wizyoung/YOLOv3_TensorFlow

Health v2 · maintenance only

Adoption not part of the score

1551 stars · 571 forks observed · 2026-08-28

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

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

library · maturity abandoned

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning deep-learning python cross-platform yolov3 object-detection tensorflow real-time-detection darknet-weights custom-training gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wizyoung/YOLOv3_TensorFlow")