Deployment

Deploy generated code to NVIDIA^® Tegra^® hardware targets

You can use GPU Coder™ with the MATLAB^® Coder™ Support Package for NVIDIA Jetson^® and NVIDIA DRIVE^® Platforms to deploy your MATLAB algorithms on embedded NVIDIA GPUs. Specifically, you can target the NVIDIA Jetson and DRIVE family of boards on either Windows^® or Linux^® systems. The support package enables you to remotely communicate with the NVIDIA target and control the peripheral devices for prototyping. The MATLAB entry-point function is deployed as a standalone executable that continues to run even if the hardware live connection is disconnected from the host computer.

To install this support package, use the Add-On Explorer in MATLAB. For information on the supported development platforms, see Install and Setup Prerequisites for NVIDIA Boards (MATLAB Coder Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms).

Note

Starting in R2021a, the GPU Coder Support Package for NVIDIA GPUs is named MATLAB Coder Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms. To use this support package in R2021a, you must have the MATLAB Coder product.

Functions

`packNGo`	Package generated code in ZIP file for relocation
`codegen`	Generate C/C++ code from MATLAB code
`jetson`	Create connection to NVIDIA Jetson hardware
`drive`	Create connection to NVIDIA DRIVE hardware

Objects

`coder.hardware`	Create hardware board configuration object for C/C++ code generation from MATLAB code
`jetson`	Connection to NVIDIA Jetson hardware
`drive`	Connection to NVIDIA DRIVE hardware

Topics

MATLAB

Build and Run an Executable on NVIDIA Hardware
Targeting embedded NVIDIA boards from the MATLAB command line.
Build and Run an Executable on NVIDIA Hardware Using GPU Coder App
Targeting embedded NVIDIA boards by using the GPU Coder app.
Relocate Generated Code to Another Development Environment
Package generated files into a compressed file that you can relocate and unpack with a standard zip utility.

Simulink

Targeting NVIDIA Embedded Boards
Build and deploy to NVIDIA GPU boards.
Numerical Equivalence Testing
Compare results from model and generated code simulations.
Parameter Tuning and Signal Monitoring by Using External Mode
Tune parameters and monitor signals through a TCP/IP communication channel between development computer and target hardware.
Generate CUDA ROS Node from Simulink (ROS Toolbox)
Configure Simulink® Coder™ to generate and build a CUDA® ROS node from a Simulink model.
Lane and Vehicle Detection in ROS Using YOLO v2 Deep Learning Algorithm (ROS Toolbox)
This example shows how to use deep convolutional neural networks inside a ROS enabled Simulink® model to perform lane and vehicle detection.
Sign Following Robot Using YOLOv2 Detection Algorithm with ROS in Simulink (ROS Toolbox)
This example shows how to use Simulink® to control a simulated robot running on a separate ROS-based simulator.

Featured Examples

Getting Started with the MATLAB Coder Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms

Use the MATLAB® Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms with embedded boards from NVIDIA®. The example uses a simple vector addition algorithm to illustrate: Connection to the embedded board from the MATLAB environment.

Open Script

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.

Open Script

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 Code Generation for Semantic Segmentation Network.

Open Script

Top-Hat Filtering to Remove Uneven Background Illumination on NVIDIA Jetson TX2 Developer Kit

Deploy Image Processing Toolbox™ algorithms to NVIDIA® Jetson TX2 board using the GPU Coder™ Support Package for NVIDIA GPUs. The imtophat (Image Processing Toolbox) function that performs morphological top-hat filtering on a grayscale image is used as an example to demonstrate this concept. Top-hat filtering computes the morphological opening of the image (using imopen (Image Processing Toolbox)) and then subtracts the result from the original image. The generated CUDA® code uses shared memory to speed up the operations on the GPU.

Open Script

Deployment and Classification of Webcam Images on NVIDIA Jetson TX2 Platform

Generate CUDA® code from a DAGNetwork object and deploy the generated code onto the NVIDIA® Jetson® TX2 board using the GPU Coder™ Support Package for NVIDIA GPUs. This example uses the resnet50 deep learning network to classify images from a USB webcam video stream.

Open Live Script

Deploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink

Deploy a Simulink® model on the NVIDIA® Jetson TX2 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.

Deploy Signal Classifier on NVIDIA Jetson Using Wavelet Analysis and Deep Learning

Generate and deploy a CUDA® executable that classifies human electrocardiogram (ECG) signals using features extracted by the continuous wavelet transform (CWT) and a pretrained convolutional neural network (CNN).

Open Live Script

Ground Plane Segmentation and Obstacle Detection on NVIDIA Jetson Xavier™ NX Embedded platform

Ground plane segmentation of 3-D lidar data on Jetson Xavier to find obstacles near a vehicle.

Open Live Script