I want to train my recognition system with the feature dataset that I have created.
There are 9 inputs (features) and 40 targets (classes)
inputs and targets are on the same matrix. The first 9 columns are the features and the remaining 40 columns are the outputs
I have written this code below:
load dataSet.mat;
inputs = featureSet(:,1:9)';
targets = featureSet(:,10:49)';
% Create a Pattern Recognition Network
hiddenLayerSize = ns;
net = patternnet(hiddenLayerSize);
net.divideParam.trainRatio = trRa/100;
net.divideParam.valRatio = vaRa/100;
net.divideParam.testRatio = teRa/100;
% Train the Network
[net,tr] = train(net,inputs,targets);
% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs);
% Recalculate Training, Validation and Test Performance
trainTargets = targets .* tr.trainMask{1};
valTargets = targets .* tr.valMask{1};
testTargets = targets .* tr.testMask{1};
trainPerformance = perform(net,trainTargets,outputs);
valPerformance = perform(net,valTargets,outputs);
testPerformance = perform(net,testTargets,outputs);
I have copied this code from my previous working character recognition application. There is only two differences from the former application: input count and target count.
After starting training GUI window of nntraintool opens and no action is observed. Additionally, I get message at the bottom says "Performance goal met."
What could be the reason?
