Deep Learning Code Generation

Generate C/C++, CUDA^®, or HDL code and deploy deep learning networks

Generate code for pretrained deep neural networks. You can accelerate the simulation of your algorithms in MATLAB^®要么Simulink^®by using different execution environments. By using support packages, you can also generate and deploy C/C++, CUDA, and HDL code on target hardware.

采用深度学习工具箱™ together with the深度学习工具箱Model Quantization Librarysupport package to reduce the memory footprint and computational requirements of a deep neural network by quantizing the weights, biases, and activations of layers to reduced precision scaled integer data types. You can then generate C/C++, CUDA, or HDL code from these quantized networks.

采用MATLAB Coder™要么Simulink Codertogether 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.

使用GPU编码器™与Deep Learing Toolbox一起生成在桌面或嵌入目标上运行的CUDA MEX或独立的CUDA代码。您可以部署生成的独立CUDA代码，该代码使用CUDA深神经网络库（CUDNN），TensorRT™高性能推理库或MALI GPU的ARM计算库。

使用Deep Learning HDL Toolbox™与Deep Learing Toolbox一起生成预磨损网络的HDL代码。您可以在英特尔和Xilinx上部署生成的HDL代码^®FPGA and SoC devices.

Workflow diagram for code generation from deep neural networks.

代码生成基础知识

Networks and Layers Supported for Code Generation(MATLAB Coder)
万博1manbetx支持的网络，图层和类（GPU编码器）
Supported Networks, Layers, Boards, and Tools(Deep Learning HDL Toolbox)

深度学习网络的代码生成
Generate Generic C/C++ for Sequence-to-Sequence Deep Learning Simulink Models(Simulink Coder)
Get Started with Deep Learning FPGA Deployment on Intel Arria 10 SoC(Deep Learning HDL Toolbox)

Quantization
量化层的权重，偏置和激活，以减少精度缩放整数数据类型
Deep Learning Code Generation from MATLAB Applications
Generate C/C++, GPU, and HDL code for deployment on desktop or embedded targets
Deep Learning Code Generation from Simulink Applications
生成C / C ++和GPU代码，以便在桌面或嵌入目标上部署

Related Information

Deep Learning with MATLAB Coder(MATLAB Coder)

Deep Learning with GPU Coder（GPU编码器）

开始使用深度学习HDL工具箱(Deep Learning HDL Toolbox)

Featured Examples

深度学习网络的代码生成

Perform code generation for an image classification application that uses deep learning. It uses the codegen command to generate a MEX function that runs prediction by using image classification networks such as MobileNet-v2, ResNet, and GoogLeNet.

打开直播脚本

代码生成的语义分割网络

Code generation for an image segmentation application that uses deep learning. It uses the codegen command to generate a MEX function that performs prediction on a DAG Network object for SegNet [1], a deep learning network for image segmentation.

打开直播脚本

用GPU编码器优化车道检测

从深度学习网络生成CUDA®代码，由SeriesNetWork对象表示。在该示例中，系列网络是一种卷积神经网络，可以从图像中检测和输出车道标记边界。

打开直播脚本

Quantize Residual Network Trained for Image Classification and Generate CUDA Code

Quantize the learnable parameters in the convolution layers of a deep learning neural network that has residual connections and has been trained for image classification with CIFAR-10 data.

打开直播脚本