jetson-examples

This repository provides examples for running AI models and applications on NVIDIA Jetson devices with a single command.

This repo builds upon the work of the jetson-containers, ultralytics and other excellent projects.

Features

• 🚀 Easy Deployment: Deploy state-of-the-art AI models on Jetson devices in one line.
• 🔄 Versatile Examples: Supports text generation, image generation, computer vision and so on.
• ⚡ Optimized for Jetson: Leverages Nvidia Jetson hardware for efficient performance.

Install

To install the package, run:

pip3 install jetson-examples

Notes:

• Check here for more installation methods
• To upgrade to the latest version, use: pip3 install jetson-examples --upgrade.

Quickstart

To run and chat with LLaVA, execute:

reComputer run llava

Example list

Here are some examples that can be run:

Example	Type	Model/Data Size	Docker Image Size	Command
🆕 llama-factory	Finetune LLM		13.5GB	reComputer run llama-factory
🆕 depth-anything	Computer Vision		12.9GB	reComputer run depth-anything
yolov10	Computer Vision	7.2M	5.74 GB	reComputer run yolov10
llama3	Text (LLM)	4.9GB	10.5GB	reComputer run llama3
ollama	Inference Server	*	10.5GB	reComputer run ollama
LLaVA	Text + Vision (VLM)	13GB	14.4GB	reComputer run llava
Live LLaVA	Text + Vision (VLM)	13GB	20.3GB	reComputer run live-llava
stable-diffusion-webui	Image Generation	3.97G	7.3GB	reComputer run stable-diffusion-webui
nanoowl	Vision Transformers(ViT)	613MB	15.1GB	reComputer run nanoowl
nanodb	Vector Database	76GB	7.0GB	reComputer run nanodb
whisper	Audio	1.5GB	6.0GB	reComputer run whisper
yolov8-rail-inspection	Computer Vision	6M	13.8GB	reComputer run yolov8-rail-inspection
ultralytics-yolo	Computer Vision		15.4GB	reComputer run ultralytics-yolo

Note: You should have enough space to run example, like LLaVA, at least 27.4GB totally

More Examples can be found examples.md

Development

Want to add your own example? Check out the development guide.

We welcome contributions to improve jetson-examples! If you have an example you'd like to share, please submit a pull request. Thank you to all of our contributors! 🙏

TODO List

• detect host environment and install what we need
• all type jetson support checking list
• try jetpack 6.0
• check disk space enough or not before run
• allow to setting some configs, such as BASE_PATH
• support jetson-containers update
• better table to show example's difference

License

This project is licensed under the MIT License.

Resources

• https://github.com/dusty-nv/jetson-containers
• https://www.jetson-ai-lab.com/
• https://www.ultralytics.com/