WongKinYiu/yolov9

Health v2 · maintenance only

Adoption not part of the score

9551 stars · 1625 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Official PyTorch implementation of the YOLOv9 object detection paper, featuring Programmable Gradient Information for improved accuracy. It provides pretrained models (T/S/M/C/E variants), training and inference scripts, and ONNX/TensorRT export support.

Use cases

• train a custom object detection model
• run real-time object detection on images and video
• export YOLOv9 models to ONNX or TensorRT
• benchmark state-of-the-art object detection on COCO
• fine-tune a pretrained YOLO detector on my own dataset
• deploy an object detection model for edge inference

When to choose

• you need cutting-edge YOLO-family object detection with strong COCO accuracy
• you want to train or fine-tune a detector on custom data
• you need official reference weights and export paths for deployment

When to avoid

• you need instance segmentation or classification as the primary task
• you require a permissively licensed model (GPL-3.0)
• you want a maintained production framework rather than a research codebase

Facets

library · maturity active

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning artificial-intelligence python cross-platform object-detection yolo pytorch paper-implementation model-training onnx-export gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="WongKinYiu/yolov9")