如何监控深度学习训练

Question

我想在训练发生的时候监控它，我应该如何修改我的代码？我找到了一些解释，她的https://se.mathworks.com/help/deeplearning/ug/monitor-deep-learning-training-progress.html，但我不能应用它，谁能帮帮忙吗？

[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));

Answer 1

我认为只有使用trainNetwork函数(net = trainNetwork(XTrain,YTrain,layers,options))才能做到这一点，不幸的是，fitcecoc中没有提供此选项。因此，您可以将训练数据和网络层以及选项发送到trainNetwork，以便为您绘制训练进度。请注意，为了绘制进度图，您还应该在选项中指定'training- progress‘作为'Plots’值，如以下代码中的最后一行所示：

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