Problem with Multivariate LSTM Forecasting

3 次查看（过去 30 天）

Mohamed Nedal 2020-4-7

评论： Ehsan Kamjoo 2021-1-12

Hello,

Kindly check the attached code with a data workspace example.

I would like to implement an LSTM network that forecasts an output (the last column) by means of 7 inputs.

When I run the code I get this error:

Error using trainNetwork (line 170)

To RESHAPE the number of elements must not change.

Error in multi_lstmOMNI_noStand2 (line 46)

net = trainNetwork(XTrain,YTrain,layers,options);

Caused by:

Error using reshape

To RESHAPE the number of elements must not change.

I would like to know how to fix it and how to proceed the prediction for any defined time step.

If you have also any suggestion to improve the code that would be great.

I'm still a novice with this. If you could help that would be much appreciated.

Thank you!

Ehsan Kamjoo 2021-1-12

Hi,

Have you found the answer? I have the same problem.

Thank you,

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

R2019b

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

Translated by