allanzelener/YAD2K

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2728 stars · 878 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity abandoned

machine-learning deep-learning image-processing cli computer-vision deep-learning machine-learning developer-tools python cross-platform yolo object-detection keras tensorflow darknet model-conversion yolo-v2

Member repositories

For agents

markdown · JSON · MCP: product_card(name="allanzelener/YAD2K")