Main Content

Deep Learning Code Generation

生成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®或者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.

Use Deep Learning Toolbox™ together with the深度学习工具箱模型量化库support 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.

UseMATLAB Coder™或者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®计算库。另外,您可以生成不调用第三方库函数的通用CPU代码。

Use GPU Coder™ together with Deep Learning Toolbox to generate CUDA MEX or standalone CUDA code that runs on desktop or embedded targets. You can deploy the generated standalone CUDA code that uses the CUDA deep neural network library (cuDNN), the TensorRT™ high performance inference library, or the ARM Compute library for Mali GPU.

Use Deep Learning HDL Toolbox™ together with Deep Learning Toolbox to generate HDL code for pretrained networks. You can deploy the generated HDL code on Intel and Xilinx®FPGA和SOC设备。

Workflow diagram for code generation from deep neural networks.

Categories

Related Information