# wizyoung/YOLOv3_TensorFlow

Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.

Repository: https://github.com/wizyoung/YOLOv3_TensorFlow
Canonical: https://ross.abutalabs.com/products/yolov3_tensorflow
Language: Python
License: MIT
License Family: permissive
Topics: yolov3, tensorflow, object-detection, real-time, tensorflow-yolo
Last push: 2022-09-16T16:58:43+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": 2783, "days_push": 1447, "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 1551, forks 571 (observed 2026-08-28T04:05:02.271992+00:00)

## What it is
A pure TensorFlow implementation of the YOLOv3 real-time object detection model, including weight conversion from darknet, training, and evaluation pipelines. It supports training on custom datasets with an efficient tf.data pipeline and fast GPU non-maximum suppression.

## Use cases
- train yolov3 on my own dataset
- convert darknet yolov3 weights to tensorflow
- detect objects in images and videos in real time
- run yolov3 inference with tensorflow
- compute anchor boxes with kmeans for custom dataset
- evaluate object detection model on custom data

## When to choose
- you need a TensorFlow 1.x YOLOv3 implementation with full training pipeline
- you want to convert pretrained darknet COCO weights to TensorFlow checkpoints
- you need fast GPU non-maximum suppression and tf.data-based training

## When to avoid
- you need maintained code or TensorFlow 2.x support
- you prefer PyTorch or newer YOLO versions like YOLOv5/YOLOv8
- you need production support or bug fixes

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: yolov3, object-detection, tensorflow, real-time-detection, darknet-weights, custom-training, gpu, linux

## Member repositories
- wizyoung/YOLOv3_TensorFlow (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:02.271992+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 2026-08-30T04:30:18.088673+00:00, confidence not recorded.
  - readme: https://github.com/wizyoung/YOLOv3_TensorFlow (fetched 2026-08-28T04:05:02.271992+00:00, sha 1b1e448b44d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.