NVIDIA-AI-IOT / nanoowl
A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
☆232Updated last month
Related projects: ⓘ
- A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT☆623Updated 9 months ago
- A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson☆145Updated 10 months ago
- ☆351Updated 9 months ago
- ☆77Updated this week
- Creation of annotated datasets from scratch using Generative AI and Foundation Computer Vision models☆78Updated this week
- A reference example for integrating NanoOwl with Metropolis Microservices for Jetson☆25Updated 3 months ago
- ☆74Updated this week
- Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector…☆171Updated 2 weeks ago
- A really more real-time adaptation of deep sort☆156Updated 3 weeks ago
- Code for replicating Roboflow 100 benchmark results and programmatically downloading benchmark datasets☆242Updated 3 months ago
- ☆320Updated 6 months ago
- ☆158Updated last year
- ☆153Updated last month
- A project demonstrating how to use nvmetamux to run multiple models in parallel.☆91Updated 4 months ago
- Quick start scripts and tutorial notebooks to get started with TAO Toolkit☆35Updated 3 weeks ago
- Easy to use neural networks for NVIDIA Jetson (and desktop too!)☆75Updated last year
- A project demonstrating how to make DeepStream docker images.☆57Updated 3 months ago
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Pose models☆116Updated 2 months ago
- A reference application for a local AI assistant with LLM and RAG☆82Updated 2 months ago
- This repository provides YOLOV5 GPU optimization sample☆100Updated last year
- API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series☆707Updated last month
- Python scripts for the Segment Anythin 2 (SAM2) model in ONNX☆128Updated 3 weeks ago
- A package to read and convert object detection datasets (COCO, YOLO, PascalVOC, LabelMe, CVAT, OpenImage, ...) and evaluate them with COC…☆169Updated 3 weeks ago
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Face models☆49Updated last year
- code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction☆377Updated 3 months ago
- A DeepStream sample application demonstrating end-to-end retail video analytics for brick-and-mortar retail.☆42Updated last year
- Export Segment Anything Models to ONNX☆240Updated last month
- [ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking☆135Updated 5 months ago
- TAO Toolkit deep learning networks with PyTorch backend☆81Updated 2 weeks ago
- Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.☆357Updated 5 months ago