Main Content

CPU Code Generation from MATLAB Applications

Generate C/C++ code for deployment on desktop or embedded targets

Use a combination of MATLAB® Coder™, Simulink® Coder, and Embedded Coder® together with Deep Learning Toolbox™ to generate MEX or standalone CPU code that runs on desktop or embedded targets. You can deploy the generated standalone code that uses the Intel® MKL-DNN library or the ARM® Compute library. Alternatively, you can generate generic CPU code that does not call third-party library functions. You can also generate and deploy code that uses TensorFlow™ Lite models to perform inference.


codegenGenerate C/C++ code from MATLAB code
coder.getDeepLearningLayersGet the list of layers supported for code generation for a specific deep learning library
coder.loadDeepLearningNetworkLoad deep learning network model
coder.loadNetworkDistributionDiscriminatorLoad network distribution discriminator for code generation (Since R2023a)
coder.DeepLearningConfigCreate deep learning code generation configuration objects
loadTFLiteModelLoad TensorFlow Lite model (Since R2022a)
predictCompute deep learning network output for inference by using a TensorFlow Lite model (Since R2022a)
TFLiteModelTensorFlow Lite model (Since R2022a)


MATLAB CoderGenerate C code or MEX function from MATLAB code