在目标硬件上运行

将 MATLAB^® 函数作为独立可执行文件部署到硬件上

MATLAB Support Package for Raspberry Pi^® Hardware 还使您能够在硬件上部署 MATLAB 函数。使用 MATLAB Coder™，您可以为 MATLAB 算法生成 C 代码，并将其部署为在 Raspberry Pi 硬件上独立运行。即使硬件与计算机断开连接，独立可执行文件也会继续运行。要了解详细信息，请参阅Additional Capabilities with MATLAB Coder。

注意

您可以使用 MATLAB Online™ 在硬件上部署 MATLAB 函数。有关详细信息，请参阅Connect to Raspberry Pi Hardware Board in MATLAB Online。

对象

raspi Connection to Raspberry Pi board

函数

`targetHardware`	Create configuration object for hardware
`deploy`	Deploy MATLAB function on hardware

App

Raspberry Pi 资源监视器

Monitor and manage Raspberry Pi resources (自 R2020b 起)

主题

Additional Capabilities with MATLAB Coder
Include additional capabilities for code generation.
Automatically Run MATLAB Function on Raspberry Pi After Restart
Automatically start a MATLAB function deployed on Raspberry Pi hardware every time you restart the hardware.
Workflow to Deploy MATLAB Function on Raspberry Pi

Workflow to explain the steps involved in deploying a MATLAB function on the hardware.
- 步骤 1: Create or Open a MATLAB Function
- 步骤 2: Run the MATLAB Function Using Live IO from Hardware
- 步骤 3: Add Compilation Directive to MATLAB Function
- 步骤 4: Check MATLAB Function Using Code Analyzer
- 步骤 5: Check MATLAB Function for Unsupported Calls
- 步骤 6: Create Hardware Configuration Object
- 步骤 7: Deploy MATLAB Function on Hardware

精选示例

Getting Started with Deploying a MATLAB Function on the Raspberry Pi Hardware

Deploy a MATLAB® function as a standalone executable on the Raspberry Pi® Hardware using MATLAB Support Package for Raspberry Pi Hardware.

Deploy an Edge Detection Algorithm on the Raspberry Pi Hardware

Deploy an Edge detection function on the Raspberry Pi® hardware as a standalone executable using MATLAB® Support Package for Raspberry Pi Hardware. In this example, you will learn how to acquire live image from a webcam connected to the Raspberry Pi hardware, run the edge detection function on the acquired image, and display the result on the monitor that is connected to the same Raspberry Pi hardware.

Identify Objects Within Live Video Using ResNet-50 on Raspberry Pi Hardware

Predict the objects in a live video stream on Raspberry Pi® by deploying an image classification algorithm using MATLAB® Support Package for Raspberry Pi Hardware. The algorithm uses ResNet-50 neural network to identify the objects captured by the webcam that is connected to the Raspberry Pi hardware.

打开实时脚本

Send Inputs to MATLAB Function from Command Line of Raspberry Pi

Deploy a MATLAB® function that accepts inputs from command line of Raspberry Pi® using MATLAB Support Package for Raspberry Pi Hardware. In this example, a MATLAB function for adding two numbers is used for deployment.

打开实时脚本

Send Inputs to MATLAB Function from Command Line of Raspberry Pi in MATLAB Online

Deploy a MATLAB® function that accepts inputs from command line of Raspberry Pi® using MATLAB Support Package for Raspberry Pi Hardware in MATLAB Online. In this example, a MATLAB function for adding two numbers is used for deployment.

Classify Static Image Using Deep Learning on Raspberry Pi

Generate and deploy code for an image classification algorithm using MATLAB® Support Package for Raspberry Pi® Hardware. The algorithm uses the ResNet-50 neural network to identify the image that is passed as an input using the command line of Raspberry Pi.

打开实时脚本

Speech Command Recognition Code Generation on Raspberry Pi

Deploy feature extraction and a convolutional neural network (CNN) for speech command recognition to Raspberry Pi™. To generate the feature extraction and network code, you use MATLAB Coder™, MATLAB® Support Package for Raspberry Pi Hardware, and the ARM® Compute Library. In this example, the generated code is an executable on your Raspberry Pi, which is called by a MATLAB script that displays the predicted speech command along with the signal and auditory spectrogram. Interaction between the MATLAB script and the executable on your Raspberry Pi is handled using the user datagram protocol (UDP). For details about audio preprocessing and network training, see Train Speech Command Recognition Model Using Deep Learning (Audio Toolbox).

Keyword Spotting in Noise Code Generation on Raspberry Pi

Demonstrates code generation for keyword spotting using a Bidirectional Long Short-Term Memory (BiLSTM) network and mel frequency cepstral coefficient (MFCC) feature extraction on Raspberry Pi™. MATLAB® Coder™ with Deep Learning Support enables the generation of a standalone executable (.elf) file on Raspberry Pi. Communication between MATLAB® (.mlx) file and the generated executable file occurs over asynchronous User Datagram Protocol (UDP). The incoming speech signal is displayed using a timescope. A mask is shown as a blue rectangle surrounding spotted instances of the keyword, YES. For more details on MFCC feature extraction and deep learning network training, visit Keyword Spotting in Noise Using MFCC and LSTM Networks (Audio Toolbox).