NVIDIA-AI-IOT/nanoowl
A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
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.
Stars
409
Forks
70
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
openvinotoolkit/nncf
Neural Network Compression Framework for enhanced OpenVINO™ inference
huggingface/optimum
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers...
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
huggingface/optimum-intel
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
eole-nlp/eole
Open language modeling toolkit based on PyTorch