从 MATLAB 应用生成 CPU 代码

生成用于在桌面或嵌入式目标上部署的 C/C++ 代码

将 MATLAB^® Coder™、Simulink^® Coder 和 Embedded Coder^® 的组合与 Deep Learning Toolbox™ 结合使用，以生成在桌面或嵌入式目标上运行的 MEX 或独立 CPU 代码。您可以部署生成的使用 Intel^® MKL-DNN 库或 ARM^® Compute 库的独立代码。您也可以生成不调用第三方库函数的泛型 CPU 代码。您还可以生成和部署使用 TensorFlow™ Lite 模型来执行推断的代码。

函数

`codegen`	从 MATLAB 代码生成 C/C++ 代码。
`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 (自 R2023a 起)
`coder.DeepLearningConfig`	Create deep learning code generation configuration objects
`loadTFLiteModel`	Load TensorFlow Lite model (自 R2022a 起)
`predict`	Compute deep learning network output for inference by using a TensorFlow Lite model (自 R2022a 起)
`TFLiteModel`	TensorFlow Lite model (自 R2022a 起)

App

MATLAB Coder

从 MATLAB 代码生成 C 代码或 MEX 函数

主题

概述

代码生成支持的网络和层 (MATLAB Coder)
选择目标处理器支持的卷积神经网络。
加载预训练网络以用于代码生成 (MATLAB Coder)
创建 SeriesNetwork、DAGNetwork、yolov2ObjectDetector、ssdObjectDetector 或 dlnetwork 对象以用于代码生成。
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.

应用

ARM 目标上的深度学习代码生成
此示例说明如何在不使用硬件支持包的情况下，在基于 ARM® 的设备上为预测生成和部署代码。
通过 ARM 计算使用 codegen 进行深度学习预测
此示例说明如何使用 codegen 为在 ARM® 处理器上使用深度学习的徽标分类应用程序生成代码。徽标分类应用程序使用 LogoNet 串行网络从图像中执行徽标识别。生成的代码利用 ARM Compute Library 进行计算机视觉和机器学习。
针对不同批量大小在 Intel 目标上进行深度学习代码生成
此示例说明如何使用 codegen 命令为在 Intel® 处理器上使用深度学习的图像分类应用程序生成代码。生成的代码使用了用于深度神经网络的 Intel 数学核心函数库 (MKL-DNN)。此示例由两部分组成：
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.

从 MATLAB 应用生成 CPU 代码

函数

App

主题

概述

应用

WeChat