# thtrieu/darkflow

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

Repository: https://github.com/thtrieu/darkflow
Canonical: https://ross.abutalabs.com/products/darkflow
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: tensorflow, graph, darknet, deep-learning, deep-neural-networks, convolutional-neural-networks, convolutional-networks, image-processing, object-detection, machine-learning, real-time, mobile-development
Last push: 2023-10-23T23:26:26+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3669, "days_push": 1045, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6139, forks 2016 (observed 2026-08-28T04:09:36.458169+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: deep-learning, computer-vision, machine-learning, image-processing
- platform: python, cross-platform
- tags: yolo, object-detection, darknet, tensorflow, cnn, real-time-detection, model-conversion, mobile-deployment, linux, macos, mobile

## Member repositories
- thtrieu/darkflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:36.458169+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:47:34.708569+00:00, confidence not recorded.
  - readme: https://github.com/thtrieu/darkflow (fetched 2026-08-28T04:09:36.458169+00:00, sha 2efcf9e28ba5)
- Data as of 2026-08-30T08:39:29.467469+00:00.