jetson-orin-nano

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

💾 Create minimalist, Ubuntu based images for the Nvidia jetson boards

Go with your own intelligence - Go applications that directly integrate llama.cpp for local inference using hardware acceleration.

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

C library to manage the GPIO header of the Nvidia Jetson boards

Qt Cross Compilation for Raspberry Pi and Jetson Nano/Nx/Orin with Docker Isolation

Gemma models running 100% local on an 8 GB Jetson Orin Nano: voice assistants with RAG, multi-agent NPCs, live EN-JA translation, and a Gemma 4 voice + vision agent that decides when to look through the webcam. The demos from the Gemma 2 launch at Google Tokyo.

Start running LLMs, vision models, and camera pipelines in under an hour. This fully-configured single board computer comes with a bootable NVMe pre-loaded with Ollama, Llama.cpp, Roboflow vision inference, various LLM and VLM models, and 20+ applications ready to run. Save 40-120 hours of setup time.

A lightweight C++ implementation of YoloV8 running on NVIDIAs TensorRT engine

CUDA matrix multiplication benchmarking on Jetson Orin Nano. Four implementations, three power modes, five matrix sizes. 99.5% mathematical validation. C++/CUDA and Python.

This repository implements the YOLOv9 model on Jetson Orin Nano

A guide following the steps I took to get a working NVMe installation of Ubuntu 20.04 + Jetpack 5.1.2 on the Jetson Orin Nano using NVIDIA SDKManager.

Husky Simulation and Hardware In the Loop simulation on Isaac SIM with Isaac ROS

Exploring Vision & AI with on the Jetson Nano B01, Jetson Xavier NX and Jetson Orin Nano

MIPI CSI-2 kernel driver for Onsemi AR0234 global shutter sensor on NVIDIA Jetson Orin NX / Nano (JetPack 6)

This repo contains model compression(using TensorRT) and documentation of running various deep learning models on NVIDIA Jetson Orin, Nano (aarch64 architectures)

A step-by-step guide to setting up a GUI on a headless Jetson Orin Nano.

This repository features the code base for the "Autonomous Drone for Dynamic Smoke Plume Tracking" project.

Built a real-time, purely classical computer vision system for fabric defect detection using multi-method analysis (GLCM, FFT, Gabor, statistical variance, background subtraction, and edge–Hough), with IoU-based bounding box fusion for robust localization. Deployed and optimized the pipeline on Jetson Nano for real time defect detection.

Custom Spot Micro — STM32 firmware + ROS2 Humble on Jetson Orin Nano