# qqwweee/keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

Repository: https://github.com/qqwweee/keras-yolo3
Canonical: https://ross.abutalabs.com/products/keras-yolo3
Language: Python
License: MIT
License Family: permissive
Last push: 2023-03-12T02:57:19+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3074, "days_push": 1270, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7114, forks 3369 (observed 2026-08-28T04:09:56.001967+00:00)

## What it is
A Keras (TensorFlow backend) implementation of YOLOv3 for object detection, including Darknet weight conversion, image/video detection scripts, and custom training support. It is inspired by YAD2K and supports Tiny YOLOv3 and multi-GPU usage.

## Use cases
- run object detection on images and videos with YOLOv3
- convert Darknet YOLOv3 weights to Keras h5 models
- train YOLOv3 on a custom dataset with bounding box annotations
- detect objects in webcam or video streams
- use Tiny YOLOv3 for lightweight detection
- fine-tune YOLOv3 with pretrained darknet53 weights

## When to choose
- you need YOLOv3 object detection in a Keras/TensorFlow 1.x workflow
- you want to train YOLOv3 on custom VOC-style annotated data
- you need to convert existing Darknet weights to Keras

## When to avoid
- you need the latest YOLO versions or modern TensorFlow 2.x/Keras 3 support
- you want an actively maintained project with recent updates
- you need production-grade serving rather than scripts

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, windows
- tags: yolo, object-detection, keras, tensorflow, yolov3, darknet, real-time-detection, linux, macos, gpu

## Member repositories
- qqwweee/keras-yolo3 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:56.001967+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 2026-08-29T17:40:06.585910+00:00, confidence not recorded.
  - readme: https://github.com/qqwweee/keras-yolo3 (fetched 2026-08-28T04:09:56.001967+00:00, sha d70e745972bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.