展開

MATLAB^® アルゴリズムをスタンドアロンの実行可能ファイルとしてハードウェアに展開する

MATLAB Coder™ Support Package for NVIDIA^® Jetson™ and NVIDIA DRIVE^® Platforms により、ハードウェア上に MATLAB 関数を展開できるようになります。関数は、ハードウェアのライブ接続がホストコンピューターから切断された場合でも実行を続けるスタンドアロンの実行可能ファイルとして展開されます。

関数

すべて展開する

ボード接続

`jetson`	Connection to NVIDIA Jetson hardware
`drive`	Connection to NVIDIA DRIVE hardware

GPIO

`configurePin`	Configure GPIO pin as digital input or digital output (R2021b 以降)
`readDigitalPin`	Read logical value from GPIO input pin (R2021b 以降)
`showPins`	Show diagram of GPIO pins (R2021b 以降)
`writeDigitalPin`	Write logical value to GPIO output pin (R2021b 以降)

周辺装置

`audiocapture`	Connection between audio input device and NVIDIA hardware (R2021a 以降)
`audioplayer`	Connection between audio output device and NVIDIA hardware (R2021a 以降)
`capture`	Capture data from audio device connected to NVIDIA hardware (R2021a 以降)
`play`	Play audio from audio device connected to NVIDIA hardware (R2021a 以降)
`camera`	Connection to USB or CSI camera
`getCameraList`	Get a list of available cameras on the NVIDIA hardware
`listAudioDevices`	Get a list of available audio devices on the NVIDIA hardware (R2021a 以降)
`image`	Display image
`imageDisplay`	NVIDIA display object
`snapshot`	Capture RGB image from Camera
`updatePeripheralInfo`	Scan for and update the list of peripherals connected to the target hardware
`velodynelidar`	Connection to a Velodyne LiDAR sensor (R2022b 以降)
`read`	Acquire point clouds from `velodynelidar` object buffer (R2022b 以降)
`start`	Start streaming point clouds from Velodyne LiDAR sensor (R2022b 以降)
`stop`	Stop streaming point clouds from Velodyne LiDAR sensor (R2020b 以降)
`webcam`	Connection to USB web camera

ファイル操作

`getFile`	Transfer file from NVIDIA hardware to host computer
`putFile`	Transfer file from host computer to target hardware
`deleteFile`	Delete file on target hardware

ユーティリティ

`openShell`	Open terminal on host computer to use a Linux shell on NVIDIA hardware
`system`	Run commands in a Linux shell on the NVIDIA hardware
`getL4TVersion`	Get the L4T version of the NVIDIA Jetson hardware
`getPdkorSdkVersion`	Get the version number of the DriveWorks SDK installed on the NVIDIA DRIVE hardware
`getDisplayEnvironment`	Get the display environment value used for redirecting the display on the target
`setDisplayEnvironment`	Set the display environment value used for redirecting the display on the target
`setupCodegenContext`	Select the target hardware to build code for from multiple live connection objects
`getLinuxVersion`	Get information about the Linux environment on the target
`killApplication`	Kill an application on the NVIDIA target by name
`killProcess`	Kill a process on the NVIDIA target by ID
`runApplication`	Launch an application on the NVIDIA target by name
`runExecutable`	Launch an executable on the NVIDIA target by name

プロセッサインザループ

`setPILTimeout`	Set the timeout value that PIL uses for reading data
`setPILPort`	Set the TCP/IP port number used by the PIL execution
`getPILTimeout`	Get the timeout value that PIL uses for reading data
`getPILPort`	Get the TCP/IP port number used by the PIL execution

Modbus 通信

`modbus`	Create a Modbus object for NVIDIA boards (R2022a 以降)
`read`	Read data from a connected Modbus device (R2022a 以降)
`write`	Perform a write operation to the connected Modbus device (R2022a 以降)

トピック

MATLAB

Build and Run an Executable on NVIDIA Hardware
Build and run an executable on NVIDIA hardware.
Build and Run an Executable on NVIDIA Hardware Using GPU Coder App
Use GPU Coder™ app to build and run an executable on NVIDIA hardware.
Read Video Files on NVIDIA Hardware
Generate CUDA^® code for reading video files on the NVIDIA target by using the videoReader function.
Stop or Restart an Executable Running on NVIDIA Hardware
Stop or restart an executable running on the hardware.
Processor-In-The-Loop Execution from Command Line
Use PIL execution to verify the numerical behavior of the generated code at the MATLAB command line.
Processor-In-The-Loop Execution with the GPU Coder App
Use the GPU Coder app to verify the numerical behavior of the generated code.
Execution-Time Profiling for PIL
Why measure execution times for code generated from entry-point functions.

Simulink

NVIDIA 組み込みボードのターゲット化 (GPU Coder)
ビルドして NVIDIA GPU ボードに展開する。
数値的等価性テスト (GPU Coder)
モデルと生成されたコードのシミュレーション結果を比較する。
エクスターナルモードを使用したパラメーターの調整と信号の監視 (GPU Coder)
開発用コンピューターとターゲットハードウェアの間の TCP/IP 通信チャネルで、パラメーターを調整し、信号を監視します。

注目の例

Deploy and Run Sobel Edge Detection with I/O on NVIDIA Jetson Nano

Deploy Sobel edge detection application that uses a Raspberry Pi Camera Module V2 and displays the edge detected output on the NVIDIA® Jetson™ Nano Hardware. The Sobel Edge Detection on NVIDIA Jetson Nano Using Raspberry Pi Camera Module V2 example showed how to capture image frames from the Raspberry Pi Camera Module V2 on an NVIDIA Jetson Nano hardware and process them in the MATLAB® environment. This example shows how to generate code for accessing I/O peripherals (camera and display) and perform processing on the NVIDIA Jetson Nano hardware.

ライブスクリプトを開く

Sobel Edge Detection on NVIDIA Jetson Nano Using Raspberry Pi Camera Module V2

Capture and process images from a Raspberry Pi® Camera Module V2 connected to the NVIDIA® Jetson™ Nano. The MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE® Platforms allows you to capture images from the Camera Module V2 and bring them into the MATLAB environment for processing. In this example you learn how to develop a Sobel edge detection algorithm by using this capability.

スクリプトを開く

Semantic Segmentation on NVIDIA DRIVE

Generate and deploy a CUDA® executable for an image segmentation application that uses deep learning. It uses the MATLAB® Coder™ Support Package for NVIDIA® Jetson™ and NVIDIA DRIVE™ Platforms to deploy the executable on the NVIDIA DRIVE™ platform. This example performs code generation on the host computer and builds the generated code on the target platform by using remote build capability of the support package. For more information, see セマンティックセグメンテーションネットワークのコード生成 (GPU Coder).

ライブスクリプトを開く

Processor-in-the-Loop Execution on NVIDIA Targets Using GPU Coder

How the MATLAB® Coder™ Support Package for NVIDIA® Jetson™ and NVIDIA DRIVE™ Platforms enables the GPU Coder™ product to run PIL execution on NVIDIA DRIVE and Jetson hardware platforms. This example uses the GPU Code generation for fog rectification example from GPU Coder to demonstrate PIL execution. For more information, see 霧の修正 (GPU Coder).

ライブスクリプトを開く

NVIDIA Jetson TX2 開発者キットで不均一な背景の照度を除去するトップハットフィルター処理

この例では、GPU Coder™ Support Package for NVIDIA GPUs を使用して、Image Processing Toolbox™ アルゴリズムを NVIDIA® Jetson TX2 ボードに展開する方法を説明します。この概念を説明するための例として、関数 imtophat (Image Processing Toolbox) を使用します。この関数は、グレースケールイメージに対してモルフォロジートップハットフィルター処理を実行します。トップハットフィルター処理を実行するとイメージのモルフォロジーオープニングが計算され (imopen (Image Processing Toolbox) を使用)、次に元のイメージから結果が減算されます。生成された CUDA® コードでは、GPU での演算を高速化するために共有メモリが使用されます。

NVIDIA Jetson TX2 プラットフォームでの Web カメライメージの展開と分類

この例では、GPU Coder™ Support Package for NVIDIA GPUs を使用して、DAGNetwork オブジェクトから CUDA® コードを生成し、その生成コードを NVIDIA® Jetson® TX2 ボードに展開する方法を説明します。この例では、resnet50 深層学習ネットワークを使用して、USB Web カメラのビデオストリームのイメージを分類します。

Deploy and Run Fog Rectification for Video on NVIDIA Jetson

Generate and deploy a CUDA® executable for a video-based fog rectification application. The example shows the deployable code generation capabilities that the MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms provides for the MATLAB VideoReader function. This example generates a CUDA application that reads the contents of a video file, performs fog rectification operation, and displays the output video on the NVIDIA® hardware.

ライブスクリプトを開く

Deploy and Classify Webcam Images on NVIDIA Jetson Platform from Simulink

Deploy a Simulink® model on the NVIDIA® Jetson™ board for classifying webcam images. This example classifies images from a webcam in real-time by using the pretrained deep convolutional neural network, ResNet-50. The Simulink model in the example uses the camera and display blocks from the MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE™ Platforms to capture the live video stream from a webcam and display the prediction results on a monitor connected to the Jetson platform.

スクリプトを開く

Keyword Spotting in Audio Using MFCC and LSTM Networks on NVIDIA Embedded Hardware from Simulink

Deploy a Simulink® model on the NVIDIA® Jetson™ board for keyword spotting in audio data. This example identifies the keyword(YES) in the input audio data using Mel Frequency Cepstral Coefficients (MFCC) and a pretrained Bidirectional Long Short-Term Memory (BiLSTM) network.

スクリプトを開く

CAN Bus Communication on NVIDIA Jetson TX2 in Simulink

Deploy a Simulink® model that uses CAN communication for a deep learning application. The Simulink model in this example uses the CAN Transmit and CAN Receive blocks from the MATLAB® Coder™ Support Package for NVIDIA® Jetson® and NVIDIA DRIVE® Platforms to model a CAN bus system on the Jetson TX2 platform. The model uses the CAN bus to transmit the recognized traffic sign objects in a video frame from one CAN node to another CAN node.

ライブスクリプトを開く