PlzHelp:Invalid training data. Predictors must be a N-by-1 cell array of sequences, where N is the number of sequences. All sequences must have the same feature dimension and

Question

Paromita Kundu on 1 Mar 2024

0
Link

Direct link to this question

https://se.mathworks.com/matlabcentral/answers/2089156-plzhelp-invalid-training-data-predictors-must-be-a-n-by-1-cell-array-of-sequences-where-n-is-the-n

Commented: Paromita Kundu on 2 Mar 2024

inputSize = [224 224 3];
filterSize = 5;
numFilters = 20;
numHiddenUnits = 200;
numClasses = 4;
layers = [ ...
    sequenceInputLayer(inputSize,'Name','input')
    
    sequenceFoldingLayer('Name','fold')
    
    convolution2dLayer(filterSize,numFilters,'Name','conv')
    batchNormalizationLayer('Name','bn')
    reluLayer('Name','relu')
    
    sequenceUnfoldingLayer('Name','unfold')
    flattenLayer('Name','flatten')
    
    lstmLayer(numHiddenUnits,'OutputMode','last','Name','lstm')
    
    fullyConnectedLayer(numClasses, 'Name','fc')
    softmaxLayer('Name','softmax')
    classificationLayer('Name','classification')];
lgraph = layerGraph(layers);
lgraph = connectLayers(lgraph,'fold/miniBatchSize','unfold/miniBatchSize');
miniBatchSize = 32;
options = trainingOptions("adam", ...
    'MaxEpochs',3, ...
    'MiniBatchSize',32, ...
    'InitialLearnRate',0.005, ...
    'LearnRateDropPeriod',2, ...
    'LearnRateSchedule',"piecewise", ...
    'L2Regularization',5e-4, ...
    'SequencePaddingDirection',"left", ...
    'Shuffle',"every-epoch", ...
    'ValidationFrequency',floor(numel(imdsTrain.Files)/miniBatchSize), ...
    'ValidationData',{imdsValidation,imdsValidation.Labels}, ...
    'Verbose',false, ...
    'Plots',"training-progress");
% 
net = trainNetwork(imdsTrain.Files,imdsTrain.Labels,lgraph,options);