试用软件

Is it possible to add a second source of data in the lstm ?

1 次查看（过去 30 天）

显示更早的评论

aryan ramesh 2022-2-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1645790-is-it-possible-to-add-a-second-source-of-data-in-the-lstm

评论： aryan ramesh 2022-2-18

在 MATLAB Online 中打开

Is there a way to use the train Network or any other function in the lstm to add a second source of data?

For Example:

net1 =  trainNetwork(XTrain, XTrain2, labelTrain, labelTrain2, layers, options );
layers = [ ...
    sequenceInputLayer(1)
    bilstmLayer(100,"OutputMode","sequence", XTrain2, labelTrain2)
    dropoutLayer(0.2)
    bilstmLayer(90,"OutputMode","last", XTrain2, labelTrain2)
    dropoutLayer(0.2)
    batchNormalizationLayer
    fullyConnectedLayer(2)
    softmaxLayer
    classificationLayer];

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

yanqi liu 2022-2-10

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1645790-is-it-possible-to-add-a-second-source-of-data-in-the-lstm#answer_892660

yes，sir，may be use combine to make multi data to one object

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

aryan ramesh 2022-2-18

I was wondering if matlab has input flexibility like in keras functional API

visible1 = Input(shape=(n_steps, n_features))

cnn1 = Conv1D(filters=64, kernel_size=2, activation=‘relu’)(visible1)

cnn1 = MaxPooling1D(pool_size=2)(cnn1)

请先登录，再进行评论。

请先登录，再回答此问题。

类别

AI, Data Science, and Statistics Deep Learning Toolbox Automatic Differentiation Custom Training Loops

在 Help Center 和 File Exchange 中查找有关 Custom Training Loops 的更多信息

标签

产品

MATLAB

版本

R2021a

Community Treasure Hunt

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

Translated by

试用软件