Darknet/YOLO

• Download Darknet/YOLO from here: https://github.com/hank-ai/darknet

 

• If you want to use Darknet/YOLO, please see the FAQ with many common questions and answers.
• Note Hank.ai's announcement in May 2023 on officially sponsoring the Darknet/YOLO codebase.
• The Darknet source repo location has changed! Both the original pjreddie and alexeyab repos are abandoned. The new repo to use for Darknet is hosted by Hank.ai. See this link for details: https://www.ccoderun.ca/programming/darknet_faq/#which_repos_to_use_and_avoid
• Direct link to the new GitHub source code repo for Darknet/YOLO: https://github.com/hank-ai/darknet.
• For assistance, please join the Darknet/YOLO Discord server: https://discord.gg/zSq8rtW.

Other related projects:

• DarkHelp is a professional, free, open-source CLI tool and C/C++/Python API to use Darknet/YOLO. The purpose behind DarkHelp is to makes things easier to use.
• DarkMark is a free open-source tool for managing Darknet/YOLO project, annotating images, videos, and PDFs, and generating Darknet/YOLO training files.
• Stéphane's YouTube channel with many "How-To" videos.

The Doxygen pages below are meant to assist software developers in understanding the source code. If you're looking for help with using Darknet/YOLO, see the links above.

• main()
• darknet_fatal_error()
• update_train_loss_chart()
• train_detector()
  • train_network() (CPU only)
  • train_network_waitkey() (1 GPU)
  • train_networks() (multi-GPU)
• display_loaded_images()
• display_iteration_summary()
• display_last_accuracy()
• Darknet::TimingAndTracking

darknet_utils.hpp:

• format_time()
• format_time_remaining()
• format_loss()
• format_map_accuracy()
• in_colour()