Hi everyone , i have LSTM trained model (time series sequence) which i want to load in my simulink model. how can i proceed with it. any help please

2 views (last 30 days)
Hi everyone , i have LSTM trained model (time series sequence) which i want to load in my simulink model.
how can i proceed with it. any help please

Answers (1)

Cris LaPierre
Cris LaPierre on 26 May 2024
Edited: Cris LaPierre on 26 May 2024
Train your network in MATLAB, then perform inference with it in Simulink using the predict block from the Deep Learning Blockset.
You can see an example here and a video tutorial here. You do need to be on at least R2020b..
  2 Comments
nes
nes on 26 May 2024
thank you for your replay , i want to add something my LSTM model is to classify signal so first i load the trained model using stateful predict then do my classification conditions ? or just i use stateful classify
when i use stateful classify the code of classification must be written in the same code of the LSTM or separately . thank you
Cris LaPierre
Cris LaPierre on 26 May 2024
I would just use predict, not stateful predict. What the model does is determined when you train it. See this example about using an LSTM to classify (label) a sequence.

Sign in to comment.

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!