Main Content

Experiment with Weight Initializers for Transfer Learning

This example shows how to configure an experiment that initializes the weights of convolution and fully connected layers using different weight initializers for training. To compare the performance of different weight initializers for your task, create an experiment using this example as a guide.

When training a deep learning network, the initialization of layer weights and biases can have a big impact on how well the network trains. The choice of initializer has a bigger impact on networks without batch normalization layers. For more information on weight initializers, see Compare Layer Weight Initializers.

Open Experiment

First, open the example. Experiment Manager loads a project with a preconfigured experiment that you can inspect and run. To open the experiment, in the Experiment Browser pane, double-click the name of the experiment (WeightInitializerExperiment).

Built-in training experiments consist of a description, a table of hyperparameters, a setup function, and a collection of metric functions to evaluate the results of the experiment. For more information, see Configure Built-In Training Experiment.

The Description field contains a textual description of the experiment. For this example, the description is:

Perform transfer learning by initializing the weights of convolution and
fully connected layers in a pretrained network.

The Hyperparameters section specifies the strategy (Exhaustive Sweep) and hyperparameter values to use for the experiment. When you run the experiment, Experiment Manager trains the network using every combination of hyperparameter values specified in the hyperparameter table. This example uses the hyperparameters WeightsInitializer and BiasInitializer to specify the weight and bias initializers for the convolution and fully connected layers in a pretrained network. For more information about these initializers, see WeightsInitializer and BiasInitializer.

The Setup Function configures the training data, network architecture, and training options for the experiment. The input to the setup function is a structure with fields from the hyperparameter table. The setup function returns three outputs that you use to train a network for image classification problems. In this example, the setup function:

  • Loads a pretrained GoogLeNet network.

lgraph = googlenet(Weights="none");
  • Downloads and extracts the Flowers data set, which is about 218 MB. For more information on this data set, see Image Data Sets.

url = "http://download.tensorflow.org/example_images/flower_photos.tgz";
downloadFolder = tempdir;
filename = fullfile(downloadFolder,"flower_dataset.tgz");
imageFolder = fullfile(downloadFolder,"flower_photos");
if ~exist(imageFolder,"dir")
    disp("Downloading Flower Dataset (218 MB)...")
    websave(filename,url);
    untar(filename,downloadFolder)
end
imds = imageDatastore(imageFolder, ...
    IncludeSubfolders=true, ...
    LabelSource="foldernames");
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.9);
inputSize = net.Layers(1).InputSize;
augimdsTrain = augmentedImageDatastore(inputSize,imdsTrain);
augimdsValidation = augmentedImageDatastore(inputSize,imdsValidation);
  • Initializes the input weight in the convolution and fully connected layers by using the initializers specified in the hyperparameter table. The auxiliary function findLayersToReplace, which is listed in Appendix 2 at the end of this example, determines the layers in the network architecture that can be modified for transfer learning.

numClasses = numel(categories(imdsTrain.Labels));
weightsInitializer = params.WeightsInitializer;
biasInitializer = params.BiasInitializer;
learnableLayer = findLayersToReplace(lgraph);
newLearnableLayer = fullyConnectedLayer(numClasses,Name="new_fc");
lgraph = replaceLayer(lgraph,learnableLayer.Name,newLearnableLayer);
for i = 1:numel(lgraph.Layers)
    layer = lgraph.Layers(i);
     if class(layer) == "nnet.cnn.layer.Convolution2DLayer" || ...
             class(layer) == "nnet.cnn.layer.FullyConnectedLayer"
         layerName = layer.Name;
         newLayer = layer;
         newLayer.WeightsInitializer = weightsInitializer;
         newLayer.BiasInitializer = biasInitializer;
         lgraph = replaceLayer(lgraph,layerName,newLayer);
     end
 end
  • Defines a trainingOptions object for the experiment. The example trains the network for 10 epochs, using a mini-batch size of 128 and validating the network every 5 epochs.

miniBatchSize = 128;
validationFrequencyEpochs = 5;
numObservations = augimdsTrain.NumObservations;
numIterationsPerEpoch = floor(numObservations/miniBatchSize);
validationFrequency = validationFrequencyEpochs * numIterationsPerEpoch;
options = trainingOptions("sgdm", ...
    MaxEpochs=10, ...
    MiniBatchSize=miniBatchSize, ...
    Shuffle="every-epoch", ...
    ValidationData=augimdsValidation, ...
    ValidationFrequency=validationFrequency, ...
    Verbose=false);

To inspect the setup function, under Setup Function, click Edit. The setup function opens in MATLAB® Editor. In addition, the code for the setup function appears in Appendix 1 at the end of this example.

The Metrics section specifies optional functions that evaluate the results of the experiment. This example does not include any custom metric functions.

Run Experiment

When you run the experiment, Experiment Manager trains the network defined by the setup function multiple times. Each trial uses a different combination of hyperparameter values. By default, Experiment Manager runs one trial at a time. If you have Parallel Computing Toolbox™, you can run multiple trials at the same time. For best results, before you run your experiment, start a parallel pool with as many workers as GPUs. For more information, see Use Experiment Manager to Train Networks in Parallel and GPU Support by Release (Parallel Computing Toolbox).

  • To run one trial of the experiment at a time, on the Experiment Manager toolstrip, click Run.

  • To run multiple trials at the same time, click Use Parallel and then Run. If there is no current parallel pool, Experiment Manager starts one using the default cluster profile. Experiment Manager then executes multiple simultaneous trials, depending on the number of parallel workers available.

A table of results displays the accuracy and loss for each trial. While the experiment is running, click Training Plot to display the training plot and track the progress of each trial. Click Confusion Matrix to display the confusion matrix for the validation data in each completed trial.

Note that, for the trials that use the He weight initializer, Experiment Manager interrupts the training because the training and validation loss become undefined after a few iterations. Continuing the training for those trials does not produce any useful results.

When the experiment finishes, you can sort the results table by column, filter trials by using the Filters pane, or record observations by adding annotations. For more information, see Sort, Filter, and Annotate Experiment Results.

To test the performance of an individual trial, export the trained network or the training information for the trial. On the Experiment Manager toolstrip, select Export > Trained Network or Export > Training Information, respectively. For more information, see net and info.

Close Experiment

In the Experiment Browser pane, right-click the name of the project and select Close Project. Experiment Manager closes all of the experiments and results contained in the project.

Appendix 1: Setup Function

This function configures the training data, network architecture, and training options for the experiment.

Input

  • params is a structure with fields from the Experiment Manager hyperparameter table.

Output

  • augimdsTrain is an augmented image datastore object for the training data.

  • lgraph is a layer graph that defines the neural network architecture.

  • options is a trainingOptions object.

function [augimdsTrain,lgraph,options] = WeightInitializerExperiment_setup1(params)

lgraph = googlenet(Weights="none");

url = "http://download.tensorflow.org/example_images/flower_photos.tgz";
downloadFolder = tempdir;
filename = fullfile(downloadFolder,"flower_dataset.tgz");
imageFolder = fullfile(downloadFolder,"flower_photos");
if ~exist(imageFolder,"dir")
    disp("Downloading Flower Dataset (218 MB)...")
    websave(filename,url);
    untar(filename,downloadFolder)
end
imds = imageDatastore(imageFolder, ...
    IncludeSubfolders=true, ...
    LabelSource="foldernames");
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.9);
inputSize = lgraph.Layers(1).InputSize;
augimdsTrain = augmentedImageDatastore(inputSize,imdsTrain);
augimdsValidation = augmentedImageDatastore(inputSize,imdsValidation);

numClasses = numel(categories(imdsTrain.Labels));
weightsInitializer = params.WeightsInitializer;
biasInitializer = params.BiasInitializer;
learnableLayer = findLayersToReplace(lgraph);
newLearnableLayer = fullyConnectedLayer(numClasses,Name="new_fc");
lgraph = replaceLayer(lgraph,learnableLayer.Name,newLearnableLayer);
for i = 1:numel(lgraph.Layers)
    layer = lgraph.Layers(i);
    
    if class(layer) == "nnet.cnn.layer.Convolution2DLayer" || ...
            class(layer) == "nnet.cnn.layer.FullyConnectedLayer"
        layerName = layer.Name;
        newLayer = layer;
        
        newLayer.WeightsInitializer = weightsInitializer;
        newLayer.BiasInitializer = biasInitializer;
        
        lgraph = replaceLayer(lgraph,layerName,newLayer);
    end
end

miniBatchSize = 128;
validationFrequencyEpochs = 5;
numObservations = augimdsTrain.NumObservations;
numIterationsPerEpoch = floor(numObservations/miniBatchSize);
validationFrequency = validationFrequencyEpochs * numIterationsPerEpoch;
options = trainingOptions("sgdm", ...
    MaxEpochs=10, ...
    MiniBatchSize=miniBatchSize, ...
    Shuffle="every-epoch", ...
    ValidationData=augimdsValidation, ...
    ValidationFrequency=validationFrequency, ...
    Verbose=false);

end

Appendix 2: Find Layers to Replace

This function finds the single classification layer and the preceding learnable (fully connected or convolutional) layer of the layer graph lgraph.

function [learnableLayer,classLayer] = findLayersToReplace(lgraph)

if ~isa(lgraph,"nnet.cnn.LayerGraph")
    error("Argument must be a LayerGraph object.")
end

src = string(lgraph.Connections.Source);
dst = string(lgraph.Connections.Destination);
layerNames = string({lgraph.Layers.Name}');

isClassificationLayer = arrayfun(@(l) ...
    (isa(l,"nnet.cnn.layer.ClassificationOutputLayer")|isa(l,"nnet.layer.ClassificationLayer")), ...
    lgraph.Layers);

if sum(isClassificationLayer) ~= 1
    error("Layer graph must have a single classification layer.")
end
classLayer = lgraph.Layers(isClassificationLayer);

currentLayerIdx = find(isClassificationLayer);
while true
    
    if numel(currentLayerIdx) ~= 1
        error("Layer graph must have a single learnable layer preceding the classification layer.")
    end
    
    currentLayerType = class(lgraph.Layers(currentLayerIdx));
    isLearnableLayer = ismember(currentLayerType, ...
        ["nnet.cnn.layer.FullyConnectedLayer","nnet.cnn.layer.Convolution2DLayer"]);
    
    if isLearnableLayer
        learnableLayer =  lgraph.Layers(currentLayerIdx);
        return
    end
    
    currentDstIdx = find(layerNames(currentLayerIdx) == dst);
    currentLayerIdx = find(src(currentDstIdx) == layerNames);
end
end


See Also

Apps

Functions

Related Topics