How can I deploy a trained LSTM net on simulink to classify new data?

17 views (last 30 days)
Matthew Bigelow
Matthew Bigelow on 8 Oct 2018
Answered: Arkadiy Turevskiy on 18 Oct 2021
Have tried gensim and genfunction, they do not work on sequence nets. I have tried using classify(net,x)inside a user defined matlab function. This seems a little more promising however it gives the error stating that- net is not defined in the matlab function- when I try to start the simulation even though the net structure is open in the matlab workspace. Any ideas on how to do/get around this? Im a bit new at this and time is a bit of a factor for my project any help would be appreciated.
  1 Comment
Muhammad Faisal Khalid
Muhammad Faisal Khalid on 16 Oct 2021
Hi.
did you find the solution of the above problem as i am also facing this at the moment.

Sign in to comment.

Answers (1)

Arkadiy Turevskiy
Arkadiy Turevskiy on 18 Oct 2021
Hi,
We added a library of blocks to integrate deep learning networks into Simulink models starting with 20b. Support for LSTM and other recurrent networks was added in 21a.
To bring trained LSTM into a Simulink model, please use Stateful Classify block. In the block dialog specify .MAT file with your LSTM network.
See this example to help you.
All deep learning blocks are decribed here.
HTH.
Arkadiy

Community Treasure Hunt

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

Start Hunting!