# allanzelener/YAD2K

YAD2K: Yet Another Darknet 2 Keras

Repository: https://github.com/allanzelener/YAD2K
Canonical: https://ross.abutalabs.com/products/yad2k
Language: Python
License: NOASSERTION
License Family: other
Last push: 2020-12-16T17:18:51+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": 3487, "days_push": 2086, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2728, forks 878 (observed 2026-08-28T04:07:15.962031+00:00)

## What it is
YAD2K is a 90% Keras / 10% TensorFlow implementation and converter for YOLO_v2 object detection models. It converts Darknet cfg and weight files into Keras models and includes reference implementations of Darknet-19 and YOLO_v2 plus test and training scripts.

## Use cases
- convert darknet yolo weights to keras
- run yolo v2 object detection in python
- load yolo.cfg and yolo.weights into a keras model
- train a yolo model on pascal voc
- implement yolo v2 in keras and tensorflow
- run non-max suppression on yolo detections

## When to choose
- you need to run or fine-tune YOLO_v2 models in a Keras/TensorFlow 1.x stack
- you want a readable reference implementation of Darknet-19 and YOLO_v2
- you have existing Darknet cfg/weights you want to use from Python

## When to avoid
- you need YOLOv3, YOLOv4, or newer models
- you use modern TensorFlow 2.x / Keras versions, since the project is unmaintained and depends on old APIs
- you need production-grade object detection with active support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, cli
- domain: computer-vision, deep-learning, machine-learning, developer-tools
- platform: python, cross-platform
- tags: yolo, object-detection, keras, tensorflow, darknet, model-conversion, yolo-v2

## Member repositories
- allanzelener/YAD2K (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:15.962031+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 2026-08-30T02:14:42.881716+00:00, confidence not recorded.
  - readme: https://github.com/allanzelener/YAD2K (fetched 2026-08-28T04:07:15.962031+00:00, sha fecbd2335a92)
- Data as of 2026-08-30T08:39:29.467469+00:00.