Deep Learning Code Generation Fundamentals

Functions, objects, and workflows that you can use to generate code for deep learning networks

You can use MATLAB^® Coder™ with Deep Learning Toolbox™ to generate C++ code from a trained CNN. You can then deploy the generated code to an embedded platform that uses an Intel^® or ARM^® processor. You can also generate generic C or C++ code from a trained CNN that does not depend on any third-party libraries.

Functions

`codegen`	Generate C/C++ code from MATLAB code
`coder.loadDeepLearningNetwork`	Load deep learning network model
`coder.DeepLearningConfig`	Create deep learning code generation configuration objects
`coder.DeepLearningCodeConfig`	Parameters to configure deep learning code generation that does not depend on third-party libraries (Since R2021a)
`coder.ARMNEONConfig`	Parameters to configure deep learning code generation with the ARM Compute Library
`coder.CMSISNNConfig`	Parameters to configure deep learning code generation with the CMSIS-NN library for Cortex-M targets (Since R2022a)
`coder.MklDNNConfig`	Parameters to configure deep learning code generation with the Intel Math Kernel Library for Deep Neural Networks
`analyzeNetworkForCodegen`	Analyze deep learning network for code generation (Since R2022b)
`coder.regenerateDeepLearningParameters`	Regenerate files containing network learnables and states parameters (Since R2021b)

Topics

Prerequisites for Deep Learning with MATLAB Coder
Install products and configure environment for code generation for deep learning networks.
Workflow for Deep Learning Code Generation with MATLAB Coder
Generate code for prediction from a pretrained network.
Networks and Layers Supported for Code Generation
Choose a convolutional neural network that is supported for your target processor.
Analyze Network for Code Generation
Check code generation compatibility of a deep learning network.
Code Generation for dlarray
Use deep learning arrays in MATLAB code intended for code generation.
dlarray Limitations for Code Generation
Adhere to code generation limitations for deep learning arrays.
Load Pretrained Networks for Code Generation
Create a SeriesNetwork, DAGNetwork, yolov2ObjectDetector, ssdObjectDetector, or dlnetwork object for code generation.
Generate Generic C/C++ Code for Deep Learning Networks
Generate C/C++ code for prediction from a deep learning network that does not depend on third-party libraries.
Optimize C/C++ Code Performance for Deep Learning Applications without Deep Learning Libraries
Code generation configuration settings that optimize the performance of the generated C/C++ code for a deep learning network.
Code Generation for Deep Learning Networks with MKL-DNN
Generate C++ code for prediction from a deep learning network, targeting an Intel CPU.
Code Generation for Deep Learning Networks with ARM Compute Library
Generate C++ code for prediction from a deep learning network, targeting an ARM processor.
Cross-Compile Deep Learning Code That Uses ARM Compute Library
Generate library or executable code on host computer for deployment on ARM hardware target.
Generate int8 Code for Deep Learning Networks
Quantize and generate code for a pretrained convolutional neural network.
Generate bfloat16 Code for Deep Learning Networks
Perform learnables compression and generate C/C++ code in Brain Floating Point format, bfloat16.
Update Network Parameters After Code Generation
Perform post code generation updates of deep learning network parameters.

Related Information

Get Started with Deep Learning Toolbox (Deep Learning Toolbox)
Deep Learning with GPU Coder (GPU Coder)

Featured Examples

Generate Digit Images Using Variational Autoencoder on Intel CPUs

Generate code for a trained VAE dlnetwork to generate hand-drawn digits.

Open Live Script

Cross Compile Deep Learning Code for ARM Neon Targets

Generate library or executable code on host computer for deployment on ARM hardware target.

Open Live Script

Post-Code-Generation Update of Deep Learning Network Parameters

Incrementally update the network learnables of a deep learning network application running on edge devices such as Raspberry Pi. This example uses a cart-pole reinforcement learning application to illustrate:

Open Live Script