assembleNetwork

Assemble deep learning network from pretrained layers

collapse all in page

Syntax

assembledNet = assembleNetwork(layers)

Description

assembleNetwork creates deep learning networks from layers without training.

Use assembleNetwork for the following tasks:

  • Convert a layer array or layer graph to a network ready for prediction.

  • Assemble networks from imported layers.

  • Modify the weights of a trained network.

To train a network from scratch, use trainNetwork.

example

assembledNet = assembleNetwork(layers) assembles the layer array or layer graph layers into a deep learning network ready to use for prediction.

Examples

collapse all

This example uses:

Open Live Script

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 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 They have been replaced by placeholder layers.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.

Replace Placeholder Layers

To replace the placeholder layers, first identify the names of the layers to replace. Find the placeholder layers using findPlaceholderLayers and display their Keras configurations.

placeholderLayers = findPlaceholderLayers(lgraph);
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 by saving 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);

Specify Class Names

The imported classification layer does not contain the classes, so you must specify these before assembling the network. 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.

The classification layer has the name 'ClassificationLayer_activation_1'. Set the classes to 0, 1, ..., 9, and then replace the imported classification layer with the new one.

cLayer = lgraph.Layers(end);
cLayer.Classes = string(0:9);
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: [15x1 nnet.cnn.layer.Layer]
    Connections: [15x2 table]
     InputNames: {'input_1'}
    OutputNames: {'ClassificationLayer_activation_1'}

Input Arguments

collapse all

Network layers, specified as a Layer array or a LayerGraph object.

To create a network with all layers connected sequentially, you can use a Layer array as the input argument. In this case, the returned network is a SeriesNetwork object.

A directed acyclic graph (DAG) network has a complex structure in which layers can have multiple inputs and outputs. To create a DAG network, specify the network architecture as a LayerGraph object and then use that layer graph as the input argument to assembleNetwork.

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

Output Arguments

collapse all

Assembled network ready for prediction, returned as a SeriesNetwork object or a DAGNetwork object. The returned network depends on the layers input argument:

  • If layers is a Layer array, then assembledNet is a SeriesNetwork object.

  • If layers is a LayerGraph object, then assembledNet is a DAGNetwork object.

See Also

| | | |

Topics

Introduced in R2018b

Deep Learning Toolbox Documentation

Support