connectLayers

Connect layers in neural network

Syntax

netUpdated = connectLayers(net,s,d)

Description

netUpdated = connectLayers(net,s,d) connects the source layer s to the destination layer d in the dlnetwork object net. The updated network, netUpdated, contains the same layers as net and includes the new connection.

Examples

Create and Connect Addition Layer

Create an empty neural network dlnetwork object and add an addition layer with two inputs and the name 'add'.

net = dlnetwork;
layer = additionLayer(2,'Name','add');
net = addLayers(net,layer);

Add two ReLU layers to the neural network and connect them to the addition layer. The addition layer outputs the sum of the outputs from the ReLU layers.

layer = reluLayer('Name','relu1');
net = addLayers(net,layer);
net = connectLayers(net,'relu1','add/in1');

layer = reluLayer('Name','relu2');
net = addLayers(net,layer);
net = connectLayers(net,'relu2','add/in2');

Visualize the updated network in a plot.

plot(net)

Create Neural Network from Scratch

Define a two-output neural network that predicts both categorical labels and numeric values given 2-D images as input.

Specify the number of classes and responses.

numClasses = 10;
numResponses = 1;

Create an empty neural network.

net = dlnetwork;

Define the layers of the main branch of the network and the softmax output.

layers = [
    imageInputLayer([28 28 1],Normalization="none")

    convolution2dLayer(5,16,Padding="same")
    batchNormalizationLayer
    reluLayer(Name="relu_1")

    convolution2dLayer(3,32,Padding="same",Stride=2)
    batchNormalizationLayer
    reluLayer
    convolution2dLayer(3,32,Padding="same")
    batchNormalizationLayer
    reluLayer

    additionLayer(2,Name="add")

    fullyConnectedLayer(numClasses)
    softmaxLayer(Name="softmax")];

net = addLayers(net,layers);

Add the skip connection.

layers = [
    convolution2dLayer(1,32,Stride=2,Name="conv_skip")
    batchNormalizationLayer
    reluLayer(Name="relu_skip")];

net = addLayers(net,layers);
net = connectLayers(net,"relu_1","conv_skip");
net = connectLayers(net,"relu_skip","add/in2");

Add the fully connected layer for the regression output.

layers = fullyConnectedLayer(numResponses,Name="fc_2");
net = addLayers(net,layers);
net = connectLayers(net,"add","fc_2");

View the neural network in a plot.

figure
plot(net)

Input Arguments

net — Neural network

dlnetwork object

Neural network, specified as a dlnetwork object.

s — Connection source

string scalar | character vector

Connection source, specified as a character vector or a string scalar.

• If the source layer has a single output, then s is the name of the layer.

• If the source layer has multiple outputs, then s is the layer name followed by the "/" character and the name of the layer output: "layerName/outputName".

Example: "conv"

Example: "mpool/indices"

d — Connection destination

string scalar | character vector

Connection destination, specified as a string scalar or a character vector.

• If the destination layer has a single input, then d is the name of the layer.

• If the destination layer has multiple inputs, then d is the layer name followed by the "/" character and the name of the layer input: "layerName/inputName".

Example: "fc"

Example: "add/in1"

Output Arguments

netUpdated — Updated network

dlnetwork object

Updated network, returned as an uninitialized dlnetwork object.

To initialize the learnable parameters of a dlnetwork object, use the initialize function.

The connectLayers function does not preserve quantization information. If the input network is a quantized network, then the output network does not contain quantization information.

Version History

Introduced in R2017b

R2024a: LayerGraph objects are not recommended

Starting in R2024a, LayerGraph objects are not recommended. Use dlnetwork objects instead. This recommendation means that this syntax is not recommended for LayerGraph input:

• lgraphUpdated = connectLayers(lgraph,s,d)

Most functions that support LayerGraph objects also support dlnetwork objects. This table shows some typical usages of LayerGraph objects and how to update your code to use dlnetwork object functions instead.

Not Recommended	Recommended
lgraph = layerGraph;	net = dlnetwork;
lgraph = layerGraph(layers);	net = dlnetwork(layers,Initialize=false);
lgraph = layerGraph(net);	net = dag2dlnetwork(net);
lgraph = addLayers(lgraph,layers);	net = addLayers(net,layers);
lgraph = removeLayers(lgraph,layerNames);	net = removeLayers(net,layerNames);
lgraph = replaceLayer(lgraph,layerName,layers);	net = replaceLayer(net,layerName,layers);
lgraph = connectLayers(lgraph,s,d);	net = connectLayers(net,s,d);
lgraph = disconnectLayers(lgraph,s,d);	net = disconnectLayers(net,s,d);
plot(lgraph);	plot(net);

To train a neural network specified as a dlnetwork object, use the trainnet function.