How to save the best model during neural network training?

38 次查看（过去 30 天）
wanting wang
wanting wang 2022-10-21
回答： Antoni Woss 2022-10-21
During the NN training there is multiple validation, in some of the epoch the validation accuracy is high. However, maybe due to the overfitting the val accuracy drops after more training. How do I save the model which have the best validation accuracy?
  2 个评论
wanting wang
wanting wang 2022-10-21
layers = [ ...
sequenceInputLayer(inputSize)
bilstmLayer(numHiddenUnits,'OutputMode','last')
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer];
maxEpochs = 200;
miniBatchSize = 20;
options = trainingOptions('adam', ...
'ExecutionEnvironment','cpu', ...
'GradientThreshold',1, ...
'MaxEpochs',maxEpochs, ...
'ValidationData',{XVal,YVal}, ...
'ValidationFrequency',30, ...
'MiniBatchSize',miniBatchSize, ...
'SequenceLength','longest', ...
'Shuffle','every-epoch', ...
'Verbose',0, ...
'Plots','none');
[net,info] = trainNetwork(XTrain,YTrain,layers,options);
That is how I construct my neural network. It end up with a output net trained after 200epoch. However, sometimes I got an ideal model with fine training accracy and high validation accuracy at around 150 or 160 epochs, I want to save that model rather than 200-epoch overfitting model.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Antoni Woss
Antoni Woss 2022-10-21
You can choose to return the network with the optimal validation accuracy by specifying the 'OutputNetwork' name-value argument with the value 'best-validation-loss'. This will return the network corresponding to the training iteration with the lowest validation loss.
For more information on the validation options, take a look at the following documentation page: https://www.mathworks.com/help/deeplearning/ref/trainingoptions.html

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by