Darknet: Open Source Neural Networks in C

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation. You can find the source on GitHub or you can read more about what Darknet can do right here:

Installing Darknet

Darknet is easy to install and run. This post will guide you through it.

YOLO: Real-Time Object Detection

You only look once (YOLO) is a state-of-the-art, real-time object detection system.

ImageNet Classification

Classify images with popular models like ResNet and ResNeXt.


Use Darknet's black magic to conjure ghosts, ghouls, and wild badgermoles. But be warned, ye who enter here: no one is safe in the land of nightmares.

RNNs in Darknet

Recurrent neural networks are all the rage for time-series data and NLP. Learn how to use them in Darknet!

DarkGo: Go in Darknet

Play Go using a policy network trained with Darknet

Tiny Darknet

Image classification made tiny.

Train a Classifier on CIFAR-10

Learn how to train a classifier from scratch in Darknet.

Hardware Guide: Neural Networks on GPUs (Updated 2016-1-30)

I've had a number of people ask me what hardware I would recommend for training neural networks for vision applications. Here are some of my thoughts.


If you use Darknet in your research please cite it:

  author =   {Joseph Redmon},
  title =    {Darknet: Open Source Neural Networks in C},
  howpublished = {\url{http://pjreddie.com/darknet/}},
  year = {2013--2016}


For questions or help with Darknet please contact the Darknet mailing list. I will respond to questions as soon as possible!