如何监控深度学习训练答案

【问题标题】：How to monitor deep learning training如何监控深度学习训练
【发布时间】：2020-04-13 16:20:17
【问题描述】：

我想在培训发生时对其进行监控，我应该如何更改我的代码？我找到了她https://se.mathworks.com/help/deeplearning/ug/monitor-deep-learning-training-progress.html 的一些解释，但我无法应用它，有人可以帮忙吗？


[trainingSet,testSet] = splitEachLabel(imds,0.3,'randomize');
imageSize = net.Layers(1).InputSize; 
augmentedTrainingSet = augmentedImageDatastore(imageSize,...
    trainingSet,'ColorPreprocessing','gray2rgb'); 
augmentedTestSet = augmentedImageDatastore(imageSize,...
    testSet,'ColorPreprocessing','gray2rgb');
w1 = net.Layers(2).Weights;
w1 = mat2gray(w1); 
featureLayer = 'fc1000'; 
trainingFeatures = activations(net,augmentedTrainingSet,...
    featureLayer,'MiniBatchSize',32,'OutputAs','columns');
trainingLables = trainingSet.Labels;
classifier=fitcecoc(trainingFeatures,...
    trainingLables,'Learner','Linear','Coding','onevsall','ObservationsIn','columns');
testFeature = activations(net,augmentedTestSet,...
    featureLayer,'MiniBatchSize',32,'OutputAs','columns');
predictLabels = predict(classifier, testFeature,'ObservationsIn','columns');
testLables = testSet.Labels; 
confMat = confusionmat(testLables , predictLabels);
confMat = bsxfun(@rdivide , confMat , sum(confMat,2));
mean(diag(confMat));

【问题讨论】：

标签： matlab deep-learning

【解决方案1】：

我认为这只能使用 trainNetwork 函数 (net = trainNetwork(XTrain,YTrain,layers,options)) 才能实现，不幸的是 fitcecoc 中没有提供此选项。因此，您可以改为发送您的训练数据和网络层以及 trainNetwork 选项来为您绘制训练进度。请注意，为了绘制进度，您还应该将“training-progress”指定为选项中的“Plots”值，如以下代码中的最后一行所示，例如：

options = trainingOptions('sgdm', ...
    'MaxEpochs',8, ...
    'ValidationData',{XValidation,YValidation}, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');

【讨论】：