MATLAB实现堆叠LSTM（含代码）

最新推荐文章于 2024-08-25 19:11:32 发布

confitee

最新推荐文章于 2024-08-25 19:11:32 发布

阅读量1.4k

点赞数 1

文章标签： lstm 人工智能 rnn Powered by 金山文档

原文链接：https://www.mathworks.com/help/releases/R2022a/deeplearning/ref/nnet.cnn.layer.lstmlayer.html

版权

通过在 LSTM 层之前插入具有输出模式的额外 LSTM 层来使 LSTM 网络更深。为防止过度拟合，可以在 LSTM 图层之后插入辍学图层。'sequence'

对于序列到标签分类网络，最后一个 LSTM 图层的输出模式必须为。'last'

numFeatures = 12;
numHiddenUnits1 = 125;
numHiddenUnits2 = 100;
numClasses = 9;
layers = [ ...
    sequenceInputLayer(numFeatures)
    lstmLayer(numHiddenUnits1,'OutputMode','sequence')
    dropoutLayer(0.2)
    lstmLayer(numHiddenUnits2,'OutputMode','last')
    dropoutLayer(0.2)
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];

对于序列到序列分类网络，最后一个 LSTM 层的输出模式必须为。'sequence'

numFeatures = 12;
numHiddenUnits1 = 125;
numHiddenUnits2 = 100;
numClasses = 9;
layers = [ ...
    sequenceInputLayer(numFeatures)
    lstmLayer(numHiddenUnits1,'OutputMode','sequence')
    dropoutLayer(0.2)
    lstmLayer(numHiddenUnits2,'OutputMode','sequence')
    dropoutLayer(0.2)
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];