qqwweee/keras-yolo3

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7114 stars · 3369 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python windows yolo object-detection keras tensorflow yolov3 darknet real-time-detection linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="qqwweee/keras-yolo3")