connectLayers

Connect layers in layer graph

Syntax

newlgraph = connectLayers(lgraph,s,d)

Description

example

newlgraph = connectLayers(lgraph,s,d) connects the source layer s to the destination layer d in the layer graph lgraph. The new layer graph, newlgraph, contains the same layers as lgraph and includes the new connection.

Examples

collapse all

Create an addition layer with two inputs and the name 'add_1'.

add = additionLayer(2,'Name','add_1')
add = 
  AdditionLayer with properties:

          Name: 'add_1'
     NumInputs: 2
    InputNames: {'in1'  'in2'}

Create two ReLU layers and connect them to the addition layer. The addition layer sums the outputs from the ReLU layers.

relu_1 = reluLayer('Name','relu_1');
relu_2 = reluLayer('Name','relu_2');

lgraph = layerGraph;
lgraph = addLayers(lgraph,relu_1);
lgraph = addLayers(lgraph,relu_2);
lgraph = addLayers(lgraph,add);

lgraph = connectLayers(lgraph,'relu_1','add_1/in1');
lgraph = connectLayers(lgraph,'relu_2','add_1/in2');

plot(lgraph)

Create a simple directed acyclic graph (DAG) network for deep learning. Train the network to classify images of digits. The simple network in this example consists of:

  • A main branch with layers connected sequentially.

  • A shortcut connection containing a single 1-by-1 convolutional layer. Shortcut connections enable the parameter gradients to flow more easily from the output layer to the earlier layers of the network.

Create the main branch of the network as a layer array. The addition layer sums multiple inputs element-wise. Specify the number of inputs for the addition layer to sum. All layers must have names and all names must be unique.

layers = [
    imageInputLayer([28 28 1],'Name','input')
    
    convolution2dLayer(5,16,'Padding','same','Name','conv_1')
    batchNormalizationLayer('Name','BN_1')
    reluLayer('Name','relu_1')
    
    convolution2dLayer(3,32,'Padding','same','Stride',2,'Name','conv_2')
    batchNormalizationLayer('Name','BN_2')
    reluLayer('Name','relu_2')
    convolution2dLayer(3,32,'Padding','same','Name','conv_3')
    batchNormalizationLayer('Name','BN_3')
    reluLayer('Name','relu_3')
    
    additionLayer(2,'Name','add')
    
    averagePooling2dLayer(2,'Stride',2,'Name','avpool')
    fullyConnectedLayer(10,'Name','fc')
    softmaxLayer('Name','softmax')
    classificationLayer('Name','classOutput')];

Create a layer graph from the layer array. layerGraph connects all the layers in layers sequentially. Plot the layer graph.

lgraph = layerGraph(layers);
figure
plot(lgraph)

Create the 1-by-1 convolutional layer and add it to the layer graph. Specify the number of convolutional filters and the stride so that the activation size matches the activation size of the 'relu_3' layer. This arrangement enables the addition layer to add the outputs of the 'skipConv' and 'relu_3' layers. To check that the layer is in the graph, plot the layer graph.

skipConv = convolution2dLayer(1,32,'Stride',2,'Name','skipConv');
lgraph = addLayers(lgraph,skipConv);
figure
plot(lgraph)

Create the shortcut connection from the 'relu_1' layer to the 'add' layer. Because you specified two as the number of inputs to the addition layer when you created it, the layer has two inputs named 'in1' and 'in2'. The 'relu_3' layer is already connected to the 'in1' input. Connect the 'relu_1' layer to the 'skipConv' layer and the 'skipConv' layer to the 'in2' input of the 'add' layer. The addition layer now sums the outputs of the 'relu_3' and 'skipConv' layers. To check that the layers are connected correctly, plot the layer graph.

lgraph = connectLayers(lgraph,'relu_1','skipConv');
lgraph = connectLayers(lgraph,'skipConv','add/in2');
figure
plot(lgraph);

Load the training and validation data, which consists of 28-by-28 grayscale images of digits.

[XTrain,YTrain] = digitTrain4DArrayData;
[XValidation,YValidation] = digitTest4DArrayData;

Specify training options and train the network. trainNetwork validates the network using the validation data every ValidationFrequency iterations.

options = trainingOptions('sgdm', ...
    'MaxEpochs',8, ...
    'Shuffle','every-epoch', ...
    'ValidationData',{XValidation,YValidation}, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');
net = trainNetwork(XTrain,YTrain,lgraph,options);

Display the properties of the trained network. The network is a DAGNetwork object.

net
net = 
  DAGNetwork with properties:

         Layers: [16×1 nnet.cnn.layer.Layer]
    Connections: [16×2 table]

Classify the validation images and calculate the accuracy. The network is very accurate.

YPredicted = classify(net,XValidation);
accuracy = mean(YPredicted == YValidation)
accuracy = 0.9968

Input Arguments

collapse all

Layer graph, specified as a LayerGraph object. To create a layer graph, use layerGraph.

Connection source, specified as a character vector.

  • 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: 'conv1'

Example: 'mpool/indices'

Connection destination, specified as 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: 'addlayer1/in2'

Output Arguments

collapse all

Output layer graph, returned as a LayerGraph object.

Introduced in R2017b