Simulink를 사용한 딥러닝

Simulink를 사용한 딥러닝 워크플로 확장

Deep Learning Toolbox™에 포함된 Deep Neural Networks 블록 라이브러리의 블록을 사용하거나 Computer Vision Toolbox™에 포함된 Analysis & Enhancement 블록 라이브러리의 Deep Learning Object Detector 블록을 사용하여 Simulink^® 모델에서 딥러닝 기능을 구현합니다.

Simulink의 딥러닝 기능은 MATLAB Function 블록을 사용하는데 이를 위해 지원되는 컴파일러가 필요합니다. 대부분의 플랫폼에서 MATLAB^®을 설치할 때 디폴트 C 컴파일러가 제공됩니다. C++ 언어를 사용하는 경우 호환되는 C++ 컴파일러를 설치해야 합니다. 지원되는 컴파일러 목록을 보려면 지원 및 호환되는 컴파일러를 열고 사용자의 운영 체제에 해당하는 탭을 클릭한 다음 Simulink Product Family 표에서 For Model Referencing, Accelerator mode, Rapid Accelerator mode, and MATLAB Function blocks 열로 이동하십시오. 시스템에 MATLAB 지원 컴파일러가 여러 개 설치된 경우 mex -setup 명령을 사용하여 디폴트 컴파일러를 변경할 수 있습니다. 디폴트 컴파일러 변경하기 항목을 참조하십시오.

블록

Image Classifier	훈련된 딥러닝 신경망을 사용하여 데이터 분류 (R2020b 이후)
Predict	훈련된 딥러닝 신경망을 사용하여 응답 변수 예측 (R2020b 이후)
Stateful Classify	Classify data using a trained deep learning recurrent neural network (R2021a 이후)
Stateful Predict	Predict responses using a trained recurrent neural network (R2021a 이후)
Deep Learning Object Detector	훈련된 딥러닝 객체 검출기를 사용하여 객체 검출 (R2021b 이후)
TensorFlow Model Predict	Predict responses using pretrained Python TensorFlow model (R2024a 이후)
PyTorch Model Predict	Predict responses using pretrained Python PyTorch model (R2024a 이후)
ONNX Model Predict	Predict responses using pretrained Python ONNX model (R2024a 이후)
Custom Python Model Predict	Predict responses using pretrained custom Python model (R2024a 이후)

도움말 항목

영상

GoogLeNet을 사용하여 Simulink에서 영상 분류하기
이 예제에서는 Image Classifier 블록을 사용하여 Simulink®에서 영상을 분류하는 방법을 보여줍니다.
Acceleration for Simulink Deep Learning Models
Improve simulation speed with accelerator and rapid accelerator modes.
Lane and Vehicle Detection in Simulink Using Deep Learning
This example shows how to use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection.
Classify ECG Signals in Simulink Using Deep Learning
This example shows how to use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals.
Classify Images in Simulink with Imported TensorFlow Network
Import a pretrained TensorFlow™ network using importTensorFlowNetwork, and then use the Predict block for image classification in Simulink.
Classify Images Using TensorFlow Model Predict Block
Classify images using TensorFlow Model Predict block.
Classify Images Using ONNX Model Predict Block
Classify images using ONNX Model Predict block.
Classify Images Using PyTorch Model Predict Block
Classify images using PyTorch Model Predict block.

시퀀스

Simulink에서 예측을 수행하고 신경망 상태 업데이트하기
이 예제에서는 Stateful Predict 블록을 사용하여 Simulink®에서 훈련된 순환 신경망의 응답 변수 예측을 수행하는 방법을 보여줍니다.
Classify and Update Network State in Simulink
This example shows how to classify data for a trained recurrent neural network in Simulink® by using the Stateful Classify block.
Speech Command Recognition in Simulink
Detect the presence of speech commands in audio using a Simulink model.
Time Series Prediction in Simulink Using Deep Learning Network
This example shows how to use an LSTM deep learning network inside a Simulink® model to predict the remaining useful life (RUL) of an engine.
Physical System Modeling Using LSTM Network in Simulink
This example shows how to create a reduced order model (ROM) to replace a Simscape component in a Simulink® model by training a long short-term memory (LSTM) neural network.
Improve Performance of Deep Learning Simulations in Simulink
This example shows how to use code generation to improve the performance of deep learning simulations in Simulink®.

강화 학습

Control Water Level in a Tank Using a DDPG Agent
Train a controller using reinforcement learning with a plant modeled in Simulink as the training environment.
Train DDPG Agent for Adaptive Cruise Control
Train a reinforcement learning agent for an adaptive cruise control application.
Train DQN Agent for Lane Keeping Assist Using Parallel Computing
Train a reinforcement learning agent for a lane keeping assist application.
Train DDPG Agent for Path-Following Control
Train a reinforcement learning agent for a lane following application.

코드 생성

Simulink 애플리케이션에서 딥러닝 코드 생성
데스크탑 또는 임베디드 타깃 배포용 C/C++ 및 GPU 코드 생성
Export Network to FMU
This example shows how to export a trained network as a Functional Mock-up Unit (FMU). (R2023b 이후)

추천 예제

Lane and Vehicle Detection in Simulink Using Deep Learning

Use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection. This example takes the frames from 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.

스크립트 열기

Classify ECG Signals in Simulink Using Deep Learning

Use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals. This example uses the pretrained convolutional neural network from the Classify Time Series Using Wavelet Analysis and Deep Learning example of the Wavelet Toolbox™ to classify ECG signals based on images from the CWT of the time series data. For information on training, see 웨이블릿 분석 및 딥러닝을 사용하여 시계열 분류하기 (Wavelet Toolbox).

스크립트 열기

Time Series Prediction in Simulink Using Deep Learning Network

Use an LSTM deep learning network inside a Simulink® model to predict the remaining useful life (RUL) of an engine. You include the network inside the Simulink model by using a Stateful Predict block, which predicts the RUL at every simulation step.

라이브 스크립트 열기

Battery State of Charge Estimation in Simulink Using Feedforward Neural Network

Use a feedforward deep learning network inside a Simulink® model to predict the state of charge (SOC) of a battery. You include the network inside the Simulink model by using a Predict block, which predicts the SOC at every simulation step.

라이브 스크립트 열기