Main Content

averagePooling2dLayer

Average pooling layer

expand all in page

Description

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

Creation

Syntax

layer = averagePooling2dLayer(poolSize)
layer = averagePooling2dLayer(poolSize,Name,Value)

Description

layer= averagePooling2dLayer(poolSize)creates an average pooling layer and sets thePoolSizeproperty.

example

layer= averagePooling2dLayer(poolSize,Name,Value)sets the optionalStrideandNameproperties using name-value pairs. To specify input padding, use the'Padding'name-value pair argument. For example,averagePooling2dLayer(2,'Stride',2)creates an average pooling layer with pool size[2 2]and stride[2 2]. You can specify multiple name-value pairs. Enclose each property name in single quotes.

Input Arguments

expand all

Name-Value Pair Arguments

Use comma-separated name-value pair arguments to specify the size of the zero padding to add along the edges of the layer input or to set theStrideandNameproperties. Enclose names in single quotes.

Example:averagePooling2dLayer(2,'Stride',2)creates an average pooling layer with pool size[2 2]and stride[2 2].

输入边缘填充, specified as the comma-separated pair consisting of'Padding'and 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 isceil(inputSize/stride), whereinputSizeis the height or width of the input andstrideis the stride in the corresponding dimension. The software adds the same amount of padding to the top and bottom, and to the left and right, if possible. If the padding that must be added vertically has an odd value, then the software adds extra padding to the bottom. If the padding that must be added horizontally has an odd value, then the software adds extra padding to the right.

  • Nonnegative integerp— Add padding of sizepto all the edges of the input.

  • Vector[a b]of nonnegative integers — Add padding of sizeato the top and bottom of the input and padding of sizebto the left and right.

  • Vector[t b l r]of nonnegative integers — Add padding of sizetto the top,bto the bottom,lto the left, andrto the right of the input.

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

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

Properties

expand all

Average Pooling

Dimensions of the pooling regions, specified as a vector of two positive integers[h w], wherehis the height andwis the width. When creating the layer, you can specifyPoolSizeas a scalar to use the same value for both dimensions.

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

The padding dimensionsPaddingSizemust be less than the pooling region dimensionsPoolSize.

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

步长为traversing the input vertically and horizontally, specified as a vector of two positive integers[a b], whereais the vertical step size andbis the horizontal step size. When creating the layer, you can specifyStrideas a scalar to use the same value for both dimensions.

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

The padding dimensionsPaddingSizemust be less than the pooling region dimensionsPoolSize.

Example:[2 3]specifies a vertical step size of 2 and a horizontal step size of 3.

Size of padding to apply to input borders, specified as a vector[t b l r]of four nonnegative integers, wheretis the padding applied to the top,bis the padding applied to the bottom,lis the padding applied to the left, andris the padding applied to the right.

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

Example:[1 1 2 2]adds one row of padding to the top and bottom, and two columns of padding to the left and right of the input.

Method to determine padding size, specified as'manual'or'same'.

The software automatically sets the value ofPaddingModebased on the'Padding'value you specify when creating a layer.

  • If you set the'Padding'option to a scalar or a vector of nonnegative integers, then the software automatically setsPaddingModeto'manual'.

  • If you set the'Padding'option to'same', then the software automatically setsPaddingModeto'same'and calculates the size of the padding at training 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 isceil(inputSize/stride), whereinputSizeis the height or width of the input andstrideis the stride in the corresponding dimension. The software adds the same amount of padding to the top and bottom, and to the left and right, if possible. If the padding that must be added vertically has an odd value, then the software adds extra padding to the bottom. If the padding that must be added horizontally has an odd value, then the software adds extra padding to the right.

Value used to pad input, specified as0or"mean".

When you use thePaddingoption to add padding to the input, the value of the padding applied can be one of the following:

  • 0— Input is padded with zeros at the positions specified by thePaddingproperty. The padded areas are included in the calculation of the average value of the pooling regions along the edges.

  • "mean"— Input is padded with the mean of the pooling region at the positions specified by thePaddingoption. The padded areas are effectively excluded from the calculation of the average value of each pooling region.

Note

Paddingproperty will be removed in a future release. UsePaddingSizeinstead. When creating a layer, use the'Padding'name-value pair argument to specify the padding size.

Size of padding to apply to input borders vertically and horizontally, specified as a vector[a b]of two nonnegative integers, whereais the padding applied to the top and bottom of the input data andbis the padding applied to the left and right.

Example:[1 1]adds one row of padding to the top and bottom, and one column of padding to the left and right of the input.

Layer

Layer name, specified as a character vector or a string scalar. ForLayerarray input, thetrainNetwork,assembleNetwork,layerGraph, anddlnetworkfunctions automatically assign names to layers withNameset to''.

数据类型:char|string

This property is read-only.

Number of inputs of the layer. This layer accepts a single input only.

数据类型:double

This property is read-only.

Input names of the layer. This layer accepts a single input only.

数据类型:cell

This property is read-only.

Number of outputs of the layer. This layer has a single output only.

数据类型:double

This property is read-only.

Output names of the layer. This layer has a single output only.

数据类型:cell

Examples

collapse all

Open Live Script

Create an average pooling layer with the name'avg1'.

layer = averagePooling2dLayer(2,'Name','avg1')
layer = AveragePooling2DLayer with properties: Name: 'avg1' Hyperparameters PoolSize: [2 2] Stride: [1 1] PaddingMode: 'manual' PaddingSize: [0 0 0 0] PaddingValue: 0

Include an average pooling layer in aLayerarray.

layers = [...imageInputLayer([28 28 1]) convolution2dLayer(5,20) reluLayer averagePooling2dLayer(2) fullyConnectedLayer(10) softmaxLayer classificationLayer]
layers = 7x1 Layer array with layers: 1 '' Image Input 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' ReLU ReLU 4 '' Average Pooling 2x2 average pooling with stride [1 1] and padding [0 0 0 0] 5 '' Fully Connected 10 fully connected layer 6 '' Softmax softmax 7 '' Classification Output crossentropyex
Open Live Script

创建一个与nonoverlappin平均池层g pooling regions.

layer = averagePooling2dLayer(2,'Stride',2)
layer = AveragePooling2DLayer with properties: Name: '' Hyperparameters PoolSize: [2 2] Stride: [2 2] PaddingMode: 'manual' PaddingSize: [0 0 0 0] PaddingValue: 0

The height and width of the rectangular regions (pool size) are both 2. The pooling regions do not overlap because the step size for traversing the images vertically and horizontally (stride) is also 2.

Include an average pooling layer with nonoverlapping regions in aLayerarray.

layers = [...imageInputLayer([28 28 1]) convolution2dLayer(5,20) reluLayer averagePooling2dLayer(2,'Stride',2) fullyConnectedLayer(10) softmaxLayer classificationLayer]
layers = 7x1 Layer array with layers: 1 '' Image Input 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' ReLU ReLU 4 '' Average Pooling 2x2 average pooling with stride [2 2] and padding [0 0 0 0] 5 '' Fully Connected 10 fully connected layer 6 '' Softmax softmax 7 '' Classification Output crossentropyex
Open Live Script

Create an average pooling layer with overlapping pooling regions.

layer = averagePooling2dLayer([3 2],'Stride',2)
layer = AveragePooling2DLayer with properties: Name: '' Hyperparameters PoolSize: [3 2] Stride: [2 2] PaddingMode: 'manual' PaddingSize: [0 0 0 0] PaddingValue: 0

This layer creates pooling regions of size [3 2] and takes the average of the six elements in each region. The pooling regions overlap becauseStrideincludes dimensions that are less than the respective pooling dimensionsPoolSize.

Include an average pooling layer with overlapping pooling regions in aLayerarray.

layers = [...imageInputLayer([28 28 1]) convolution2dLayer(5,20) reluLayer averagePooling2dLayer([3 2],'Stride',2) fullyConnectedLayer(10) softmaxLayer classificationLayer]
layers = 7x1 Layer array with layers: 1 '' Image Input 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' ReLU ReLU 4 '' Average Pooling 3x2 average pooling with stride [2 2] and padding [0 0 0 0] 5 '' Fully Connected 10 fully connected layer 6 '' Softmax softmax 7 '' Classification Output crossentropyex

More About

expand all

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™.

See Also

||

Topics

Introduced in R2016a

Deep Learning Toolbox Documentation

金宝app

Introducing Deep Learning with MATLAB

Introducing Deep Learning with MATLAB

Download ebook