Generazione di codice CPU dalle applicazioni MATLAB

Generare codice C/C++ per la distribuzione su target desktop o integrati

Utilizzare una combinazione di MATLAB^® Coder™, Simulink^® Coder e Embedded Coder^® insieme a Deep Learning Toolbox™ per generare codice CPU MEX o autonomo da eseguire su target desktop o integrati. È possibile distribuire il codice autonomo che utilizza la libreria Intel^® MKL-DNN o la libreria ARM^® Calcola. In alternativa, è possibile generare codice CPU generico che non richiama funzioni di libreria di terze parti. È inoltre possibile generare e distribuire codice che utilizza i modelli TensorFlow™ Lite per eseguire l’inferenza.

Funzioni

`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 (Da R2023a)
`coder.DeepLearningConfig`	Create deep learning code generation configuration objects
`loadTFLiteModel`	Load TensorFlow Lite model (Da R2022a)
`predict`	Compute deep learning network output for inference by using a TensorFlow Lite model (Da R2022a)
`TFLiteModel`	TensorFlow Lite model (Da R2022a)

App

MATLAB Coder

Generate C code or MEX function from MATLAB code

Argomenti

Panoramica

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 a SeriesNetwork, DAGNetwork, yolov2ObjectDetector, ssdObjectDetector, or dlnetwork 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.

Applicazioni

Code Generation for Deep Learning on ARM Targets
This example shows how to generate and deploy code for prediction on an ARM®-based device without using a hardware support package.
Deep Learning Prediction with ARM Compute Using codegen
This example shows how to use codegen 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.