训练卷积神经网络MATLAB - MATLAB爱好者论坛-LabFans.com

poster · 2019-12-06, 18:01

我在数据中有一行功能，在每一行数据的标签中都有一个不同的值...我的网络也给我同样的错误...这是我的代码。

%loading train and test data trainingData = load('train.mat'); trainData = trainingData.data; trainLabels = categorical(trainingData.labels); testingData = load('test.mat'); testData = testingData.data; testLabels = testingData.labels; % Define Network Architecture % Define the convolutional neural network architecture. layers = [ imageInputLayer([1 144 1]) % 22X1X1 refers to number of features per sample convolution2dLayer(3,16,'Padding','same') reluLayer fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer fullyConnectedLayer(2) % 2 refers to number of neurons in next output layer (number of output classes) softmaxLayer classificationLayer]; options = trainingOptions('sgdm',... 'MaxEpochs',500, ... 'Verbose',false,... 'Plots','training-progress'); %train the network net = trainNetwork(trainData,trainLabels,layers,options); %test the network predictedLabels = classify(net,trainD)' accuracy = sum(predictedLabels == testLabels)/numel(testLabels) 它给我这个错误

无效的训练数据。 X和Y必须具有相同数量的观察值。 convnet1d（第27行）中的错误net = trainNetwork（trainData，trainLabels。'，layers，options）;原因：使用nnet.internal.cnn.util.NetworkDataValidator / assertXAndYHaveSameNumberOfObservations时出错（第142行）无效的训练数据。 X和Y必须具有相同数量的观察值。

关于此的任何帮助。我有这个工作区...可能会帮助您了解数据的维度，请在此处输入图像描述

更多&回答...

2019-12-06, 18:01	#1
poster 高级会员注册日期: 2019-11-21 帖子: 3,006 声望力: 66	训练卷积神经网络MATLAB 我在数据中有一行功能，在每一行数据的标签中都有一个不同的值...我的网络也给我同样的错误...这是我的代码。 %loading train and test data trainingData = load('train.mat'); trainData = trainingData.data; trainLabels = categorical(trainingData.labels); testingData = load('test.mat'); testData = testingData.data; testLabels = testingData.labels; % Define Network Architecture % Define the convolutional neural network architecture. layers = [ imageInputLayer([1 144 1]) % 22X1X1 refers to number of features per sample convolution2dLayer(3,16,'Padding','same') reluLayer fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer fullyConnectedLayer(2) % 2 refers to number of neurons in next output layer (number of output classes) softmaxLayer classificationLayer]; options = trainingOptions('sgdm',... 'MaxEpochs',500, ... 'Verbose',false,... 'Plots','training-progress'); %train the network net = trainNetwork(trainData,trainLabels,layers,options); %test the network predictedLabels = classify(net,trainD)' accuracy = sum(predictedLabels == testLabels)/numel(testLabels) 它给我这个错误无效的训练数据。 X和Y必须具有相同数量的观察值。 convnet1d（第27行）中的错误net = trainNetwork（trainData，trainLabels。'，layers，options）;原因：使用nnet.internal.cnn.util.NetworkDataValidator / assertXAndYHaveSameNumberOfObservations时出错（第142行）无效的训练数据。 X和Y必须具有相同数量的观察值。关于此的任何帮助。我有这个工作区...可能会帮助您了解数据的维度，请在此处输入图像描述更多&回答...