NVIDIA-AI-IOT / nanoowl
A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
☆256Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for nanoowl
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆664Updated last year
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆151Updated last year
- ☆82Updated 2 months ago
- ☆364Updated 11 months ago
- Quick start scripts and tutorial notebooks to get started with TAO Toolkit☆49Updated 2 months ago
- A reference example for integrating NanoOwl with Metropolis Microservices for Jetson☆26Updated 5 months ago
- Run Segment Anything Model 2 on a live video stream☆187Updated last month
- ☆82Updated this week
- Code for replicating Roboflow 100 benchmark results and programmatically downloading benchmark datasets☆248Updated 3 weeks ago
- A really more real-time adaptation of deep sort☆166Updated 3 months ago
- ☆108Updated last year
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆175Updated 2 months ago
- A project demonstrating how to make DeepStream docker images.☆60Updated last week
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Pose models☆123Updated 4 months ago
- ☆162Updated 4 months ago
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆95Updated 3 months ago
- CoRL 2024☆347Updated 3 weeks ago
- Creation of annotated datasets from scratch using Generative AI and Foundation Computer Vision models☆78Updated last week
- YOLOv8-3D is a LowCode, Simple 2D and 3D Bounding Box Object Detection and Tracking , Python 3.10☆165Updated last year
- ☆211Updated 4 months ago
- ☆78Updated last year
- This repository provides YOLOV5 GPU optimization sample☆100Updated last year
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO-Segmentation models☆54Updated 8 months ago
- yolov5, yolov8, segmenations, face, pose, keypoints on deepstream☆89Updated 11 months ago
- ☆163Updated last year
- Official Code for Tracking Any Object Amodally☆113Updated 4 months ago
- API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆784Updated 3 months ago
- A project demonstrating how to use nvmetamux to run multiple models in parallel.☆95Updated last month
- Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.☆95Updated last month
- [AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated c…☆279Updated 7 months ago