# pjreddie/darknet

Convolutional Neural Networks

Repository: https://github.com/pjreddie/darknet
Canonical: https://ross.abutalabs.com/products/darknet
Homepage: http://pjreddie.com/darknet/
Language: C
License: NOASSERTION
License Family: other
Last push: 2024-05-03T13:53:58+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4527, "days_push": 852, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26492, forks 21016 (observed 2026-08-28T04:11:46.987271+00:00)

## What it is
Darknet is an open-source neural network framework written in C and CUDA, best known as the original home of the YOLO real-time object detection system. It supports CPU and GPU computation and includes tools for image classification, object detection, and training custom networks.

## Use cases
- run real-time object detection with yolo
- train a custom object detector on my own dataset
- classify images with resnet on cpu or gpu
- lightweight c neural network framework without python dependencies
- detect objects in images and video from the command line
- train an image classifier from scratch

## When to choose
- you want a fast, dependency-light C/CUDA framework for YOLO-style object detection
- you need real-time inference on CPU or NVIDIA GPU without a Python stack
- you want to reproduce or build on classic YOLOv1-v4 research

## When to avoid
- you need modern tooling, Python APIs, or active development - consider PyTorch-based YOLO implementations
- you need non-vision tasks like transformers or large-scale training
- you require a permissive license - the licensing here is non-standard

## Facets
- artifact type: framework
- maturity: maintenance
- function: deep-learning, machine-learning, computer-vision, image-processing, gpu-computing
- domain: deep-learning, computer-vision, machine-learning, gpu-computing
- platform: cpp
- tags: yolo, object-detection, cuda, neural-networks, c, real-time-inference, linux, macos, gpu

## Member repositories
- pjreddie/darknet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:46.987271+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 2026-08-29T16:55:51.797703+00:00, confidence not recorded.
  - readme: https://github.com/pjreddie/darknet (fetched 2026-08-28T04:11:46.987271+00:00, sha 6ad278153db3)
  - homepage: http://pjreddie.com/darknet/ (fetched 2026-08-29T07:52:08.595150+00:00, sha 4835fa4782ca)
  - site_page: https://pjreddie.com/darknet/install (fetched 2026-08-29T07:52:08.604435+00:00, sha cba6380db3d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.