identityLayer

Identity layer

Since R2024b

Description

An identity layer is a layer whose output is identical to its input. You can use an identity layer to create a skip connection, which allows the input to skip one or more layers in the main branch of a neural network. For more information about skip connections, see More About.

Creation

Syntax

layer = identityLayer

layer = identityLayer(Name=name)

Description

layer = identityLayer creates an identity layer and stores it in an IdentityLayer object.

layer = identityLayer(Name=name) additionally specifies the layer name.

Input Arguments

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

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 IdentityLayer 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

Examples

Create Layer Array with Identity Layer

Include an identity layer in a layer array.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    identityLayer
    maxPooling2dLayer(2,Stride=2)
    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   ''   Identity          Identity
     4   ''   2-D Max Pooling   2×2 max pooling with stride [2  2] and padding [0  0  0  0]
     5   ''   Fully Connected   10 fully connected layer
     6   ''   Softmax           softmax

The third layer in layers is an IdentityLayer object that contains the properties of the identity layer.

Display the properties of the identity layer.

layers(3)

ans = 
  IdentityLayer with properties:

    Name: ''

Create Residual Network That Includes Identity Layer

Create a deep learning neural network that includes residual blocks and an identity layer. For more information about residual neural networks, see More About.

Define Block Architecture

Write a function that returns a network layer representing a residual block.

function resblock = residualBlockLayer(name)

reslayers = dlnetwork;

layers = [
    identityLayer(Name="split")
    convolution2dLayer(3,32,Padding="same")
    batchNormalizationLayer
    reluLayer
    convolution2dLayer(3,32,Padding="same")
    batchNormalizationLayer
    additionLayer(2,Name="add")
    reluLayer];

reslayers = addLayers(reslayers,layers);
reslayers = connectLayers(reslayers,"split","add/in2");

resblock = networkLayer(reslayers,Name=name);

end

The residualBlockLayer function accepts a layer name and returns a networkLayer object representing a residual block. The function uses identityLayer with the connectLayers function to create a skip connection between the input of the residual block and the second input of its final layer.

Create and Analyze Residual Network

Create a residual network using residualBlockLayer to generate the residual blocks.

layers = [
    imageInputLayer([224 224 3])
    convolution2dLayer(7,32,Stride=2,Padding="same")
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(3,Stride=2)
    residualBlockLayer("resBlock1")
    residualBlockLayer("resBlock2")
    globalAveragePooling2dLayer
    fullyConnectedLayer(5)
    softmaxLayer];

resnet = dlnetwork(layers)

resnet = 
  dlnetwork with properties:

         Layers: [10×1 nnet.cnn.layer.Layer]
    Connections: [9×2 table]
     Learnables: [22×3 table]
          State: [10×3 table]
     InputNames: {'imageinput'}
    OutputNames: {'softmax'}
    Initialized: 1

  View summary with summary.

resnet is a dlnetwork object that represents a residual network. resnet contains two networkLayer objects corresponding to two residual blocks.

Inspect Network

Use the expandLayers and analyzeNetwork functions to inspect the residual block layers in the Deep Network Designer app. The leftmost pane in Deep Network Designer shows the network layers and their connections.

xresnet = expandLayers(resnet);
analyzeNetwork(xresnet)

The names of the layers inside the first and second residual blocks begin with resBlock1: and resBlock2:, respectively. The first layer inside each block is an identity layer that accepts input from outside the residual block. Each identity layer has a skip connection to an addition layer. The names of the identity layers are resBlock1:split and resBlock2:split, and the names of the addition layers are resBlock1:add and resBlock2:add.

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 R2024b