Need help on neural network train test and validation accuracy

Question

debasmita bhoumik 2016-8-28

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/301174-need-help-on-neural-network-train-test-and-validation-accuracy

编辑： Greg Heath 2016-9-1

My data set have 420 images(24 features each). there are 160 for train. 20 for validation. 240 for testing. my problem is, after writing this code am getting 100% accuracy which is absurd. plz help me in this matter as am not sure if my code is correct or not.

% Solve a Pattern Recognition Problem with a Neural Network
load('ftrmat420.mat'); %420 x 24
load('class_test.mat'); %1 x 420
x=transpose(ftrmat420);
t=class_test;
inputs = x
targets = t
% Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
% Set up Division of Data for Training, Validation, Testing
%net.divideParam.trainRatio = 30/100;
%net.divideParam.valRatio = 13/100;
%net.divideParam.testRatio = 57/100;
%[trainInd,valInd,testInd] = divideind(420,241:420,1:10,1:240);
net.divideFcn = 'divideind';
 net.divideParam.trainInd = 261:420;
net.divideParam.valInd   = 241:260;
 net.divideParam.testInd  = 1:240;
% Train the Network
[net,tr] = train(net,inputs,targets);
% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs)
performance = perform(net,targets,outputs)
% View the Network
view(net)
% Plots
% Uncomment these lines to enable various plots.
 figure, plotperform(tr)
 figure, plottrainstate(tr)
 figure, plotconfusion(targets,outputs)
[c,cm] = confusion(targets,outputs)
fprintf('Percentage Correct Classification   : %f%%\n', 100*(1-c));
fprintf('Percentage Incorrect Classification : %f%%\n', 100*c);
figure, ploterrhist(errors)
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)