How to divide my dataset into validation and test set in deep networks with Auto-Encoders?

i am using this example

http://www.mathworks.com/help/nnet/ug/construct-deep-network-using-autoencoders.html#nnet-ex20671592

i want to divide data like this but its not working

% Setup Division of Data for Training, Validation, Testing

net.divideParam.trainRatio = 80/100;

net.divideParam.valRatio = 15/100;

net.divideParam.testRatio = 15/100;

[mizuki]

What is the error you get? or what is "not working" exactly?

It seems that 80+15+15=110, so the ratio of training, validation and test data becomes 0.8/1.1=0.727, 0.15/1.1=0.136 and 0.136.

[Machine Learning Enthusiast]

sorry.I replace 80 with 70 in training.So,total 70+15+15=100

i want to implement this division in above example(link),but still its not working.I am trying to get this kind of Confusion Matrix(as shown in figure).

I will be grateful if you share your email.I want to discuss with you. thank you

Answer 1

[Richard Palmer]

Your percentages do not add up to 1.

[Machine Learning Enthusiast]

I replace 80 with 70 in training.So,total 70+15+15=100. Still not working