Main Content

layerGraph

Graph of network layers for deep learning

Description

A layer graph specifies the architecture of a deep learning network with a more complex graph structure in which layers can have inputs from multiple layers and outputs to multiple layers. Networks with this structure are called directed acyclic graph (DAG) networks. After you create a layerGraph object, you can use the object functions to plot the graph and modify it by adding, removing, connecting, and disconnecting layers. To train the network, use the layer graph as input to the trainNetwork function.

Creation

Description

example

lgraph = layerGraph creates an empty layer graph that contains no layers. You can add layers to the empty graph by using the addLayers function.

example

lgraph = layerGraph(layers) creates a layer graph from an array of network layers and sets the Layers property. The layers in lgraph are connected in the same sequential order as in layers.

example

lgraph = layerGraph(net) extracts the layer graph of a SeriesNetwork or DAGNetwork object. For example, you can extract the layer graph of a pretrained network to perform transfer learning.

lgraph = layerGraph(dlnet) extracts the layer graph of a dlnetwork. Use this syntax to use a dlnetwork with the trainNetwork function or Deep Network Designer.

Input Arguments

expand all

Trained network, specified as a SeriesNetwork or a DAGNetwork object. You can get a trained network by importing a pretrained network (for example, by using the googlenet function) or by training your own network using trainNetwork.

Network for custom training loops, specified as a dlnetwork object.

For dlnetwork input, the software extracts the numeric data from the learnable parameters and converts it to single precision.

Properties

expand all

This property is read-only.

Network layers, specified as a Layer array.

This property is read-only.

Layer connections, specified as a table with two columns.

Each table row represents a connection in the layer graph. The first column, Source, specifies the source of each connection. The second column, Destination, specifies the destination of each connection. The connection sources and destinations are either layer names or have the form 'layerName/IOName', where 'IOName' is the name of the layer input or output.

Data Types: table

This property is read-only.

Network input layer names, specified as a cell array of character vectors.

Data Types: cell

Network output layer names, specified as a cell array of character vectors.

Data Types: cell

Object Functions

addLayersAdd layers to layer graph
removeLayersRemove layers from layer graph
replaceLayerReplace layer in layer graph
connectLayersConnect layers in layer graph
disconnectLayersDisconnect layers in layer graph
plotPlot neural network layer graph

Examples

collapse all

Create an empty layer graph and an array of layers. Add the layers to the layer graph and plot the graph. addLayers connects the layers sequentially.

lgraph = layerGraph;

layers = [
    imageInputLayer([32 32 3],'Name','input')  
    convolution2dLayer(3,16,'Padding','same','Name','conv_1')
    batchNormalizationLayer('Name','BN_1')
    reluLayer('Name','relu_1')];

lgraph = addLayers(lgraph,layers);
figure
plot(lgraph)

Figure contains an axes object. The axes object contains an object of type graphplot.

Create an array of layers.

layers = [
    imageInputLayer([28 28 1],'Name','input')  
    convolution2dLayer(3,16,'Padding','same','Name','conv_1')
    batchNormalizationLayer('Name','BN_1')
    reluLayer('Name','relu_1')];

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)

Figure contains an axes object. The axes object contains an object of type graphplot.

Load a pretrained SqueezeNet network. You can use this trained network for classification and prediction.

net = squeezenet;

To modify the network structure, first extract the structure of the DAG network by using layerGraph. You can then use the object functions of LayerGraph to modify the network architecture.

lgraph = layerGraph(net)
lgraph = 
  LayerGraph with properties:

         Layers: [68x1 nnet.cnn.layer.Layer]
    Connections: [75x2 table]
     InputNames: {'data'}
    OutputNames: {'ClassificationLayer_predictions'}

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. To easily add connections later, specify names for the first ReLU layer and the addition layer.

layers = [
    imageInputLayer([28 28 1])
    
    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')
    
    averagePooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

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)

Figure contains an axes object. The axes object contains an object of type graphplot.

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 third ReLU layer. This arrangement enables the addition layer to add the outputs of the third ReLU layer and the 1-by-1 convolutional layer. 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)

Figure contains an axes object. The axes object contains an object of type graphplot.

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 third ReLU 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 third ReLU layer and the 'skipConv' layer. 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);

Figure contains an axes object. The axes object contains an object of type graphplot.

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);

Figure Training Progress (01-Sep-2021 08:31:32) contains 2 axes objects and another object of type uigridlayout. Axes object 1 contains 15 objects of type patch, text, line. Axes object 2 contains 15 objects of type patch, text, line.

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

net
net = 
  DAGNetwork with properties:

         Layers: [16x1 nnet.cnn.layer.Layer]
    Connections: [16x2 table]
     InputNames: {'imageinput'}
    OutputNames: {'classoutput'}

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

YPredicted = classify(net,XValidation);
accuracy = mean(YPredicted == YValidation)
accuracy = 0.9934
Introduced in R2017b