Darknet_YOLO目标检测框架_Darknet_YOLO object detection framework.z

# Table of Contents * [Darknet Object Detection Framework and YOLO](#darknet-object-detection-framework-and-yolo) * [Papers](#papers) * [General Information](#general-information) * [Darknet Version](#darknet-version) * [Pre-trained Weights](#pre-trained-weights) * [People-R-People Pre-trained Weights](#people-r-people-pre-trained-weights) * [MSCOCO Pre-trained Weights](#mscoco-pre-trained-weights) * [Building](#building) * [Google Colab](#google-colab) * [WSL](#wsl) * [Linux CMake Method](#linux-cmake-method) * [Windows CMake Method](#windows-cmake-method) * [Docker](#docker) * [Using Darknet](#using-darknet) * [CLI](#cli) * [Training](#training) * [Other Tools and Links](#other-tools-and-links) * [Roadmap](#roadmap) * [Short-term goals](#short-term-goals) * [Mid-term goals](#mid-term-goals) * [Long-term goals](#long-term-goals) # Darknet Object Detection Framework and YOLO  Darknet is an open source neural network framework written in C, C++, and CUDA. YOLO (You Only Look Once) is a state-of-the-art, real-time, object detection system, which runs in the Darknet framework. * 2025-08: Darknet/YOLO repo has moved to **[Codeberg.org/CCodeRun/darknet/](https://codeberg.org/CCodeRun/darknet/)** * All commits are automatically mirrored from Codeberg to the older Hank.ai GitHub repo. * See the **[Darknet/YOLO web site](https://darknetcv.ai/)** * Please read through the **[Darknet/YOLO FAQ](https://www.ccoderun.ca/programming/darknet_faq/)** * Join the **[Darknet/YOLO discord server](https://discord.gg/CPZJPSYZU2)** # Papers * Paper **[YOLOv7](https://arxiv.org/abs/2207.02696)** * Paper **[Scaled-YOLOv4](https://openaccess.thecvf.com/content/CVPR2021/html/Wang_Scaled-YOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.html)** * Paper **[YOLOv4](https://arxiv.org/abs/2004.10934)** * Paper **[YOLOv3](https://arxiv.org/abs/1804.02767)** # General Information The Darknet/YOLO framework continues to be both **faster** and **more accurate** than other frameworks and versions of YOLO. This framework is both **completely free** and **open source**. You can incorporate Darknet/YOLO into existing projects and products -- including commercial ones -- without a license or paying a fee. Darknet V3 ("Jazz") released in October 2024 can accurately run the LEGO dataset videos at up to **1000 FPS** when using a NVIDIA RTX 3090 GPU, meaning each video frame is read, resized, and processed by Darknet/YOLO in 1 millisecond or less. Additional performance improvements have been implemented in Darknet V4 and the upcoming Darknet V5, without compromising the quality of detections. Please join the Darknet/YOLO Discord server if you need help or you want to discuss Darknet/YOLO and related tools: https://discord.gg/CPZJPSYZU2 The CPU version of Darknet/YOLO can run on simple devices such as Raspberry Pi, cloud &amp; colab servers, desktops, laptops, and high-end training rigs. The GPU version of Darknet/YOLO requires either a CUDA-capable GPU from NVIDIA, or a ROCm-capable GPU from AMD. Darknet/YOLO is known to work on Linux, Windows, and Mac. See the [building instructions](#building) below. ## Darknet Version * The original Darknet tool written by Joseph Redmon in 2013-2017 did not have a version number. We consider this version 0.x. * The next popular Darknet repo maintained by Alexey Bochkovskiy between 2017-2021 also did not have a version number. We consider this version 1.x. * The Darknet repo sponsored by Hank.ai and maintained by Stéphane Charette starting in 2023 was the first one with a `version` command. From 2023 until late 2024, it returned version 2.x "OAK". * The goal was to try and break as little of the existing functionality while getting familiar with the codebase. * Re-wrote the build steps so we have 1 unified way to build using CMake on Windows, Linux, and Mac. * Converted the codebase to use the C++ compiler. * Enhanced chart.png while training. * Bug fixes and performance-related optimizations, mostly related to cutting down the time it takes to train a network. * The last branch of this codebase is version 2.1 in the `v2` branch. * The next phase of development started in mid-2024 and was released in October 2024. The `version` command now returns 3.x "JAZZ". * Removed many old and unmaintained commands. * You can always do a checkout of the previous `v2` branch if you need to run one of these commands. Let us know so we can investigate adding back any missing commands. * Many performance optimizations, both when training and during inference. * Legacy C API was modified; applications that use the original Darknet API will need minor modifications: https://darknetcv.ai/api/api.html * New Darknet V3 C and C++ API to make it easier for developers to write applications that use Darknet/YOLO: https://darknetcv.ai/api/api.html * New apps and sample code in `src-examples`: https://darknetcv.ai/api/files.html * The next release was in early 2025. The `version` command now returns 4.x "SLATE". * Added support for AMD GPUs using ROCm. * Still need to add support for MIOpen. * All `printf()` and `std::cout` calls have all been replaced so Darknet/YOLO logging messages can easily be redirected. * The latest release was in August 2025. The `version` command now returns 5.x "Moonlit". * Move source code repo from github to [codeberg](https://codeberg.org/CCodeRun/darknet#table-of-contents). * More performance optimizations. * Use of OpenBLAS when building CPU-only versions of Darknet. * Support for Profile-Guided Optimization. * ONNX export functionality. [experimental] * JAVA language bindings. [incomplete, in-progress] # Pre-trained Weights People are generally expected to [train their own network](#training). But pre-trained weights are also popular. These are weights which someone else has trained and made available for free on the internet. This is sometimes convenient when first installing Darknet/YOLO, since the software can be quickly tested without having to train a new neural network. * [People-R-People Pre-trained Weights](#people-r-people-pre-trained-weights) (2 classes, `person` and `head`) * [MSCOCO Pre-trained Weights](#mscoco-pre-trained-weights) (80 classes covering a large range of objects, such as `person`, `backpack`, `chair`, `clock`, ...) * There are several other simple datasets and pre-trained weights available for testing Darknet/YOLO, such as [LEGO Gears](https://www.ccoderun.ca/programming/2024-05-01_LegoGears/) and [Rolodex](https://www.ccoderun.ca/programming/2023-11-06_Rolodex/). See <a target="_blank" href="https://www.ccoderun.ca/programming/yolo_faq/#datasets">the Darknet/YOLO FAQ</a> for details. ## People-R-People Pre-trained Weights The People-R-People pre-trained weights are used to find people. This dataset only has 2 classes: `person` and `head`.  You can download these pre-trained weights directly from [C Code Run's web site](https://www.ccoderun.ca/programming/2025-01-20_People-R-People/). ## MSCOCO Pre-trained Weights Several popular versions of YOLO were pre-trained for convenience on the [MSCOCO dataset](https://cocodataset.org/). This dataset has 80 classes, which can be seen in the text file [`cfg/coco.names`](cfg/coco.names). The MSCOCO pre-trained weights can be downloaded from several different locations, and are also available for download from this repo: * YOLOv2, November 2016 * [YOLOv2-tiny](https://github.com/hank-ai/darknet/issues/21#issuecomment-1807469361) * [YOLOv2-full](https://github.com/hank-ai/darknet/issues/21#issuecomment-1807478865) * YOLOv3, May 2018 * [YOLOv3-tiny](https://github.com/hank-ai/darknet/issues/21#issuecomment-1807479419) * [YOLOv3-full](https://github.com/hank-ai/darknet/issues/21#issuecomment-1807480139) * YOLOv4, May 2020 * [Y