MATLAB 애플리케이션에서 CPU 코드 생성
데스크탑 또는 임베디드 타깃 배포용 C/C++ 코드 생성
MATLAB® Coder™, Simulink® Coder 및 Embedded Coder®와 함께 Deep Learning Toolbox™를 사용하여 데스크탑 또는 임베디드 타깃에서 실행되는 MEX 또는 독립 실행형 CPU 코드를 생성합니다. Intel® MKL-DNN 라이브러리 또는 ARM® Compute Library를 사용하는, 생성된 독립 실행형 코드를 배포할 수 있습니다. 또는 타사 라이브러리 함수를 호출하지 않는 일반 CPU 코드를 생성할 수 있습니다. TensorFlow™ Lite 모델을 사용하여 추론을 수행하는 코드를 생성하고 배포할 수도 있습니다.
함수
codegen | Generate C/C++ code from MATLAB code |
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 (R2023a 이후) |
coder.DeepLearningConfig | Create deep learning code generation configuration objects |
loadTFLiteModel | Load TensorFlow Lite model (R2022a 이후) |
predict | Compute deep learning network output for inference by using a TensorFlow Lite model (R2022a 이후) |
TFLiteModel | TensorFlow Lite model (R2022a 이후) |
앱
MATLAB Coder | MATLAB 코드에서 C 코드 또는 MEX 함수 생성 |
도움말 항목
개요
- Networks and Layers Supported for Code Generation (MATLAB Coder)
Choose a convolutional neural network that is supported for your target processor. - Load Pretrained Networks for Code Generation (MATLAB Coder)
Create aSeriesNetwork
,DAGNetwork
,yolov2ObjectDetector
,ssdObjectDetector
, ordlnetwork
object for code generation. - 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.
응용 사례
- Generate Code and Deploy SqueezeNet 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 SqueezeNet network. - Deep Learning Prediction with ARM Compute Using codegen
This example shows how to usecodegen
to generate code for a logo classification application that uses deep learning on ARM® processors. - Generate Code for a Deep Learning Network for x86-64 Platforms Using Advanced Vector Instructions
This example shows how to generate code that uses advanced vector instructions and implements an image classification algorithm. - 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. - Raspberry Pi에 신호 분할 심층 신경망 배포하기
MEX 함수와 독립형 실행 파일을 생성하여 Raspberry Pi에서 파형 분할을 수행합니다. - 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.