Error Using trainNetwork (line 170). Too many input arguments.

Where did i go wrong? Please help me with the code.

I have a table of 500x31 (features as columns =30 and class lable column 31 ). Feature values are in rows for 5 class (100 rows for each class).

dataset sample is shown below. when i run the code i am getting error

"Error using trainNetwork (line 170)

Too many input arguments.

Error in calling1 (line 30)

net = trainNetwork(dataTrain,YTrain,layers_1,options);

Caused by:

Error using trainNetwork>iParseInputArguments (line 326)

Too many input arguments."

%Spliting the data set into 80:20

cvp=cvpartition(coif2level3.class,'holdout',0.2);

dataTrain=coif2level3(training(cvp),:);

dataValidation=coif2level3(test(cvp),:);

XTrain=dataTrain(:,1:30);

YTrain=dataTrain.class;

YValidation=dataValidation.class;

%XTrain size 400x30

%YTrain size 400X1

%workspace

% Defining LSTM Architecture

numFeatures = 30;

numHiddenUnits = 100;

numClasses = 5;

layers_1= [ ...

sequenceInputLayer(numFeatures)

lstmLayer(numHiddenUnits,'OutputMode','last')

fullyConnectedLayer(numClasses)

softmaxLayer

classificationLayer];

miniBatchSize = 27;

maxEpochs = 100;

options = trainingOptions('adam', ...

'ExecutionEnvironment','cpu', ...

'MaxEpochs', ...

'MiniBatchSize',miniBatchSize, ...

'GradientThreshold',2, ...

'Shuffle','every-epoch', ...

'Verbose',false, ...

'Plots','training-progress');

net = trainNetwork(dataTrain,YTrain,layers_1,options);

Answer 1

[Christopher McCausland]

"Too many input arguments" is a sign that the function expects fewer input arguments. In this case your input arguments appear to be=> dataTrain,YTrain,layers_1,options.

Are only the arguments included in your function call? I think you may have included an extra one, or more.

[Returned_Argument] = myfunc(dataTrain,YTrain,layers_1,options);

[syed]

I didnot understand you .. the function trainNetwork takes in 4 input arguments. (dataTrain,YTrain,layers_1,options)

net = trainNetwork(dataTrain,YTrain,layers_1,options);

[Christopher McCausland]

Hi Syed,

I did some further digging, I suggest you have a look at the expected inputs for the trainNetwork function, here is the help file link. A similar question has been asked before here, as you can see they have passed unexpected variable types and recevive a similar error. The use of categorical inputs rather than numerical is not supported.

[syed]

Dear Christopher

The link was very helpful. I developed the code but face one error with featureInputLayer

%LSTM code for classification with featureset
%reading the feature file as table
filename="coif3_level1.xlsx";
data=readtable(filename);

%converting the class lable into categorical
labelname="class";
data=convertvars(data,labelname,'categorical');

%spliting the data set randomly 80:20 ratio.
data=splitvars(data);
head(data)
classNames=categories(data{:,labelname});
numObservations=size(data,1);
numObservationsTrain=floor(0.80*numObservations);
numObservationsTest=numObservations - numObservationsTrain;

%Create an array of random indices corresponding to the observations and partition it using the partition sizes
idx = randperm(numObservations);
idxTrain = idx(1:numObservationsTrain);
idxTest = idx(numObservationsTrain+1:end);

%Partition the table of data into training, validation, and testing partitions using the indices.
dataTrain=data(idxTrain,:);
dataTest=data(idxTest,:);

%Define a network with a feature input layer and specify the number of features. Also, configure the input layer to normalize the data using Z-score normalization.
numFeatures=size(data,2) - 1;
numClasses=numel(classNames);
 
layers = [
    featureInputLayer(numFeatures,'Normalization', 'zscore')
    fullyConnectedLayer(50)
    batchNormalizationLayer
    reluLayer
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];

miniBatchSize = 16;

options = trainingOptions('adam', ...
    'MiniBatchSize',miniBatchSize, ...
    'Shuffle','every-epoch', ...
    'Plots','training-progress', ...
    'Verbose',false);

%Train the network using the architecture defined by layers, the training data, and the training options.
net = trainNetwork(dataTrain,layers,options);

%Predict the labels of the test data using the trained network and calculate the accuracy. The accuracy is the proportion of the labels that the network predicts correctly.
YPred = classify(net,dataTest,'MiniBatchSize',miniBatchSize);
YTest = dataTest{:,labelname};

%Prefromance Overall Accuracy
Overall_Accuracy = sum(YPred == YTest)/numel(YTest);
figure
confusionchart(YTest,YPred,'ColumnSummary','column-normalized',...
              'RowSummary','row-normalized','Title','Confusion Chart for LSTM');

when I run the code i get an error as " Unrecognized function or variable 'featureInputLayer'. ". I am using matlab 2020a

[Walter Roberson]

introduced in R2020b

[syed]

thank you