replaceLayer

Replace layer in layer graph

Syntax

newlgraph = replaceLayer(lgraph,layerName,larray)
newlgraph = replaceLayer(lgraph,layerName,larray,'ReconnectBy',mode)

Description

example

newlgraph = replaceLayer(lgraph,layerName,larray) replaces the layer layerName in the layer graph lgraph with the layers in larray.

replaceLayer connects the layers in larray sequentially and connects larray into the layer graph.

example

newlgraph = replaceLayer(lgraph,layerName,larray,'ReconnectBy',mode) additionally specifies the method of reconnecting layers.

Examples

collapse all

Define a simple network architecture and plot it.

layers = [
    imageInputLayer([28 28 1],'Name','input')    
    convolution2dLayer(3,16,'Padding','same','Name','conv_1')
    reluLayer('Name','relu_1')    
    additionLayer(2,'Name','add')
    fullyConnectedLayer(10,'Name','fc')
    softmaxLayer('Name','softmax')
    classificationLayer('Name','classoutput')];

lgraph = layerGraph(layers);
lgraph = connectLayers(lgraph,'input','add/in2');

figure
plot(lgraph)

Replace the ReLU layer in the network with a batch normalization layer followed by a leaky ReLU layer.

larray = [batchNormalizationLayer('Name','BN1')
          leakyReluLayer('Name','leakyRelu_1','Scale',0.1)];
lgraph = replaceLayer(lgraph,'relu_1',larray);

plot(lgraph)

This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with custom layers, and assemble the layers into a network ready for prediction.

Import Keras Network

Import the layers from a Keras network model. The network in 'digitsDAGnetwithnoise.h5' classifies images of digits.

filename = 'digitsDAGnetwithnoise.h5';
lgraph = importKerasLayers(filename,'ImportWeights',true);
Warning: Unable to import some Keras layers, because they are not yet supported by the Deep Learning Toolbox. They have been replaced by placeholder layers. To find these layers, call the function findPlaceholderLayers on the returned object.

The Keras network contains some layers that are not supported by Deep Learning Toolbox. The importKerasLayers function displays a warning and replaces the unsupported layers with placeholder layers.

Plot the layer graph using plot.

figure
plot(lgraph)
title("Imported Network")

Replace Placeholder Layers

To replace the placeholder layers, first identify the names of the layers to replace. Find the placeholder layers using findPlaceholderLayers.

placeholderLayers = findPlaceholderLayers(lgraph)
placeholderLayers = 
  2x1 PlaceholderLayer array with layers:

     1   'gaussian_noise_1'   PLACEHOLDER LAYER   Placeholder for 'GaussianNoise' Keras layer
     2   'gaussian_noise_2'   PLACEHOLDER LAYER   Placeholder for 'GaussianNoise' Keras layer

Display the Keras configurations of these layers.

placeholderLayers.KerasConfiguration
ans = struct with fields:
    trainable: 1
         name: 'gaussian_noise_1'
       stddev: 1.5000

ans = struct with fields:
    trainable: 1
         name: 'gaussian_noise_2'
       stddev: 0.7000

Define a custom Gaussian noise layer. To create this layer, save the file gaussianNoiseLayer.m in the current folder. Then, create two Gaussian noise layers with the same configurations as the imported Keras layers.

gnLayer1 = gaussianNoiseLayer(1.5,'new_gaussian_noise_1');
gnLayer2 = gaussianNoiseLayer(0.7,'new_gaussian_noise_2');

Replace the placeholder layers with the custom layers using replaceLayer.

lgraph = replaceLayer(lgraph,'gaussian_noise_1',gnLayer1);
lgraph = replaceLayer(lgraph,'gaussian_noise_2',gnLayer2);

Plot the updated layer graph using plot.

figure
plot(lgraph)
title("Network with Replaced Layers")

Specify Class Names

If the imported classification layer does not contain the classes, then you must specify these before prediction. If you do not specify the classes, then the software automatically sets the classes to 1, 2, ..., N, where N is the number of classes.

Find the index of the classification layer by viewing the Layers property of the layer graph.

lgraph.Layers
ans = 
  15x1 Layer array with layers:

     1   'input_1'                            Image Input             28x28x1 images
     2   'conv2d_1'                           Convolution             20 7x7x1 convolutions with stride [1  1] and padding 'same'
     3   'conv2d_1_relu'                      ReLU                    ReLU
     4   'conv2d_2'                           Convolution             20 3x3x1 convolutions with stride [1  1] and padding 'same'
     5   'conv2d_2_relu'                      ReLU                    ReLU
     6   'new_gaussian_noise_1'               Gaussian Noise          Gaussian noise with standard deviation 1.5
     7   'new_gaussian_noise_2'               Gaussian Noise          Gaussian noise with standard deviation 0.7
     8   'max_pooling2d_1'                    Max Pooling             2x2 max pooling with stride [2  2] and padding 'same'
     9   'max_pooling2d_2'                    Max Pooling             2x2 max pooling with stride [2  2] and padding 'same'
    10   'flatten_1'                          Flatten C-style         Flatten activations into 1D assuming C-style (row-major) order
    11   'flatten_2'                          Flatten C-style         Flatten activations into 1D assuming C-style (row-major) order
    12   'concatenate_1'                      Depth concatenation     Depth concatenation of 2 inputs
    13   'dense_1'                            Fully Connected         10 fully connected layer
    14   'activation_1'                       Softmax                 softmax
    15   'ClassificationLayer_activation_1'   Classification Output   crossentropyex

The classification layer has the name 'ClassificationLayer_activation_1'. View the classification layer and check the Classes property.

cLayer = lgraph.Layers(end)
cLayer = 
  ClassificationOutputLayer with properties:

            Name: 'ClassificationLayer_activation_1'
         Classes: 'auto'
      OutputSize: 'auto'

   Hyperparameters
    LossFunction: 'crossentropyex'

Because the Classes property of the layer is 'auto', you must specify the classes manually. Set the classes to 0, 1, ..., 9, and then replace the imported classification layer with the new one.

cLayer.Classes = string(0:9)
cLayer = 
  ClassificationOutputLayer with properties:

            Name: 'ClassificationLayer_activation_1'
         Classes: [0    1    2    3    4    5    6    7    8    9]
      OutputSize: 10

   Hyperparameters
    LossFunction: 'crossentropyex'

lgraph = replaceLayer(lgraph,'ClassificationLayer_activation_1',cLayer);

Assemble Network

Assemble the layer graph using assembleNetwork. The function returns a DAGNetwork object that is ready to use for prediction.

net = assembleNetwork(lgraph)
net = 
  DAGNetwork with properties:

         Layers: [15×1 nnet.cnn.layer.Layer]
    Connections: [15×2 table]

Input Arguments

collapse all

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

Name of the layer to replace, specified as a string scalar or a character vector.

Network layers, specified as a Layer array.

For a list of built-in layers, see List of Deep Learning Layers.

Method to reconnect layers specified as one of the following:

  • 'name' – Reconnect larray using the input and output names of the replaced layer. For each layer connected to an input of the replaced layer, reconnect the layer to the input of the same input name of larray(1). For each layer connected to an output of the replaced layer, reconnect the layer to the output of the same output name of larray(end).

  • 'order' – Reconnect larray using the order of the input names of larray(1) and the output names of larray(end). Reconnect the layer connected to the ith input of the replaced layer to the ith input of larray(1). Reconnect the layer connected to the jth output of the replaced layer to the jth output of larray(end).

Data Types: char | string

Output Arguments

collapse all

Output layer graph, returned as a LayerGraph object.

Introduced in R2018b