zzh8829/yolov3-tf2

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2513 stars · 890 forks observed · 2026-08-28

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

A clean implementation of YOLOv3 and YOLOv3-tiny object detection in TensorFlow 2.0, with pre-trained Darknet weight conversion, inference, and training examples. It supports eager and graph mode training, tf.data pipelines, GPU acceleration, and TensorFlow Serving deployment.

Use cases

• run yolo object detection on images in tensorflow 2
• convert darknet yolov3 weights to tensorflow
• detect objects in video or webcam feed
• train yolov3 on a custom dataset
• transfer learning for object detection with keras
• deploy yolo model with tensorflow serving

When to choose

• you want a readable, best-practices YOLOv3 implementation in TF2/Keras
• you need pre-trained weights plus a training tutorial for custom datasets
• you want GPU-accelerated detection with video and webcam support

When to avoid

• you need the latest YOLO versions (v5/v8) or state-of-the-art accuracy
• you want a maintained production package rather than an educational codebase
• you don't use TensorFlow

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing video-processing deep-learning computer-vision machine-learning image-processing python windows yolov3 object-detection tensorflow2 keras transfer-learning pretrained-weights jupyter-notebook gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zzh8829/yolov3-tf2")