使用 MATLAB Coder 进行深度学习

生成用于深度学习神经网络的 C++ 代码（需要 Deep Learning Toolbox™）

深度学习是机器学习的一个分支，它教导计算机像人类一样自然而然地做事情：从经验中学习。学习算法使用计算方法直接从数据“学习”信息，而不依赖预先确定的方程作为模型。深度学习使用卷积神经网络 (CNN) 直接从图像中学习有用的数据表示。

您可以将 MATLAB^® Coder™ 与 Deep Learning Toolbox 结合使用，从经过训练的 CNN 生成 C++ 代码。然后您可以将生成的代码部署到使用 Intel^® 或 ARM^® 处理器的嵌入式平台。您还可以从不依赖任何第三方库的经过训练的 CNN 生成泛型 C 或 C++ 代码。

MATLAB Online™ 不支持在深度学习中使用 MATLAB Coder。

函数

`codegen`	从 MATLAB 代码生成 C/C++ 代码。
`coder.loadDeepLearningNetwork`	Load deep learning network model
`coder.DeepLearningConfig`	Create deep learning code generation configuration objects
`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
`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
`coder.regenerateDeepLearningParameters`	Regenerate files containing network learnables and states parameters

主题

使用 MATLAB Coder 进行深度学习的前提条件
为用于深度学习网络的代码生成安装相关产品并配置环境。
Workflow for Deep Learning Code Generation with MATLAB Coder
Generate code for prediction from a pretrained network.
代码生成支持的网络和层
选择目标处理器支持的卷积神经网络。
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.
加载预训练网络以用于代码生成
创建 SeriesNetwork、DAGNetwork、yolov2ObjectDetector、ssdObjectDetector 或 dlnetwork 对象以用于代码生成。
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 any third-party libraries.
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.
Update Network Parameters After Code Generation
Perform post code generation updates of deep learning network parameters.

精选示例

Deep Learning Code Generation on Intel Targets for Different Batch Sizes

Generate code for deep learning networks, targeting an Intel processor.

打开脚本

Generate Digit Images Using Variational Autoencoder on Intel CPUs

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

打开实时脚本

Code Generation for Deep Learning on ARM Targets

Code generation with ARM Compute Library when you do not have a hardware support package.

打开脚本

Deep Learning Prediction with ARM Compute Using codegen

Generate code for deep learning networks, targeting an ARM processor.

打开脚本

Code Generation and Deployment of MobileNet-v2 Network to Raspberry Pi

Use the MobileNet-V2 network for object prediction on external hardware.

打开脚本

Generate C++ Code for Object Detection Using YOLO v2 and Intel MKL-DNN

Generate code for object detection on an Intel CPU.

打开脚本

Code Generation for Semantic Segmentation Application on Intel CPUs That Uses U-Net

Generate a MEX function that performs image segmentation by using the deep learning network U-Net on Intel CPUs.

打开脚本

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.

打开实时脚本

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.

打开实时脚本

Code Generation for LSTM Network That Uses Intel MKL-DNN

Generate code for a pretrained LSTM network that makes predictions for each step of an input timeseries.

打开实时脚本

Code Generation for Convolutional LSTM Network That Uses Intel MKL-DNN

Generate a MEX function for a deep learning network containing both convolutional and BiLSTM layers that classifies videos

打开实时脚本

Cross Compile Deep Learning Code for ARM Neon Targets

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

打开实时脚本

Generate INT8 Code for Deep Learning Network on Raspberry Pi

Generate code for deep learning network that performs inference computations in 8-bit integers.

打开实时脚本

Generate INT8 Code for Deep Learning Network on Cortex-M Target

Generate code for deep learning network that performs inference computations in 8-bit integers.

打开实时脚本

Generate Generic C/C++ Code for Sequence-to-Sequence Regression That Uses Deep Learning

Generate C/C++ code for a trained CNN that does not depend on any third-party libraries.

打开实时脚本

Generate Code for LSTM Network and Deploy on Cortex-M Target

Generate a Processor-In-the-Loop (PIL) executable that runs on an STM32F746G-Discovery board.

打开实时脚本

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:

打开实时脚本