Deep Learning withGPU Coder

Generate CUDA^®深度学习神经网络代码

深度学习是机器学习的一个分支，它教会计算机去做人类自然而然的事情：从经验中学习。学习算法使用计算方法直接从数据中“学习”信息，而无需依赖预定方程作为模型。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。神经网络结合了多个非线性加工层，使用并行运行的简单元素受到生物神经系统的启发。深度学习模型是通过使用大量标记的数据和包含许多层的神经网络体系结构（通常包括一些卷积层）来培训的。

You can use GPU Coder™ in tandem with the Deep Learning Toolbox™ to generate code and deploy CNN on multiple embedded platforms that use NVIDIA^®或手臂^®GPU处理器。深度学习工具箱提供简单的MATLAB^®创建和互连深神经网络层的命令。预验证的网络的可用性和诸如图像识别和驱动程序帮助应用程序之类的示例使您可以使用GPU编码器进行深度学习，而无需有关神经网络，深度学习或高级计算机视觉算法的专业知识。

Apps

expand all

GPU Coder

GPU Coder	Generate GPU code fromMATLAB代码
GPU Environment Check	Verify and set up GPU code generation environment

Functions

expand all

Code Generation

`代码gen`	Generate C/C++ code fromMATLAB代码
`cnncodegen`	Generate code for a deep learning network to target theARMMali GPU
`代码r.loadDeepLearningNetwork`	加载深度学习网络模型
`coder.deeplearningconfig`	Create deep learning code generation configuration objects
`Coder.getDeeplearninglayers`	获取为特定深度学习库的代码生成支持的层列表万博1manbetx
`代码r.regenerateDeepLearningParameters`	Regenerate files containing network learnables and states parameters

Objects

expand all

Code Configuration

`Coder.CudnnConfig`	Parameters to configure deep learning code generation with theCUDA深神经网络图书馆
`代码r.TensorRTConfig`	Parameters to configure deep learning code generation with theNVIDIATensorRT library
`代码r.gpuConfig`	Configuration parameters forCUDA代码generation fromMATLAB使用代码GPU Coder
`代码r.gpuEnvConfig`	创建包含传递给参数的配置对象`Coder.CheckgPuinstall`用于执行GPU代码生成环境检查

Model Settings

expand all

Basics

Deep Learning in MATLAB(Deep Learning Toolbox)

Discover deep learning capabilities in MATLAB using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.

了解卷积神经网络(Deep Learning Toolbox)

卷积神经网络及其在MATLAB中的工作方式。

预处理的深神经网络(Deep Learning Toolbox)

Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.

Training

图像深度学习(Deep Learning Toolbox)

训练卷积神经网络从头开始或使用预审预告片来快速学习新任务

Code Generation Overview

Workflow

Overview of CUDA code generation workflow for convolutional neural networks.

Supported Networks, Layers, and Classes

为代码生成的网络，层和类。万博1manbetx

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.

Generated CNN Class Hierarchy

Architecture of the generated CNN class and its methods.

Topics

MATLAB

Load Pretrained Networks for Code Generation
Create aSeriesNetwork,DAGNetwork,yolov2ObjectDetector,ssdObjectDetector, ordlnetworkobject for code generation.
深度学习网络的代码生成by Using cuDNN
Generate code for pretrained convolutional neural networks by using the cuDNN library.
深度学习网络的代码生成by Using TensorRT
Generate code for pretrained convolutional neural networks by using the TensorRT library.
深度学习网络的代码生成Targeting ARM Mali GPUs
Generate C++ code for prediction from a deep learning network targeting an ARM Mali GPU processor.
Update Network Parameters After Code Generation
Perform post code generation updates of deep learning network parameters.
深度学习中的数据布局注意事项
Fundamental data layout considerations for authoring example main functions.
Quantization of Deep Neural Networks
Understand effects of quantization and how to visualize dynamic ranges of network convolution layers.
Generate INT8 Code for Deep Learning Networks
Quantize and generate code for a pretrained convolutional neural network.
Lane Detection Optimized with GPU Coder
Develop a deep learning lane detection application that runs on NVIDIA GPUs.
交通标志检测和识别
Generate CUDA MEX for a traffic sign detection and recognition application that uses deep learning.
Logo Recognition Network
Generate code and classify an input image into 32 logo categories.
代码生成的语义分割网络That Uses U-net
Generate CUDA code for the U-Net deep learning network for image segmentation.
代码生成的语义分割网络
Code generation for theSegNetimage segmentation network.
代码生成深度神经网络的代码
Generate CUDA MEX from MATLAB code and denoise grayscale images by using the denoising convolutional neural network.

万博1manbetx

GPU Code Generation for Deep Learning Networks Using MATLAB Function Block
Simulate and generate code for deep learning models in Simulink using MATLAB function blocks.
GPU Code Generation for Blocks from the Deep Neural Networks Library
Simulate and generate code for deep learning models in Simulink using library blocks.
靶向NVIDIA嵌入式板
构建并部署到NVIDIA GPU板。

Related Information

Deep Learning with MATLAB Coder

Featured Examples

深度学习网络的代码生成

Get started with CUDA code generation for image classification networks such asMobileNet-v2,ResNet，和Googlenet.

打开实时脚本

Generate Digit Images on NVIDIA GPU Using Variational Autoencoder

CUDA code generation fordlnetwork和dlarrayobjects.

打开实时脚本

Train and Deploy Fully Convolutional Networks for Semantic Segmentation

将完全卷积的语义分割网络训练并部署到NVIDIA GPU。

打开实时脚本

通过使用nvidia tensorrt进行深度学习预测

Generate a CUDA MEX file that performs 32-bit, 16-bit floating point , and 8-bit integer prediction using TensorRT.

打开实时脚本

Code Generation for Object Detection by Using YOLO v2

Generate CUDA MEX for a you only look once (YOLO) v2 object detector.

打开实时脚本

Code Generation for Object Detection by Using Single Shot Multibox Detector

Generate CUDA code for a singleshot multibox vehicle detector network.

打开实时脚本

Deep Learning Prediction on ARM Mali GPU

将图像分类应用程序部署到ARM MALI GPU。

打开实时脚本

Code Generation for a Sequence-to-Sequence LSTM Network

Demonstrates how to generate CUDA® code for a long short-term memory (LSTM) network.

打开实时脚本

Code Generation for a Deep Learning Simulink Model to Classify ECG Signals

Generate CUDA for a Simulink model that classifies ECG signals using deep learning.

打开脚本

Code Generation for Lidar Point Cloud Segmentation Network

Generate CUDA MEX for a network that can segment organized lidar point clouds belonging to three classes.

打开实时脚本

Code Generation for a Video Classification Network

Classify activities on Jetson Xavier using a network with convolutional and BiLSTM layers.

打开实时脚本

Code Generation For Object Detection Using YOLO v3 Deep Learning

生成您只看一次（YOLO）V3对象检测器的CUDA MEX。

打开实时脚本

深度学习模型的代码生成，该模型执行车道和车辆检测万博1manbetx

Develop a CUDA® application from a Simulink® model that performs lane and vehicle detection using convolutional neural networks (CNN). This example takes the frames of a traffic video as an input, outputs two lane boundaries that correspond to the left and right lanes of the ego vehicle, and detects vehicles in the frame. This example uses the pretrained lane detection network from theLane Detection Optimized with GPU Coderexample of the GPU Coder Toolbox™. For more information, see Lane Detection Optimized with GPU Coder. This example also uses the pretrained vehicle detection network from theObject Detection Using YOLO v2 Deep Learningexample of the Computer Vision toolbox™. For more information, see Object Detection Using YOLO v2 Deep Learning (Computer Vision Toolbox).

打开脚本

Deploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink

Deploy a Simulink® model on the NVIDIA® Jetson TX2 board for classifying webcam images. This example classifies images from a webcam in real-time by using the pretrained deep convolutional neural network,ResNet-50. The Simulink model in the example uses the camera and display blocks from the MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms to capture the live video stream from a webcam and display the prediction results on a monitor connected to the Jetson platform.

Quantize Residual Network Trained for Image Classification and Generate CUDA Code

Quantize learnable parameters in the convolution layers of a residual network and generate CUDA code.

打开实时脚本

Quantize Layers in Object Detectors and Generate CUDA Code

Generate CUDA code for SSD and YOLO v2 vehicle detectors that perform inference computations in 8-bit integers.

打开实时脚本

Parameter Pruning and Quantization of Image Classification Network

Prune the parameters of a trained neural network using magnitude score and synaptic flow score metrics.

打开实时脚本

Code Generation For Aerial Lidar Semantic Segmentation Using PointNet++ Deep Learning

Generate CUDA MEX code for a PointNet++ network for lidar semantic segmentation.

打开实时脚本

使用Pointpillars深度学习的LIDAR对象检测代码生成代码

Generate CUDA MEX for a PointPillars object detector.

打开实时脚本

Deep Learning withGPU Coder

Apps

GPU Coder

Functions

Code Generation

Objects

Code Configuration

Model Settings

Simulation Acceleration

General Code Configuration

GPU代码配置

Basics

Training

Code Generation Overview

Topics

MATLAB

万博1manbetx

Related Information

Featured Examples

深度学习网络的代码生成

Generate Digit Images on NVIDIA GPU Using Variational Autoencoder

Train and Deploy Fully Convolutional Networks for Semantic Segmentation

通过使用nvidia tensorrt进行深度学习预测

Code Generation for Object Detection by Using YOLO v2

Code Generation for Object Detection by Using Single Shot Multibox Detector

Deep Learning Prediction on ARM Mali GPU

Code Generation for a Sequence-to-Sequence LSTM Network

Code Generation for a Deep Learning Simulink Model to Classify ECG Signals

Code Generation for Lidar Point Cloud Segmentation Network

Code Generation for a Video Classification Network

Code Generation For Object Detection Using YOLO v3 Deep Learning

深度学习模型的代码生成，该模型执行车道和车辆检测万博1manbetx

Deploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink

Quantize Residual Network Trained for Image Classification and Generate CUDA Code

Quantize Layers in Object Detectors and Generate CUDA Code

Parameter Pruning and Quantization of Image Classification Network

Code Generation For Aerial Lidar Semantic Segmentation Using PointNet++ Deep Learning

使用Pointpillars深度学习的LIDAR对象检测代码生成代码