Deep Learning mit Simulink
R2026aImplementieren Sie Deep-Learning-Funktionen in Simulink®-Modellen, indem Sie Blöcke aus den Blockbibliotheken „Deep Neural Networks“, „Python Neural Networks“ und „Deep Learning Layers“ verwenden, die in der Deep Learning Toolbox™ enthalten sind, oder indem Sie den Deep Learning Object Detector-Block aus der in der Computer Vision Toolbox™ enthaltenen Blockbibliothek „Analysis & Enhancement“ verwenden.
Um ein Simulink-Modell zu erstellen, das mit der Blockbibliothek „Deep Learning Layers“ ein Netz darstellt, verwenden Sie die Funktion exportNetworkToSimulink.
Einige Deep-Learning-Funktionalitäten in Simulink verwenden einen MATLAB Function-Block, der einen unterstützten Compiler erfordert. Für die meisten Plattformen wird ein Standard-C-Compiler mit der MATLAB®-Installation mitgeliefert. Wenn Sie die Sprache C++ verwenden, müssen Sie einen kompatiblen C++ Compiler installieren. Um eine Liste der unterstützten Compiler anzuzeigen, öffnen Sie Supported and Compatible Compilers, klicken Sie auf die Registerkarte, die Ihrem Betriebssystem entspricht, suchen Sie die Simulink Product Family-Tabelle und gehen Sie zur Spalte For Model Referencing, Accelerator mode, Rapid Accelerator mode, and MATLAB Function blocks. Wenn Sie mehrere MATLAB-unterstützte Compiler auf Ihrem System installiert haben, können Sie den Standard-Compiler mit dem Befehl mex -setup ändern. Siehe Ändern des Standard-Compilers.
Funktionen
exportNetworkToSimulink | Generate Simulink model that contains deep learning layer blocks and subsystems that correspond to deep learning layer objects (Seit R2024b) |
Blöcke
 | Classify | Classify data using a trained deep learning neural network |
 | Predict | Vorhersagen von Antworten mithilfe eines trainierten neuronalen Netzes für Deep Learning |
 | Stateful Classify | Classify data using a trained deep learning recurrent neural network |
 | Stateful Predict | Predict responses using a trained recurrent neural network |
 | Deep Learning Object Detector | Detect objects using trained deep learning object detector |
 | TensorFlow Model Predict | Predict responses using pretrained Python TensorFlow model (Seit R2024a) |
 | PyTorch Model Predict | Predict responses using pretrained Python PyTorch model (Seit R2024a) |
 | ONNX Model Predict | Predict responses using pretrained Python ONNX model (Seit R2024a) |
 | Custom Python Model Predict | Predict responses using pretrained custom Python model (Seit R2024a) |
 | Clipped ReLU Layer | Clipped Rectified Linear Unit (ReLU) layer (Seit R2024b) |
 | GELU Layer | Gaussian error linear unit (GELU) layer (Seit R2024b) |
 | Leaky ReLU Layer | Leaky rectified linear unit (ReLU) layer (Seit R2024b) |
 | PReLU Layer | Parameterized rectified linear unit (PReLU) layer (Seit R2026a) |
 | ReLU Layer | Rectified linear unit (ReLU) layer (Seit R2024b) |
 | Sigmoid Layer | Sigmoid layer (Seit R2024b) |
 | Softmax Layer | Softmax layer (Seit R2024b) |
 | Swish Layer | Swish layer (Seit R2026a) |
 | Tanh Layer | Hyperbolic tangent (tanh) layer (Seit R2024a) |
 | Addition Layer | Addition layer (Seit R2024b) |
 | Concatenation Layer | Concatenation layer (Seit R2024b) |
 | Depth Concatenation Layer | Depth concatenation layer (Seit R2024b) |
 | Multiplication Layer | Multiplication layer (Seit R2024b) |
 | Convolution 1D Layer | 1-D convolutional layer (Seit R2024b) |
 | Convolution 2D Layer | 2-D convolutional layer (Seit R2024b) |
 | Convolution 3D Layer | 3-D convolutional layer (Seit R2024b) |
 | Fully Connected Layer | Fully connected layer (Seit R2024b) |
 | Rescale-Symmetric 1D | 1-D input layer with rescale-symmetric normalization (Seit R2024b) |
 | Rescale-Symmetric 2D | 2-D input layer with rescale-symmetric normalization (Seit R2024b) |
 | Rescale-Symmetric 3D | 3-D input layer with rescale-symmetric normalization (Seit R2024b) |
 | Rescale-Zero-One 1D | 1-D input layer with rescale-zero-one normalization (Seit R2024b) |
 | Rescale-Zero-One 2D | 2-D input layer with rescale-zero-one normalization (Seit R2024b) |
 | Rescale-Zero-One 3D | 3-D input layer with rescale-zero-one normalization (Seit R2024b) |
 | Zerocenter 1D | 1-D input layer with zerocenter normalization (Seit R2024b) |
 | Zerocenter 2D | 2-D input layer with zerocenter normalization (Seit R2024b) |
 | Zerocenter 3D | 3-D input layer with zerocenter normalization (Seit R2024b) |
 | Zscore 1D | 1-D input layer with zscore normalization (Seit R2024b) |
 | Zscore 2D | 2-D input layer with zscore normalization (Seit R2024b) |
 | Zscore 3D | 3-D input layer with zscore normalization (Seit R2024b) |
 | Batch Normalization Layer | Batch normalization layer (Seit R2024b) |
 | Instance Normalization Layer | Instance normalization layer (Seit R2026a) |
 | Layer Normalization Layer | Layer normalization layer (Seit R2024b) |
 | Inverse Zerocenter | Inverse zero-center normalization (Seit R2026a) |
 | Inverse Zscore | Inverse Z-score normalization (Seit R2026a) |
 | Average Pooling 1D Layer | 1-D average pooling layer (Seit R2024b) |
 | Average Pooling 2D Layer | 2-D average pooling layer (Seit R2024b) |
 | Average Pooling 3D Layer | 3-D average pooling layer (Seit R2024b) |
 | Global Average Pooling 1D Layer | 1-D global average pooling layer (Seit R2024b) |
 | Global Average Pooling 2D Layer | 2-D global average pooling layer (Seit R2024b) |
 | Global Average Pooling 3D Layer | 3-D global average pooling layer (Seit R2024b) |
 | Global Max Pooling 1D Layer | 1-D global max pooling layer (Seit R2024b) |
 | Global Max Pooling 2D Layer | 2-D global max pooling layer (Seit R2024b) |
 | Global Max Pooling 3D Layer | 3-D global max pooling layer (Seit R2024b) |
 | Max Pooling 1D Layer | 1-D max pooling layer (Seit R2024b) |
 | Max Pooling 2D Layer | 2-D max pooling layer (Seit R2024b) |
 | Max Pooling 3D Layer | 3-D max pooling layer (Seit R2024b) |
 | Flatten Layer | Flatten layer (Seit R2024b) |
 | GRU Layer | Gated recurrent unit (GRU) layer for recurrent neural network (RNN) (Seit R2025a) |
 | GRU Projected Layer | Gated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (Seit R2025a) |
 | LSTM Layer | Long short-term memory (LSTM) layer for recurrent neural network (RNN) (Seit R2024b) |
 | LSTM Projected Layer | Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (Seit R2024b) |
 | Dropout Layer | Dropout layer (Seit R2024b) |
 | Identity Layer | Identity layer (Seit R2026a) |
 | Scaling Layer | Scaling layer (Seit R2026a) |
 | Spatial Dropout Layer | Spatial dropout layer (Seit R2026a) |
Themen
Blöcke der Deep-Learning-Schicht
- List of Deep Learning Layer Blocks and Subsystems
Discover all the deep learning layer blocks and subsystems in Simulink. - Implement Unsupported Deep Learning Layer Blocks
Learn how to implement unsupported deep learning layer blocks.
Bilder
- Classify Image in Simulink Using SqueezeNet
This example shows how to classify an image in Simulink® using the Classify block. - 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 usingimportTensorFlowNetwork, and then use the Predict block for image classification in Simulink.
Sequenzen
- Predict and Update Network State in Simulink
This example shows how to predict responses for a trained recurrent neural network in Simulink® by using theStateful Predictblock. - Classify and Update Network State in Simulink
This example shows how to classify data for a trained recurrent neural network in Simulink® by using theStateful Classifyblock. - 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. - Simulate Calorie Burn Using Neural Network in Simulink
This example shows how to include a simple fully connected neural network in a Simulink® model that predicts calorie burn when given five time steps of sensor readings from a smart watch. (Seit R2024b) - Battery State of Charge Estimation Using Deep Learning
Define requirements, prepare data, train deep learning networks, verify robustness, integrate networks into Simulink, and deploy models. (Seit R2024b) - Physical System Modeling Using LSTM Network in Simulink
This example shows how to create a reduced order model (ROM) that acts as a virtual sensor in a Simulink® model using a long short-term memory (LSTM) neural network. - Classify Motor Faults Using Deep Learning
This example shows how to train a deep learning model to classify faults in a permanent magnet synchronous motor (PMSM) using simulated data across various revolutions per minute (RPM). (Seit R2025a) - 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®.
Verstärkungslernen
- Control Water Level in a Tank Using a DDPG Agent (Reinforcement Learning Toolbox)
Use DDPG agent to control water level in a tank modeled in Simulink. - Train DDPG Agent for Adaptive Cruise Control (Reinforcement Learning Toolbox)
Train a DDPG agent for an adaptive cruise control application. - Train DQN Agent for Lane Keeping Assist Using Parallel Computing (Reinforcement Learning Toolbox)
Train a DQN agent for an automated driving application using parallel computing. - Train DDPG Agent for Path-Following Control (Reinforcement Learning Toolbox)
Train a DDPG agent for lane following control.
Gemeinsame Ausführung mit Python
- 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. - Predict Responses Using TensorFlow Model Predict Block
Predict Responses Using TensorFlow Model Predict block. - Predict Responses Using ONNX Model Predict Block
Predict Responses Using ONNX Model Predict block. - Predict Responses Using PyTorch Model Predict Block
Predict Responses Using PyTorch Model Predict block. - Predict Responses Using Custom Python Model in Simulink (Statistics and Machine Learning Toolbox)
This example shows how to use the Custom Python Model Predict (Statistics and Machine Learning Toolbox) block for prediction in Simulink®.
Codegenerierung
- Deep Learning Code-Generierung aus Simulink-Anwendungen
Generieren von C/C++ und GPU-Code für die Bereitstellung auf Desktop- oder eingebetteten Zielen - Export Network to FMU
This example shows how to export a trained network as a Functional Mock-up Unit (FMU). (Seit R2023b)
Enthaltene Beispiele
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.
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 Classify Time Series Using Wavelet Analysis and Deep Learning (Wavelet Toolbox).
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.
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.
Profile Deep Learning Network for Deployment
Profile a deep learning network in Simulink. Profiling your network before training is a good way of checking that the network meets your requirements, before spending time on training. This example shows how to check:
