README.md

Jetson-Example: Run Ultralytics YOLO on NVIDIA Jetson Orin 🚀

Experience all task models of Ultralytics YOLO with a single command.

Introduction 📘

This project enables you to deploy and experience all task models of Ultralytics YOLO on NVIDIA Jetson Orin devices with a single command. By accessing http:https://127.0.0.1:5000 on your local machine or within the same LAN, you can quickly start using Ultralytics YOLO. You can also upload your own trained models and test them with images, videos, or real-time camera feeds.

All models implemented in this project are from the official Ultralytics Yolo.

Get a Jetson Orin Device 🛒

Device Model	Description	Link
Jetson Orin Nano Dev Kit, Orin Nano 8GB, 40TOPS	Developer kit for NVIDIA Jetson Orin Nano	Buy Here
reComputer J4012, powered by Orin NX 16GB, 100 TOPS	Embedded computer powered by Orin NX	Buy Here

Quickstart ⚡

Installation via PyPI (Recommended) 🐍

1. Install the package:

   pip install jetson-examples

2. Restart your reComputer:

   sudo reboot

3. Run Ultralytics YOLO on Jetson with one command:

   reComputer run ultralytics-yolo

Notes 📝

• The first time you start the code for detection, there will be a wait of at least 30 seconds for loading; this is normal.
• To stop detection at any time, press the Stop button.
• When accessing the WebUI from other devices within the same LAN, use the URL: http:https://{Jetson_IP}:5001.

Further Development 🔧

• Training a YOLOv8 Model
• TensorRT Acceleration
• Multistreams using Deepstream Tutorials.

License

This project is licensed under the MIT License.