NVIDIA-AI-IOT/nanoowl

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

48
/ 100
Emerging

This project helps operations engineers, quality control specialists, or roboticists perform real-time object detection and classification on live camera feeds using NVIDIA Jetson Orin devices. You provide an image and descriptive text, and it outputs bounding boxes around detected objects and their classifications. This allows for flexible, on-the-fly recognition without needing to retrain a model.

409 stars. No commits in the last 6 months.

Use this if you need to rapidly detect and classify objects in live video streams or images using natural language prompts on an embedded NVIDIA Jetson Orin system.

Not ideal if you do not have NVIDIA Jetson Orin hardware or if your primary need is for object mask segmentation rather than bounding box detection.

real-time vision factory automation robotics quality control surveillance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

409

Forks

70

Language

Python

License

Apache-2.0

Last pushed

Feb 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NVIDIA-AI-IOT/nanoowl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.