thtrieu/darkflow

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

6139 stars · 2016 forks observed · 2026-08-28

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

Darkflow is a Python library that translates Darknet's YOLO neural network definitions to TensorFlow, enabling real-time object detection and classification. It can load pre-trained Darknet weights, retrain or fine-tune models in TensorFlow, and export frozen graph definitions for deployment on mobile devices.

Use cases

• run yolo object detection in tensorflow
• convert darknet weights to tensorflow
• fine-tune yolo on my own dataset
• real-time object detection from webcam
• export yolo model for android deployment
• train custom object detector with tensorflow

When to choose

• you have existing darknet/yolo cfg and weights you want to run in tensorflow
• you need to fine-tune YOLO v1/v2 models with custom labels
• you want to export a constant graph def for mobile inference

When to avoid

• you need modern TensorFlow 2.x support - the project targets TensorFlow 1.0
• you want the latest YOLO versions (v4+) or state-of-the-art detectors
• you need active maintenance and community support

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing deep-learning computer-vision machine-learning image-processing python cross-platform yolo object-detection darknet tensorflow cnn real-time-detection model-conversion mobile-deployment linux macos mobile

Member repositories

For agents

markdown · JSON · MCP: product_card(name="thtrieu/darkflow")