# WongKinYiu/yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Repository: https://github.com/WongKinYiu/yolov7
Canonical: https://ross.abutalabs.com/products/yolov7
Language: Jupyter Notebook
License: GPL-3.0
License Family: copyleft
Topics: scaled-yolov4, yolor, yolov3, yolov4, yolov7, darknet, pytorch
Last push: 2024-08-19T12:57:04+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1519, "days_push": 744, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14139, forks 4353 (observed 2026-08-28T04:11:05.558315+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, deep-learning, image-processing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: object-detection, yolo, pytorch, real-time-detection, model-training, inference, coco, gpu, docker, linux

## Member repositories
- WongKinYiu/yolov7 (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:05.558315+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:47.876862+00:00, confidence not recorded.
  - readme: https://github.com/WongKinYiu/yolov7 (fetched 2026-08-28T04:11:05.558315+00:00, sha 4153c5f50c4a)
- Data as of 2026-08-30T08:39:29.467469+00:00.