How to generate code from a trained LSTM network using MATLAB/Simulink?

Is code generation from a trained LSTM network supported, and if so, how? There appear to be different approaches to generate code from a trained LSTM network while working without/with Simulink.

Answer 1

[MathWorks Support Team]

1. Generate code from a trained LSTM network using MATLAB

In order to generate code from a trained LSTM network using MATLAB, there are different approaches:

(a) Generate C/C++ code using MATLAB Coder:

From MATLAB R2020a onwards, you can generate code for ARM Cortex-A CPUs. Refer to the blog post below on how to get started with deep learning models on ARM Cortex-A with MATLAB:

https://community.arm.com/arm-community-blogs/b/tools-software-ides-blog/posts/getting-started-with-deep-learning-models-on-arm-cortex-a-with-matlab

Another example is here: https://www.mathworks.com/help/coder/ug/code-generation-for-lstm-network-on-raspberry-pi.html

From MATLAB R2020b onwards, you can generate C++ code for an LSTM network, a stateful LSTM network, or a bidirectional LSTM network that uses the Intel® MKL-DNN library.

(b) Generate CUDA code using GPU Coder:

From R2019b onwards, you can generate code for NVIDIA GPUs. See the following documentation link for more information:

https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.lstmlayer.html#mw_a7799934-4908-476b-809d-1f063ef6a7fc

 

2. Generate code from a trained LSTM network using Simulink

From R2020b onwards, using MATLAB Coder or GPU Coder, you can use coder.loadDeepLearningNetwork and other associated functions to run inference in a MATLAB Function block. This will support accelerated simulation and code generation for both CPU or GPU targets. The following link illustrates the workflow:

https://www.mathworks.com/help/gpucoder/ug/deep-learning-in-simulink-by-using-gpu-coder.html