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.
Functions
codegen | Generate C/C++ code from MATLAB code |
coder.getDeepLearningLayers | Get the list of layers supported for code generation for a specific deep learning library |
coder.loadDeepLearningNetwork | Load deep learning network model |
coder.loadNetworkDistributionDiscriminator | Load network distribution discriminator for code generation (Since R2023a) |
coder.DeepLearningConfig | Create deep learning code generation configuration objects |
loadTFLiteModel | Load TensorFlow Lite model (Since R2022a) |
predict | Compute deep learning network output for inference by using a TensorFlow Lite model (Since R2022a) |
TFLiteModel | TensorFlow Lite model (Since R2022a) |
Apps
MATLAB Coder | Generate C code or MEX function from MATLAB code |
Topics
Overview
- Networks and Layers Supported for Code Generation (MATLAB Coder)
Choose a convolutional neural network that is supported for your target processor. - Load Pretrained Networks for Code Generation (MATLAB Coder)
Create aSeriesNetwork
,DAGNetwork
,yolov2ObjectDetector
,ssdObjectDetector
, ordlnetwork
object for code generation. - Code Generation for dlarray (MATLAB Coder)
Use deep learning arrays in MATLAB code intended for code generation. - Generate Digit Images Using Variational Autoencoder on Intel CPUs (MATLAB Coder)
Generate code for a trained VAE dlnetwork to generate hand-drawn digits. - Prerequisites for Deep Learning with TensorFlow Lite Models
Install products and configure environment for simulation and code generation with TensorFlow Lite models.
Applications
- Generate Code and Deploy SqueezeNet Network to Raspberry Pi
This example shows how to generate C code that does not depend on any third-party deep learning libraries for pretrained SqueezeNet network. - Deep Learning Prediction with ARM Compute Using codegen
This example shows how to usecodegen
to generate code for a logo classification application that uses deep learning on ARM® processors. - Generate Code for a Deep Learning Network for x86-64 Platforms Using Advanced Vector Instructions
This example shows how to generate code that uses advanced vector instructions and implements an image classification algorithm. - Generate C++ Code for Object Detection Using YOLO v2 and Intel MKL-DNN
This example shows how to generate C++ code for the YOLO v2 Object detection network on an Intel® processor. - Deploy Signal Classifier Using Wavelets and Deep Learning on Raspberry Pi
Classify human electrocardiogram signals on a Raspberry Pi® using scalograms and a deep convolutional neural network. - Deploy Signal Segmentation Deep Network on Raspberry Pi
Generate a MEX function and a standalone executable to perform waveform segmentation on a Raspberry Pi. - Generate Code and Deploy MobileNet-v2 Network to Raspberry Pi
This example shows how to generate C code that does not depend on any third-party deep learning libraries for pretrained MobileNet-v2 network. - Code Generation for Semantic Segmentation Application on ARM Neon Targets That Uses U-Net
Generate a static library that performs image segmentation by using the deep learning network U-Net on ARM targets. - Code Generation for LSTM Network on Raspberry Pi
Generate code for a pretrained long short-term memory network to predict Remaining Useful Life (RUI) of a machine. - Code Generation for LSTM Network That Classifies Text Data
Generate code for a pretrained LSTM network that makes predictions for each step of an input timeseries. - Cross Compile Deep Learning Code for ARM Neon Targets
Generate library or executable code on host computer for deployment on ARM hardware target. - Generate INT8 Code for Deep Learning Network on Raspberry Pi (MATLAB Coder)
Generate code for deep learning network that performs inference computations in 8-bit integers. - Generate Generic C Code for Sequence-to-Sequence Regression Using Deep Learning
Generate C/C++ code for a trained CNN that does not depend on any third-party libraries. - Generate Code for LSTM Network and Deploy on Cortex-M Target (MATLAB Coder)
Generate a Processor-In-the-Loop (PIL) executable that runs on an STM32F746G-Discovery board. - Generate Code for TensorFlow Lite (TFLite) Model and Deploy on Raspberry Pi
Generate code that uses a TensorFlow Lite model for inference. - Deploy Classification Application Using Mobilenet-V3 TensorFlow Lite Model on Host and Raspberry Pi
Generate code for a classification segmentation application that uses Tensorflow Lite model. - Deploy Semantic Segmentation Application Using TensorFlow Lite Model on Host and Raspberry Pi
Generate code for an image segmentation application that uses Tensorflow Lite model. - Deploy Super Resolution Application That Uses TensorFlow Lite (TFLite) Model on Host and Raspberry Pi
Generate code for a super resolution application that uses a TFLite model for inference. - Deploy Pose Estimation Application Using TensorFlow Lite Model (TFLite) Model on Host and Raspberry Pi
Simulate and generate code for a TensorFlow Lite model for 2D human pose estimation.