dlnetwork

Deep learning network for custom training loops

Description

A dlnetwork object enables support for custom training loops using automatic differentiation.

Tip

For most deep learning tasks, you can use a pretrained network and adapt it to your own data. For an example showing how to use transfer learning to retrain a convolutional neural network to classify a new set of images, see Train Deep Learning Network to Classify New Images. Alternatively, you can create and train networks from scratch using layerGraph objects with the trainNetwork and trainingOptions functions.

If the trainingOptions function does not provide the training options that you need for your task, then you can create a custom training loop using automatic differentiation. To learn more, see Define Deep Learning Network for Custom Training Loops.

Creation

Syntax

dlnet = dlnetwork(lgraph)

Description

dlnet = dlnetwork(lgraph) converts a layer graph to a dlnetwork object representing a deep neural network for custom training loops.

Input Arguments

lgraph — Network architecture

layerGraph object

Network architecture, specified as a layer graph.

The layer graph must not contain output layers. When training the network, calculate the loss separately.

For a list of layers supported by dlnetwork, see Supported Layers.

Properties

Layers — Network layers

Layer array

Network layers, specified as a Layer array.

Connections — Layer connections

table

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

Learnables — Network learnable parameters

table

Network learnable parameters, specified as a table with three columns:

• Layer – Layer name, specified as a string scalar.

• Parameter – Parameter name, specified as a string scalar.

• Value – Value of parameter, specified as a dlarray.

The network learnable parameters contain the features learned by the network. For example, the weights of convolution and fully connected layers.

Data Types: table

State — Network state

table

Network state, specified as a table.

The network state is a table with three columns:

• Layer – Layer name, specified as a string scalar.

• Parameter – Parameter name, specified as a string scalar.

• Value – Value of parameter, specified as a numeric array object.

The network state contains information remembered by the network between iterations. For example, the state of LSTM and batch normalization layers.

During training or inference, you can update the network state using the output of the forward and predict functions.

Data Types: table

InputNames — Network input layer names

cell array

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

Data Types: cell

OutputNames — Network output layer names

cell array

Network output layer names, specified as a cell array of character vectors. This property includes all layers with disconnected outputs. If a layer has multiple outputs, then the disconnected outputs are specified as 'layerName/outputName'.

Data Types: cell

Object Functions

forward	Compute deep learning network output for training
predict	Compute deep learning network output for inference
layerGraph	Graph of network layers for deep learning
setL2Factor	Set L2 regularization factor of layer learnable parameter
setLearnRateFactor	Set learn rate factor of layer learnable parameter
getLearnRateFactor	Get learn rate factor of layer learnable parameter
getL2Factor	Get L2 regularization factor of layer learnable parameter

Examples

Convert Pretrained Network to dlnetwork Object

To implement a custom training loop for your network, first convert it to a dlnetwork object. Do not include output layers in a dlnetwork object. Instead, you must specify the loss function in the custom training loop.

Load a pretrained GoogLeNet model using the googlenet function. This function requires the Deep Learning Toolbox™ Model for GoogLeNet Network support package. If this support package is not installed, then the function provides a download link.

net = googlenet;

Convert the network to a layer graph and remove the layers used for classification using removeLayers.

lgraph = layerGraph(net);
lgraph = removeLayers(lgraph,["prob" "output"]);

Convert the network to a dlnetwork object.

dlnet = dlnetwork(lgraph)

dlnet = 
  dlnetwork with properties:

         Layers: [142x1 nnet.cnn.layer.Layer]
    Connections: [168x2 table]
     Learnables: [116x3 table]
          State: [0x3 table]
     InputNames: {'data'}
    OutputNames: {'loss3-classifier'}

Train Network Using Custom Training Loop

This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.

If trainingOptions does not provide the options you need (for example, a custom learning rate schedule), then you can define your own custom training loop using automatic differentiation.

This example trains a network to classify handwritten digits with the time-based decay learning rate schedule: for each iteration, the solver uses the learning rate given by ${\rho }_{\mathit{t}}=\frac{{\rho }_0}{1+\mathit{k}\mathit{t}}$, where t is the iteration number, $${\rho }_0$$ is the initial learning rate, and k is the decay.

Load Training Data

Load the digits data as an image datastore using the imageDatastore function and specify the folder containing the image data.

dataFolder = fullfile(toolboxdir('nnet'),'nndemos','nndatasets','DigitDataset');
imds = imageDatastore(dataFolder, ...
    'IncludeSubfolders',true, ....
    'LabelSource','foldernames');

Partition the data into training and validation sets. Set aside 10% of the data for validation using the splitEachLabel function.

[imdsTrain,imdsValidation] = splitEachLabel(imds,0.9,'randomize');

The network used in this example requires input images of size 28-by-28-by-1. To automatically resize the training images, use an augmented image datastore. Specify additional augmentation operations to perform on the training images: randomly translate the images up to 5 pixels in the horizontal and vertical axes. Data augmentation helps prevent the network from overfitting and memorizing the exact details of the training images.

inputSize = [28 28 1];
pixelRange = [-5 5];
imageAugmenter = imageDataAugmenter( ...
    'RandXTranslation',pixelRange, ...
    'RandYTranslation',pixelRange);
augimdsTrain = augmentedImageDatastore(inputSize(1:2),imdsTrain,'DataAugmentation',imageAugmenter);

To automatically resize the validation images without performing further data augmentation, use an augmented image datastore without specifying any additional preprocessing operations.

augimdsValidation = augmentedImageDatastore(inputSize(1:2),imdsValidation);

Determine the number of classes in the training data.

classes = categories(imdsTrain.Labels);
numClasses = numel(classes);

Define Network

Define the network for image classification.

layers = [
    imageInputLayer(inputSize,'Normalization','none','Name','input')
    convolution2dLayer(5,20,'Name','conv1')
    batchNormalizationLayer('Name','bn1')
    reluLayer('Name','relu1')
    convolution2dLayer(3,20,'Padding','same','Name','conv2')
    batchNormalizationLayer('Name','bn2')
    reluLayer('Name','relu2')
    convolution2dLayer(3,20,'Padding','same','Name','conv3')
    batchNormalizationLayer('Name','bn3')
    reluLayer('Name','relu3')
    fullyConnectedLayer(numClasses,'Name','fc')
    softmaxLayer('Name','softmax')];
lgraph = layerGraph(layers);

Create a dlnetwork object from the layer graph.

dlnet = dlnetwork(lgraph)

dlnet = 
  dlnetwork with properties:

         Layers: [12×1 nnet.cnn.layer.Layer]
    Connections: [11×2 table]
     Learnables: [14×3 table]
          State: [6×3 table]
     InputNames: {'input'}
    OutputNames: {'softmax'}

Define Model Gradients Function

Create the function modelGradients, listed at the end of the example, that takes a dlnetwork object, a mini-batch of input data with corresponding labels and returns the gradients of the loss with respect to the learnable parameters in the network and the corresponding loss.

Specify Training Options

Train for ten epochs with a mini-batch size of 128.

numEpochs = 10;
miniBatchSize = 128;

Specify the options for SGDM optimization. Specify an initial learn rate of 0.01 with a decay of 0.01, and momentum 0.9.

initialLearnRate = 0.01;
decay = 0.01;
momentum = 0.9;

Train Model

Create a minibatchqueue object that processes and manages mini-batches of images during training. For each mini-batch:

• Use the custom mini-batch preprocessing function preprocessMiniBatch (defined at the end of this example) to convert the labels to one-hot encoded variables.

• Format the image data with the dimension labels 'SSCB' (spatial, spatial, channel, batch). By default, the minibatchqueue object converts the data to dlarray objects with underlying type single. Do not add a format to the class labels.

• Train on a GPU if one is available. By default, the minibatchqueue object converts each output to a gpuArray if a GPU is available. Using a GPU requires Parallel Computing Toolbox™ and a CUDA® enabled NVIDIA® GPU with compute capability 3.0 or higher.

mbq = minibatchqueue(augimdsTrain,...
    'MiniBatchSize',miniBatchSize,...
    'MiniBatchFcn',@preprocessMiniBatch,...
    'MiniBatchFormat',{'SSCB',''});

Initialize the training progress plot.

figure
lineLossTrain = animatedline('Color',[0.85 0.325 0.098]);
ylim([0 inf])
xlabel("Iteration")
ylabel("Loss")
grid on

Initialize the velocity parameter for the SGDM solver.

velocity = [];

Train the network using a custom training loop. For each epoch, shuffle the data and loop over mini-batches of data. For each mini-batch:

• Evaluate the model gradients, state, and loss using the dlfeval and modelGradients functions and update the network state.

• Determine the learning rate for the time-based decay learning rate schedule.

• Update the network parameters using the sgdmupdate function.

• Display the training progress.

iteration = 0;
start = tic;

% Loop over epochs.
for epoch = 1:numEpochs
    % Shuffle data.
    shuffle(mbq);
    
    % Loop over mini-batches.
    while hasdata(mbq)
        iteration = iteration + 1;
        
        % Read mini-batch of data.
        [dlX, dlY] = next(mbq);
        
        % Evaluate the model gradients, state, and loss using dlfeval and the
        % modelGradients function and update the network state.
        [gradients,state,loss] = dlfeval(@modelGradients,dlnet,dlX,dlY);
        dlnet.State = state;
        
        % Determine learning rate for time-based decay learning rate schedule.
        learnRate = initialLearnRate/(1 + decay*iteration);
        
        % Update the network parameters using the SGDM optimizer.
        [dlnet,velocity] = sgdmupdate(dlnet,gradients,velocity,learnRate,momentum);
        
        % Display the training progress.
        D = duration(0,0,toc(start),'Format','hh:mm:ss');
        addpoints(lineLossTrain,iteration,loss)
        title("Epoch: " + epoch + ", Elapsed: " + string(D))
        drawnow
    end
end

Test Model

Test the classification accuracy of the model by comparing the predictions on the validation set with the true labels.

After training, making predictions on new data does not require the labels. Create minibatchqueue object containing only the predictors of the test data:

• To ignore the labels for testing, set the number of outputs of the mini-batch queue to 1.

• Specify the same mini-batch size used for training.

• Preprocess the predictors using the preprocessMiniBatchPredictors function, listed at the end of the example.

• For the single output of the datastore, specify the mini-batch format 'SSCB' (spatial, spatial, channel, batch).

numOutputs = 1;
mbqTest = minibatchqueue(augimdsValidation,numOutputs, ...
    'MiniBatchSize',miniBatchSize, ...
    'MiniBatchFcn',@preprocessMiniBatchPredictors, ...
    'MiniBatchFormat','SSCB');

Loop over the mini-batches and classify the images using modelPredictions function, listed at the end of the example.

predictions = modelPredictions(dlnet,mbqTest,classes);

Evaluate the classification accuracy.

YTest = imdsValidation.Labels;
accuracy = mean(predictions == YTest)

accuracy = 0.9530

Model Gradients Function

The modelGradients function takes a dlnetwork object dlnet, a mini-batch of input data dlX with corresponding labels Y and returns the gradients of the loss with respect to the learnable parameters in dlnet, the network state, and the loss. To compute the gradients automatically, use the dlgradient function.

function [gradients,state,loss] = modelGradients(dlnet,dlX,Y)

[dlYPred,state] = forward(dlnet,dlX);

loss = crossentropy(dlYPred,Y);
gradients = dlgradient(loss,dlnet.Learnables);

loss = double(gather(extractdata(loss)));

end

Model Predictions Function

The modelPredictions function takes a dlnetwork object dlnet, a minibatchqueue of input data mbq, and the network classes, and computes the model predictions by iterating over all data in the minibatchqueue object. The function uses the onehotdecode function to find the predicted class with the highest score.

function predictions = modelPredictions(dlnet,mbq,classes)

predictions = [];

while hasdata(mbq)
    
    dlXTest = next(mbq);
    dlYPred = predict(dlnet,dlXTest);
    
    YPred = onehotdecode(dlYPred,classes,1)';
    
    predictions = [predictions; YPred];
end

end

Mini Batch Preprocessing Function

The preprocessMiniBatch function preprocesses a mini-batch of predictors and labels using the following steps:

1. Preprocess the images using the preprocessMiniBatchPredictors function.

2. Extract the label data from the incoming cell array and concatenate into a categorical array along the second dimension.

3. One-hot encode the categorical labels into numeric arrays. Encoding into the first dimension produces an encoded array that matches the shape of the network output.

function [X,Y] = preprocessMiniBatch(XCell,YCell)

% Preprocess predictors.
X = preprocessMiniBatchPredictors(XCell);

% Extract label data from cell and concatenate.
Y = cat(2,YCell{1:end});

% One-hot encode labels.
Y = onehotencode(Y,1);

end

Mini-Batch Predictors Preprocessing Function

The preprocessMiniBatchPredictors function preprocesses a mini-batch of predictors by extracting the image data from the input cell array and concatenate into a numeric array. For grayscale input, concatenating over the fourth dimension adds a third dimension to each image, to use as a singleton channel dimension.

function X = preprocessMiniBatchPredictors(XCell)

% Concatenate.
X = cat(4,XCell{1:end});

end

Freeze Learnable Parameters of dlnetwork Object

Load a pretrained network.

net = squeezenet;

Convert the network to a layer graph, remove the output layer, and convert it to a dlnetwork object.

lgraph = layerGraph(net);
lgraph = removeLayers(lgraph,'ClassificationLayer_predictions');
dlnet = dlnetwork(lgraph);

The Learnables property of the dlnetwork object is a table that contains the learnable parameters of the network. The table includes parameters of nested layers in separate rows. View the first few rows of the learnables table.

learnables = dlnet.Learnables;
head(learnables)

ans=8×3 table
          Layer           Parameter           Value       
    __________________    _________    ___________________

    "conv1"               "Weights"    {3x3x3x64  dlarray}
    "conv1"               "Bias"       {1x1x64    dlarray}
    "fire2-squeeze1x1"    "Weights"    {1x1x64x16 dlarray}
    "fire2-squeeze1x1"    "Bias"       {1x1x16    dlarray}
    "fire2-expand1x1"     "Weights"    {1x1x16x64 dlarray}
    "fire2-expand1x1"     "Bias"       {1x1x64    dlarray}
    "fire2-expand3x3"     "Weights"    {3x3x16x64 dlarray}
    "fire2-expand3x3"     "Bias"       {1x1x64    dlarray}

To freeze the learnable parameters of the network, loop over the learnable parameters and set the learn rate to 0 using the setLearnRateFactor function.

factor = 0;

numLearnables = size(learnables,1);
for i = 1:numLearnables
    layerName = learnables.Layer(i);
    parameterName = learnables.Parameter(i);
    
    dlnet = setLearnRateFactor(dlnet,layerName,parameterName,factor);
end

To use the updated learn rate factors when training, you must pass the dlnetwork object to the update function in the custom training loop. For example, use the command

[dlnet,velocity] = sgdmupdate(dlnet,gradients,velocity);

More About

Supported Layers

The dlnetwork function supports the layers listed below and custom layers without forward functions returning a nonempty memory value.

Input Layers

Layer	Description
imageInputLayer	An image input layer inputs 2-D images to a network and applies data normalization.
image3dInputLayer	A 3-D image input layer inputs 3-D images or volumes to a network and applies data normalization.
sequenceInputLayer	A sequence input layer inputs sequence data to a network.
featureInputLayer	A feature input layer inputs feature data into a network and applies data normalization. Use this layer when you have a data set of numeric scalars representing features (data without spatial or time dimensions).

Convolution and Fully Connected Layers

Layer	Description
convolution2dLayer	A 2-D convolutional layer applies sliding convolutional filters to the input.
convolution3dLayer	A 3-D convolutional layer applies sliding cuboidal convolution filters to three-dimensional input.
groupedConvolution2dLayer	A 2-D grouped convolutional layer separates the input channels into groups and applies sliding convolutional filters. Use grouped convolutional layers for channel-wise separable (also known as depth-wise separable) convolution.
transposedConv2dLayer	A transposed 2-D convolution layer upsamples feature maps.
transposedConv3dLayer	A transposed 3-D convolution layer upsamples three-dimensional feature maps.
fullyConnectedLayer	A fully connected layer multiplies the input by a weight matrix and then adds a bias vector.

Sequence Layers

Layer	Description
sequenceInputLayer	A sequence input layer inputs sequence data to a network.
lstmLayer	An LSTM layer learns long-term dependencies between time steps in time series and sequence data.
bilstmLayer	A bidirectional LSTM (BiLSTM) layer learns bidirectional long-term dependencies between time steps of time series or sequence data. These dependencies can be useful when you want the network to learn from the complete time series at each time step.
gruLayer	A GRU layer learns dependencies between time steps in time series and sequence data.

For lstmLayer, bilstmLayer, and gruLayer objects, dlnetwork objects support layers with the default values for the StateActivationFunction and GateActivationFunction properties.

Activation Layers

Layer	Description
reluLayer	A ReLU layer performs a threshold operation to each element of the input, where any value less than zero is set to zero.
leakyReluLayer	A leaky ReLU layer performs a threshold operation, where any input value less than zero is multiplied by a fixed scalar.
clippedReluLayer	A clipped ReLU layer performs a threshold operation, where any input value less than zero is set to zero and any value above the clipping ceiling is set to that clipping ceiling.
eluLayer	An ELU activation layer performs the identity operation on positive inputs and an exponential nonlinearity on negative inputs.
tanhLayer	A hyperbolic tangent (tanh) activation layer applies the tanh function on the layer inputs.
softmaxLayer	A softmax layer applies a softmax function to the input.

Normalization, Dropout, and Cropping Layers

Layer	Description
batchNormalizationLayer	A batch normalization layer normalizes each input channel across a mini-batch. To speed up training of convolutional neural networks and reduce the sensitivity to network initialization, use batch normalization layers between convolutional layers and nonlinearities, such as ReLU layers.
groupNormalizationLayer	A group normalization layer divides the channels of the input data into groups and normalizes the activations across each group. To speed up training of convolutional neural networks and reduce the sensitivity to network initialization, use group normalization layers between convolutional layers and nonlinearities, such as ReLU layers. You can perform instance normalization and layer normalization by setting the appropriate number of groups.
crossChannelNormalizationLayer	A channel-wise local response (cross-channel) normalization layer carries out channel-wise normalization.
dropoutLayer	A dropout layer randomly sets input elements to zero with a given probability.
crop2dLayer	A 2-D crop layer applies 2-D cropping to the input.

Pooling and Unpooling Layers

Layer	Description
averagePooling2dLayer	An average pooling layer performs down-sampling by dividing the input into rectangular pooling regions and computing the average values of each region.
averagePooling3dLayer	A 3-D average pooling layer performs down-sampling by dividing three-dimensional input into cuboidal pooling regions and computing the average values of each region.
globalAveragePooling2dLayer	A global average pooling layer performs down-sampling by computing the mean of the height and width dimensions of the input.
globalAveragePooling3dLayer	A 3-D global average pooling layer performs down-sampling by computing the mean of the height, width, and depth dimensions of the input.
maxPooling2dLayer	A max pooling layer performs down-sampling by dividing the input into rectangular pooling regions, and computing the maximum of each region.
maxPooling3dLayer	A 3-D max pooling layer performs down-sampling by dividing three-dimensional input into cuboidal pooling regions, and computing the maximum of each region.
globalMaxPooling2dLayer	A global max pooling layer performs down-sampling by computing the maximum of the height and width dimensions of the input.
globalMaxPooling3dLayer	A 3-D global max pooling layer performs down-sampling by computing the maximum of the height, width, and depth dimensions of the input.
maxUnpooling2dLayer	A max unpooling layer unpools the output of a max pooling layer.

Combination Layers

Layer	Description
additionLayer	An addition layer adds inputs from multiple neural network layers element-wise.
multiplicationLayer	A multiplication layer multiplies inputs from multiple neural network layers element-wise.
depthConcatenationLayer	A depth concatenation layer takes inputs that have the same height and width and concatenates them along the third dimension (the channel dimension).
concatenationLayer	A concatenation layer takes inputs and concatenates them along a specified dimension. The inputs must have the same size in all dimensions except the concatenation dimension.