#231 · Primary category： Computer Vision
darkflow
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
Project last updated：10/23/23
GitHub Stars
6.1K
Forks
2.0K
Contributors
32
License
GPL-3.0
Why we included this project
Darkflow reads darknet's network definitions and trained weight files, then rebuilds them as TensorFlow graphs, giving you a single `flow` command for forward passes, training from scratch, and fine-tuning on your own annotated datasets. That appeals to teams already working in TensorFlow who would rather reuse YOLO's pretrained weights than reimplement the network by hand. The same pipeline exports a constant graph definition meant for mobile targets, so it is a reasonable stop for on-device detection prototypes. Just note the age of the stack: it targets TensorFlow 1.x and the YOLO v1/v2 generations, which makes it a pragmatic fit for legacy setups and educational runs rather than a foundation for a new production system.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)