My input features for LSTM are different dimension, Is it possible to combine and train the network

4 次查看（过去 30 天）

显示更早的评论

Manoj Devaraju 2022-5-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1724415-my-input-features-for-lstm-are-different-dimension-is-it-possible-to-combine-and-train-the-network

评论： Manoj Devaraju 2022-5-26

采纳的回答： Hiro Yoshino

I have 6 input features for trining the LSTM network, but 1st coloumn has 2x28(contain 2 feature of 28 length) cells by 100 and all four are 1x100 each, Is it possible to combine all the feature and give it to network. since for LSTM we are using (sequenceInputLayer(N)) as input layer. Is there any alternate solution to this.

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。

采纳的回答

Hiro Yoshino 2022-5-24

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1724415-my-input-features-for-lstm-are-different-dimension-is-it-possible-to-combine-and-train-the-network#answer_970540

No, you cannot do that I think.

Why don't you conver the singular values into series data by using remat and put them under the 2x28 series data so you can use LSTM?

Another way to do this is creating a network with multi-inputs.

see: https://www.mathworks.com/help/deeplearning/ug/train-network-on-image-and-feature-data.html

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Manoj Devaraju 2022-5-26

Thank you so much for your response. I have tried first approach you mentioned worked well.

but creating a network with multi input, I tried to create but failed.

Can you please show me how to create multi-inputs network for my problem.

请先登录，再进行评论。

更多回答（0 个）

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox Sequence and Numeric Feature Data Workflows

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

标签

产品

MATLAB

版本

R2021b

Community Treasure Hunt

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

Translated by