Matlab：神经网络训练的问题

Question

我正在尝试使用nprtool训练神经网络，并且还手动调用newpr和train方法。 我使用面向行的样本，而不是默认为列：

使用nprtool没有问题，但是当我调用自动生成的M文件时，输出是：

??? Error using ==> network.train at 145
Targets are incorrectly sized for network.
Matrix must have 24 columns.

Error in ==> create_pr_net at 29
[net,tr] = train(net,inputs,targets);

我的输入是140x24，我的目标是140x3。

Matlab生成的代码是：

function net = create_pr_net(inputs,targets)
%CREATE_PR_NET Creates and trains a pattern recognition neural network.
%
%  NET = CREATE_PR_NET(INPUTS,TARGETS) takes these arguments:
%    INPUTS - RxQ matrix of Q R-element input samples
%    TARGETS - SxQ matrix of Q S-element associated target samples, where
%      each column contains a single 1, with all other elements set to 0.
%  and returns these results:
%    NET - The trained neural network
%
%  For example, to solve the Iris dataset problem with this function:
%
%    load iris_dataset
%    net = create_pr_net(irisInputs,irisTargets);
%    irisOutputs = sim(net,irisInputs);
%
%  To reproduce the results you obtained in NPRTOOL:
%
%    net = create_pr_net(inputs,targets);

% Create Network
numHiddenNeurons = 2000;  % Adjust as desired
net = newpr(inputs,targets,numHiddenNeurons);
net.divideParam.trainRatio = 90/100;  % Adjust as desired
net.divideParam.valRatio = 5/100;  % Adjust as desired
net.divideParam.testRatio = 5/100;  % Adjust as desired

% Train and Apply Network
[net,tr] = train(net,inputs,targets);
outputs = sim(net,inputs);

% Plot
plotperf(tr)
plotconfusion(targets,outputs)

我正在使用Matlab R2010a。

感谢。

Answer 1

如Matlab帮助文件中所述：

INPUTS - Q R元素输入样本的RxQ矩阵 TARGETS - Q S元素相关目标样本的SxQ矩阵

在手动调用Matlab训练函数之前，您可能需要输入和目标矩阵的转置。

Input = Input';和 Taget = Target';