MATLAB: Training model neural network

neural networkstraining

if reduceDataset

numUniqueLabels = numel(unique(adsTrain.Labels));

% Reduce the dataset by a factor of 20

adsTrain = splitEachLabel(adsTrain,round(numel(adsTrain.Files) / numUniqueLabels / 20));

adsValidation = splitEachLabel(adsValidation,round(numel(adsValidation.Files)/ numUniqueLabels / 20));

end

error line 2 showing statement will never execute

Best Answer

This sounds like an mlint warning. The source would be reduceDataset being false, which would cause the entire if block to be skipped.

Related Solutions

MATLAB: Invalid training data. Responses must be nonempty.

Hi Martin,

You can't pass an audioDatastore directly to the network. Create a transform datastore that organizes the data into (audio,label) pairs.

The code below is a simple example where we try to recognize a speaker using an idea similar to yours. The accuracy is not good, but hopefully it is a good starting point.

If you have not done so already, O also recommend looking into this gender ID example in Audio Toolbox:

https://www.mathworks.com/help/deeplearning/ug/classify-gender-using-long-short-term-memory-networks.html

You might have better luck extracting features from the audio, rather than passing the raw audio to a network.

In any case, here is some example code:

% Download the FSDD data set 
url = 'https://ssd.mathworks.com/supportfiles/audio/FSDD.zip';
datasetFolder = tempdir;
unzip(url,datasetFolder)
% Create datastore
% Use speaker name in file name as label
ads = audioDatastore(fullfile(datasetFolder,'FSDD'), ...
    'IncludeSubfolders',true);
[~,filenames] = fileparts(ads.Files);
ads.Labels = categorical(extractBetween(filenames,'_','_'));
[adsTrain,adsValidation] = splitEachLabel(ads,.9);
inputSize = 500;
numHiddenUnits = 100;
numClasses = length(unique(ads.Labels));
layers = [ ...
    sequenceInputLayer(inputSize)
    bilstmLayer(numHiddenUnits,"OutputMode","sequence")
    bilstmLayer(numHiddenUnits,"OutputMode","last")
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];
% Transformed datastores to be passed directly to network
tdsTrain = transform(@(x,info)processData(x,inputSize,info),adsTrain,'IncludeInfo',true);
tdsValidation = transform(@(x,info)processData(x,inputSize,info),adsValidation,'IncludeInfo',true);
options = trainingOptions("adam", ...
    "MaxEpochs",4, ...
    "MiniBatchSize",256, ...
    "Plots","training-progress", ...
    "Verbose",false, ...
    "Shuffle","every-epoch", ...
    "LearnRateSchedule","piecewise", ...
    "LearnRateDropFactor",0.1, ...
    "LearnRateDropPeriod",1, ...
    "ValidationData",tdsValidation,...
    'ValidationFrequency',100);
net = trainNetwork(tdsTrain,layers, options)

Here is the transform function I used:

function [data,info] = processData(audio,inputSize,info)
    % Break audio into sequences to length inputSize with overlap
    % inputSize/2
    audio = buffer(audio,inputSize,floor(inputSize/2));
    audio = mat2cell(audio,inputSize,ones(1,size(audio,2))).';
    label = repmat(info.Label,size(audio,1),1);
    
    data = table(audio,label);
end

MATLAB: Parfor: Unable to perform assignment because the size of the left side is 98-by-50 and the size of the right side is 107-by-50

Unfortunately, error reporting from parfor has some limitations, and specifically it cannot indicate the precise line within the loop body where the error is occurring.

Having said that, I cannot see in your loop body any places where you're performing a 2-dimensional assignment operation to generate the error that you're observing... (although my guess would be the assignment into XValidation).

One option in this case is to place the entire body of your parfor loop into a separate function - that way when things do fail, you should get a more precise error location. Something like this:

parfor ii = 1:numPar
    % Unfortunately, it looks like you'll need to pass through quite a number of parameters.
    XValidationC{ii} = loopBodyFcn(adsValidation, numPar, ii, numHops, numBands); % more here
end

Best Answer

Related Solutions

MATLAB: Invalid training data. Responses must be nonempty.

MATLAB: Parfor: Unable to perform assignment because the size of the left side is 98-by-50 and the size of the right side is 107-by-50

Related Question