding [0 0 0;0 0 0] (default) | 2-by-3 matrix of nonnegative integers

PaddingMode — Method to determine padding size Read-only: 'manual' (default) | 'same'

PaddingValue — Value used to pad input 0 (default) | 'mean'

Layer

Name — Layer name '' (default) | character vector

NumInputs — Number of inputs Read-only: 1 (default)

InputNames — Input name Read-only: {'in'} (default)

NumOutputs — Number of outputs Read-only: 1 (default)

OutputNames — Output name Read-only: {'out'} (default)

Examples

Create 3-D Average Pooling Layer

Create 3-D Average Pooling Layer with Overlapping Pooling Regions

Algorithms

3-D Average Pooling Layer

Layer Input and Output Formats

Version History

See Also

Topics

`poolSize` — Size of pooling regions
positive integer | vector of three positive integers

`Padding` — Input edge padding
`0` (default) | array of nonnegative integers | `"same"`

`Stride` — Step size for traversing input
`l` (default) | positive integer | vector of three positive integers

`PoolSize` — Size of pooling regions
vector of three positive integers

`Stride` — Step size for traversing input
`[1 1 1]` (default) | vector of three positive integers

`PaddingSize` — Size of padding
`[0 0 0;0 0 0]` (default) | 2-by-3 matrix of nonnegative integers

`PaddingMode` — Method to determine padding size
Read-only: `'manual'` (default) | `'same'`

`PaddingValue` — Value used to pad input
`0` (default) | `'mean'`

`Name` — Layer name
`''` (default) | character vector

`NumInputs` — Number of inputs
Read-only: `1` (default)

`InputNames` — Input name
Read-only: `{'in'}` (default)

`NumOutputs` — Number of outputs
Read-only: `1` (default)

`OutputNames` — Output name
Read-only: `{'out'}` (default)