WongKinYiu/yolov7

Health v2 · maintenance only

Adoption not part of the score

14139 stars · 4353 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 YOLOv7 paper, a state-of-the-art real-time object detector with trainable bag-of-freebies techniques. It provides pretrained models, training scripts, and inference tools for object detection on images and video.

Use cases

• detect objects in images with a pretrained YOLO model
• train a custom object detector on my own dataset
• run real-time object detection on video streams
• benchmark real-time object detection performance on COCO
• fine-tune YOLOv7 weights for my use case
• convert and deploy a YOLO model for inference

When to choose

• you need a high-accuracy real-time object detector with pretrained COCO weights
• you want to train or fine-tune a YOLO-family detector in PyTorch
• you need reproducible research code matching a published paper

When to avoid

• you need a maintained project with frequent updates and new features
• you want a production-ready detection pipeline with an API or serving layer out of the box
• you need a permissively licensed model (it is GPL-3.0)
• you need segmentation, pose, or other vision tasks beyond bounding-box detection

Facets

library · maturity maintenance

machine-learning computer-vision deep-learning image-processing computer-vision deep-learning machine-learning artificial-intelligence python cross-platform object-detection yolo pytorch real-time-detection model-training inference coco gpu docker linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="WongKinYiu/yolov7")