Load Training Data

Load the Japanese Vowels data set as described in [1] and [2]. The zip filejapaneseVowels.zipcontains sequences of varying length. The sequences are divided into two folders,TrainandTest, which contain training sequences and test sequences, respectively. In each of these folders, the sequences are divided into subfolders, which are numbered from1to9. The names of these subfolders are the label names. A MAT file represents each sequence. Each sequence is a matrix with 12 rows, with one row for each feature, and a varying number of columns, with one column for each time step. The number of rows is the sequence dimension and the number of columns is the sequence length.

Unzip the sequence data.

文件名="japaneseVowels.zip"; outputFolder = fullfile(tempdir,"japaneseVowels"); unzip(filename,outputFolder);

Create Custom Mini-Batch Datastore

Create a custom mini-batch datastore. The mini-batch datastoresequenceDatastorereads data from a folder and gets the labels from the subfolder names. To use this datastore, first save the filesequenceDatastore.mto the path.

Create a datastore containing the sequence data usingsequenceDatastore.

folderTrain = fullfile(outputFolder,"Train"); dsTrain = sequenceDatastore(folderTrain)

dsTrain = sequenceDatastore with properties: Datastore: [1×1 matlab.io.datastore.FileDatastore] Labels: [270×1 categorical] NumClasses: 9 SequenceDimension: 12 MiniBatchSize: 128 NumObservations: 270

Define LSTM Network Architecture

定义LSTM网络体系结构。指定sequence dimension of the input data as the input size. Specify an LSTM layer with 100 hidden units and to output the last element of the sequence. Finally, specify a fully connected layer with output size equal to the number of classes, followed by a softmax layer and a classification layer.

inputSize = dsTrain.SequenceDimension; numClasses = dsTrain.NumClasses; numHiddenUnits = 100; layers = [ sequenceInputLayer(inputSize) lstmLayer(numHiddenUnits,'OutputMode','last') fullyConnectedLayer(numClasses) softmaxLayer classificationLayer];

指定training options. Specify'adam'as the solver and'GradientThreshold'as 1. Set the mini-batch size to 27 and set the maximum number of epochs to 75. To ensure that the datastore creates mini-batches of the size that thetrainNetworkfunction expects, also set the mini-batch size of the datastore to the same value.

Because the mini-batches are small with short sequences, the CPU is better suited for training. Set'ExecutionEnvironment'to'cpu'. To train on a GPU, if available, set'ExecutionEnvironment'to'auto'(the default value).

miniBatchSize = 27; options = trainingOptions('adam',...'ExecutionEnvironment','cpu',...“MaxEpochs”,75,...'MiniBatchSize',miniBatchSize,...'GradientThreshold',1,...'Verbose',0,...“阴谋”,'training-progress'); dsTrain.MiniBatchSize = miniBatchSize;

Train the LSTM network with the specified training options.

net = trainNetwork(dsTrain,layers,options);

Test the Network

Create a sequence datastore from the test data.

folderTest = fullfile(outputFolder,"Test"); dsTest = sequenceDatastore(folderTest);

Classify the test data. Specify the same mini-batch size as for the training data. To ensure that the datastore creates mini-batches of the size that theclassifyfunction expects, also set the mini-batch size of the datastore to the same value.

dsTest.MiniBatchSize = miniBatchSize; YPred = classify(net,dsTest,'MiniBatchSize',miniBatchSize);

Calculate the classification accuracy of the predictions.

YTest = dsTest.Labels; acc = sum(YPred == YTest)./numel(YTest)

acc =0.9432