experiencor/keras-yolo3

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1608 stars · 838 forks observed · 2026-08-28

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

A Keras/TensorFlow implementation of YOLOv3 for object detection, supporting detection with pretrained weights, custom model training with warmup and multi-scale techniques, multi-GPU training, and mAP evaluation. It includes a model zoo with pretrained configurations for datasets like kangaroo, raccoon, license plate, blood cell, and VOC detection.

Use cases

• train a custom YOLOv3 object detector on my own dataset
• run object detection on images with pretrained YOLOv3 weights
• evaluate object detection model mAP on VOC-style datasets
• train YOLOv3 on multiple GPUs
• detect license plates or animals in images
• convert VOC-format annotations for YOLO training

When to choose

• you need a pure Keras/TensorFlow YOLOv3 implementation you can read and modify
• you want to train a custom single-class or few-class detector on a small dataset
• you need mAP evaluation alongside training in one codebase
• you want multi-GPU YOLOv3 training in Keras

When to avoid

• you need the latest YOLO versions (YOLOv5/v8) or state-of-the-art accuracy
• you need COCO evaluation, which is not yet implemented
• you want production-grade maintenance and recent TensorFlow compatibility
• you need alternative backbones like MobileNet, ResNet, or DenseNet, which are listed as unfinished

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python cross-platform yolo object-detection keras tensorflow training inference map-evaluation voc-dataset gpu

Member repositories

For agents

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