NVIDIA-AI-IOT / nanoowl
A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
☆300Updated 2 weeks ago
Alternatives and similar repositories for nanoowl:
Users that are interested in nanoowl are comparing it to the libraries listed below
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆708Updated last year
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆171Updated last year
- ☆374Updated last year
- ☆92Updated 5 months ago
- Quick start scripts and tutorial notebooks to get started with TAO Toolkit☆66Updated 5 months ago
- Code for replicating Roboflow 100 benchmark results and programmatically downloading benchmark datasets☆260Updated 3 months ago
- DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding☆860Updated last month
- ☆180Updated last week
- Run Segment Anything Model 2 on a live video stream☆293Updated 3 weeks ago
- A reference example for integrating NanoOwl with Metropolis Microservices for Jetson☆30Updated 8 months ago
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆216Updated 5 months ago
- A tutorial for getting started with the Deep Learning Accelerator (DLA) on NVIDIA Jetson☆316Updated 2 years ago
- CoRL 2024☆377Updated 3 months ago
- Implementation of End-to-End YOLO Models for DeepStream☆47Updated 3 months ago
- ☆98Updated this week
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO-Segmentation models☆56Updated 11 months ago
- ☆114Updated last year
- A really more real-time adaptation of deep sort☆182Updated 5 months ago
- Export Segment Anything Models to ONNX☆317Updated 6 months ago
- Creation of annotated datasets from scratch using Generative AI and Foundation Computer Vision models☆111Updated this week
- Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆894Updated last month
- A project demonstrating how to use nvmetamux to run multiple models in parallel.☆98Updated 4 months ago
- Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.☆100Updated 3 months ago
- A project demonstrating how to make DeepStream docker images.☆68Updated 2 months ago
- A pallet model trained with SDG optimized for NVIDIA Jetson.☆64Updated last year
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Pose models☆133Updated 7 months ago
- Workflow for generating synthetic data and training CV models.☆52Updated last year
- YOLOv8-3D is a LowCode, Simple 2D and 3D Bounding Box Object Detection and Tracking , Python 3.10☆175Updated last year
- Grounded Tracking for Streaming Videos☆85Updated 4 months ago
- ☆226Updated last week