Testing Neural Network after training data.

Question

MILLER BIGGELAAR 2022-8-20

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1782360-testing-neural-network-after-training-data

回答： Image Analyst 2022-8-20

Hello lovely Mathworks team. :)

I have trained a competitive neural network using the competlayer() function, the network is to classify Iris plants (I know there are examples in Mathworks about this, but it for an assignment), I have allocated 50 out of the 150 sequences to be the training data, leaving 100 to test.

I am unsure how to test the network after training it, below is my code!

clear
clc
test                = Iris_data;
label               = zeros(150,1);
label(1:50,:)       = 1;
label(51:100,:)     = 2
label(101:150,:)    = 3;
test(:,5)           = label;
k                   = randperm(150,50);
trainset                = test(k(1:50),:);
trainsetlabel           = test(k,5);
test(k,:)           = [];
datalabel           = test(:,5);
test                = test(:,1:4);
%%%%
compnet             = competlayer(3);
compnet             = train(compnet,trainset);
outputs             = compnet(test)

On the final line I receive an error >>>>

Error using network/sim

Input data sizes do not match net.inputs{1}.size.

It seems to me that the network doesn't like data unless it is the same size as the training set? If you could help figure out how to run my test data that would be greatly appreciated.

Thanks,

Miller