{"id":72714,"url":"https://github.com/coderonion/awesome-yolo-object-detection","name":"awesome-yolo-object-detection","description":"🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.","projects_count":1704,"last_synced_at":"2026-08-10T22:00:24.166Z","repository":{"id":39725493,"uuid":"461270746","full_name":"coderonion/awesome-yolo-object-detection","owner":"coderonion","description":"🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.","archived":false,"fork":false,"pushed_at":"2025-05-31T02:13:33.000Z","size":398,"stargazers_count":1776,"open_issues_count":1,"forks_count":236,"subscribers_count":36,"default_branch":"main","last_synced_at":"2026-08-05T16:46:53.234Z","etag":null,"topics":["cuda","datasets","deepseek","few-shot-object-detection","gui","llama","llm","mllm","object-detection","object-detection-datasets","open-world-object-detection","qwen","rknn","snn","spiking-neural-network","tensorrt","vlm","yolo","yolov5","yolov8"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/coderonion.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-02-19T17:57:06.000Z","updated_at":"2026-08-04T17:46:36.000Z","dependencies_parsed_at":"2024-01-14T10:24:36.084Z","dependency_job_id":"a562d80b-05be-476a-890f-e6ea1f692ced","html_url":"https://github.com/coderonion/awesome-yolo-object-detection","commit_stats":{"total_commits":387,"total_committers":12,"mean_commits":32.25,"dds":0.5142118863049095,"last_synced_commit":"80ae40fa3a72f5a3566077bfdaccb782c59812ef"},"previous_names":["codingonion/awesome-yolo-object-detection","coderonion/awesome-yolo-object-detection","sjinzh/awesome-yolo-object-detection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/coderonion/awesome-yolo-object-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coderonion%2Fawesome-yolo-object-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coderonion%2Fawesome-yolo-object-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coderonion%2Fawesome-yolo-object-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coderonion%2Fawesome-yolo-object-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/coderonion","download_url":"https://codeload.github.com/coderonion/awesome-yolo-object-detection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coderonion%2Fawesome-yolo-object-detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36341098,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-06T04:43:03.162Z","status":"ssl_error","status_checked_at":"2026-08-06T04:43:02.660Z","response_time":54,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-10-05T16:05:19.656Z","updated_at":"2026-08-10T22:00:24.167Z","primary_language":"Python","list_of_lists":false,"displayable":true,"categories":["Object Detection Datasets","Anti-UAV Datasets","Object Detection Applications","Blogs","Summary","Other Versions of YOLO","Videos","Lighter and Deployment Frameworks","Applications","Star History"],"sub_categories":[],"readme":"# Awesome-YOLO-Object-Detection\r\n[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\r\n\r\n🚀🚀🚀 YOLO is a great real-time one-stage object detection framework. This repository lists some awesome public YOLO object detection projects and datasets.\r\n\r\n## Contents\r\n- [Awesome-YOLO-Object-Detection](#awesome-yolo-object-detection)\r\n  - [Summary](#summary)\r\n    - [Famous YOLO](#famous-yolo)\r\n    - [Extensional Frameworks](#extensional-frameworks)\r\n    - [Awesome List](#awesome-list)\r\n    - [Paper and Code Overview](#paper-and-code-overview)\r\n      - [Paper Review](#paper-review)\r\n      - [Code Review](#code-review)\r\n    - [Learning Resources](#learning-resources)\r\n  - [Other Versions of YOLO](#other-versions-of-yolo)\r\n    - [PyTorch Implementation](#pytorch-implementation)\r\n    - [C Implementation](#c-implementation)\r\n    - [CPP Implementation](#cpp-implementation)\r\n    - [ROS Implementation](#ros-implementation)\r\n    - [Mojo Implementation](#mojo-implementation)\r\n    - [Rust Implementation](#rust-implementation)\r\n    - [Go Implementation](#go-implementation)\r\n    - [CSharp Implementation](#csharp-implementation)\r\n    - [Tensorflow and Keras Implementation](#tensorflow-and-keras-implementation)\r\n    - [PaddlePaddle Implementation](#paddlepaddle-implementation)\r\n    - [Caffe Implementation](#caffe-implementation)\r\n    - [MXNet Implementation](#mxnet-implementation)\r\n    - [Web Implementation](#web-implementation)\r\n    - [Others](#others)\r\n  - [Lighter and Deployment Frameworks](#lighter-and-deployment-frameworks)\r\n    - [High-performance Inference Engine](#high-performance-inference-engine)\r\n      - [ONNX](#onnx)\r\n      - [TensorRT](#tensorrt)\r\n      - [DeepStream](#deepstream)\r\n      - [OpenVINO](#openvino)\r\n      - [NCNN](#ncnn)\r\n      - [MNN](#mnn)\r\n      - [Other Engine](#other-engine)\r\n    - [NPU and FPGA Hardware Deployment](#npu-and-fpga-hardware-deployment)\r\n      - [RK3588](#rk3588)\r\n      - [FPGA](#fpga)\r\n      - [Other Hardware](#other-hardware)\r\n    - [Pruning Knoweldge-Distillation Quantization](#pruning-knoweldge-distillation-quantization)\r\n      - [Pruning](#pruning)\r\n      - [Quantization](#quantization)\r\n      - [Knoweldge-Distillation](#knoweldge-distillation)\r\n    - [Lightweight Backbones and FPN](#lightweight-backbones-and-fpn)\r\n  - [Object Detection Applications](#object-detection-applications)\r\n    - [Open World Object Detection](#open-world-object-detection)\r\n    - [Few-shot Object Detection](#few-shot-object-detection)\r\n    - [Small Object Detection](#small-object-detection)\r\n    - [Multimodal Image Detection](#multimodal-image-detection)\r\n    - [Video Object Detection](#video-object-detection)\r\n    - [Object Tracking](#object-tracking)\r\n      - [Multi-Object Tracking](#multi-object-tracking)\r\n      - [Dynamic Object Tracking](#Dynamic-object-tracking)\r\n    - [Deep Reinforcement Learning](#deep-reinforcement-learning)\r\n    - [Motion Control Field](#motion-control-field)\r\n    - [Super-Resolution Field](#super-resolution-field)\r\n    - [Spiking Neural Network](#spiking-neural-network)\r\n    - [Attention and Transformer](#attention-and-transformer)\r\n    - [Oriented Object Detection](#oriented-object-detection)\r\n    - [Face Detection and Recognition](#face-detection-and-recognition)\r\n      - [Face Detection](#face-detection)\r\n      - [Face Recognition](#face-recognition)\r\n    - [Face Mask Detection](#face-mask-detection)\r\n    - [Social Distance Detection](#social-distance-detection)\r\n    - [Autonomous Driving Field Detection](#autonomous-driving-field-detection)\r\n      - [Vehicle Detection](#vehicle-detection)\r\n      - [License Plate Detection and Recognition](#license-plate-detection-and-recognition)\r\n      - [Lane Detection](#lane-detection)\r\n      - [Driving Behavior Detection](#driving-behavior-detection)\r\n      - [Parking Slot Detection](#parking-slot-detection)\r\n      - [Traffic Light Detection](#traffic-light-detection)\r\n      - [Traffic Sign Detection](#traffic-sign-detection)\r\n      - [Crosswalk Detection](#crosswalk-detection)\r\n      - [Traffic Accidents Detection](#traffic-accidents-detection)\r\n      - [Road Damage Detection](#road-damage-detection)\r\n    - [Animal Detection](#animal-detection)\r\n    - [Helmet Detection](#helmet-detection)\r\n    - [Hand Detection](#hand-detection)\r\n    - [Gesture Recognition](#gesture-recognition)\r\n    - [Action Detection](#action-detection)\r\n    - [Emotion Recognition](#emotion-recognition)\r\n    - [Human Pose Estimation](#human-pose-estimation)\r\n    - [Distance Measurement](#distance-measurement)\r\n    - [Instance and Semantic Segmentation](#instance-and-semantic-segmentation)\r\n    - [3D Object Detection](#3d-object-detection)\r\n    - [SLAM Field Detection](#slam-field-detection)\r\n    - [Industrial Defect Detection](#industrial-defect-detection)\r\n    - [SAR Image Detection](#sar-image-detection)\r\n    - [Safety Monitoring Field Detection](#safety-monitoring-field-detection)\r\n    - [Anti-UAV Field Detection](#anti-uav-field-detection)\r\n    - [Medical Field Detection](#medical-field-detection)\r\n    - [Chemistry Field Detection](#chemistry-field-detection)\r\n    - [Agricultural Field Detection](#agricultural-field-detection)\r\n    - [Sports Field Detection](#sports-field-detection)\r\n    - [Aerial Imagery Detection](#aerial-imagery-detection)\r\n    - [Adverse Weather Conditions](#adverse-weather-conditions)\r\n    - [Adversarial Attack and Defense](#adversarial-attack-and-defense)\r\n    - [Camouflaged Detection](#camouflaged-detection)\r\n    - [Game Field Detection](#game-field-detection)\r\n    - [Automatic Annotation Tools](#automatic-annotation-tools)\r\n    - [Feature Map Visualization](#feature-map-visualization)\r\n    - [Object Detection Evaluation Metrics](#object-detection-evaluation-metrics)\r\n    - [GUI](#gui)\r\n        - [Swift-Related](#swift-related)\r\n        - [Flutter-Related](#flutter-related)\r\n        - [Streamlit-Related](#streamlit-related)\r\n        - [Gradio-Related](#gradio-related)\r\n        - [QT-Related](#qt-related)\r\n        - [PySide-Related](#pyside-related)\r\n    - [Other Applications](#other-applications)\r\n  - [Object Detection Datasets](#object-detection-datasets)\r\n    - [Datasets Share Platform](#datasets-share-platform)\r\n    - [Datasets Tools](#datasets-tools)\r\n        - [Data Annotation](#data-annotation)\r\n        - [Data Augmentation](#data-augmentation)\r\n        - [Data Management](#data-management)\r\n    - [General Detection and Recognition Datasets](#general-detection-and-recognition-datasets)\r\n        - [General Object Detection Datasets](#general-object-detection-datasets)\r\n        - [General Object Recognition Datasets](#general-object-recognition-datasets)\r\n    - [Autonomous Driving Datasets](#autonomous-driving-datasets)\r\n        - [Diverse Autonomous Driving Datasets](#diverse-autonomous-driving-datasets)\r\n        - [Traffic Sign Detection Datasets](#traffic-sign-detection-datasets)\r\n        - [License Plate Detection and Recognition Datasets](#license-plate-detection-and-recognition-datasets)\r\n    - [Adverse Weather Datasets](#adverse-weather-datasets)\r\n    - [Person Detection Datasets](#person-detection-datasets)\r\n    - [Anti-UAV Datasets](#anti-uav-datasets)\r\n    - [Optical Aerial Imagery Datasets](#optical-aerial-imagery-datasets)\r\n    - [Low-light Image Datasets](#low-light-image-datasets)\r\n    - [Infrared Image Datasets](#infrared-image-datasets)\r\n    - [SAR Image Datasets](#sar-image-datasets)\r\n    - [Sonar Image Datasets](#sonar-image-datasets)\r\n    - [Multimodal Image Datasets](#multimodal-image-datasets)\r\n    - [3D Object Detection Datasets](#3d-object-detection-datasets)\r\n    - [Vehicle-to-Everything Field Datasets](#vehicle-to-everything-field-datasets)\r\n    - [Super-Resolution Field Datasets](#super-resolution-field-datasets)\r\n    - [Face Detection and Recognition Datasets](#general-detection-and-recognition-datasets)\r\n        - [Face Detection Datasets](#face-detection-datasets)\r\n        - [Face Recognition Datasets](#face-recognition-datasets)\r\n  - [Blogs](#blogs)\r\n  - [Videos](#videos)\r\n\r\n\r\n\r\n## Summary\r\n\r\n  - ### Famous YOLO\r\n\r\n    - [YOLOv1](https://pjreddie.com/darknet/yolov1) ([Darknet](https://github.com/pjreddie/darknet) \u003cimg src=\"https://img.shields.io/github/stars/pjreddie/darknet?style=social\"/\u003e) : \"You Only Look Once: Unified, Real-Time Object Detection\". (**[CVPR 2016](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Redmon_You_Only_Look_CVPR_2016_paper.html)**)\r\n\r\n    - [YOLOv2](https://pjreddie.com/darknet/yolov2) ([Darknet](https://github.com/pjreddie/darknet) \u003cimg src=\"https://img.shields.io/github/stars/pjreddie/darknet?style=social\"/\u003e) : \"YOLO9000: Better, Faster, Stronger\". (**[CVPR 2017](https://openaccess.thecvf.com/content_cvpr_2017/html/Redmon_YOLO9000_Better_Faster_CVPR_2017_paper.html)**)\r\n\r\n    - [YOLOv3](https://pjreddie.com/darknet/yolo) ([Darknet](https://github.com/pjreddie/darknet) \u003cimg src=\"https://img.shields.io/github/stars/pjreddie/darknet?style=social\"/\u003e) : \"YOLOv3: An Incremental Improvement\". (**[arXiv 2018](https://arxiv.org/abs/1804.02767)**)\r\n\r\n    - [YOLOv4](https://github.com/AlexeyAB/darknet) \u003cimg src=\"https://img.shields.io/github/stars/AlexeyAB/darknet?style=social\"/\u003e ([WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/PyTorch_YOLOv4?style=social\"/\u003e) : \"YOLOv4: Optimal Speed and Accuracy of Object Detection\". (**[arXiv 2020](https://arxiv.org/abs/2004.10934)**)\r\n\r\n    - [Scaled-YOLOv4](https://github.com/AlexeyAB/darknet) \u003cimg src=\"https://img.shields.io/github/stars/AlexeyAB/darknet?style=social\"/\u003e ([WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/ScaledYOLOv4?style=social\"/\u003e) : \"Scaled-YOLOv4: Scaling Cross Stage Partial Network\". (**[CVPR 2021](https://openaccess.thecvf.com/content/CVPR2021/html/Wang_Scaled-YOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.html)**)\r\n\r\n    - [YOLOv5](https://github.com/ultralytics/yolov5) \u003cimg src=\"https://img.shields.io/github/stars/ultralytics/yolov5?style=social\"/\u003e : YOLOv5 🚀 in PyTorch \u003e ONNX \u003e CoreML \u003e TFLite. [docs.ultralytics.com](https://docs.ultralytics.com/). YOLOv5 🚀 is the world's most loved vision AI, representing [Ultralytics](https://ultralytics.com/) open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.\r\n\r\n    - [YOLOv6](https://github.com/meituan/YOLOv6) \u003cimg src=\"https://img.shields.io/github/stars/meituan/YOLOv6?style=social\"/\u003e : \"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications\". (**[arXiv 2022](https://arxiv.org/abs/2209.02976)**).\r\n\r\n    - [YOLOv7](https://github.com/WongKinYiu/yolov7) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/yolov7?style=social\"/\u003e : \"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors\". (**[CVPR 2023](https://arxiv.org/abs/2207.02696)**).\r\n\r\n    - [YOLOv8](https://github.com/ultralytics/ultralytics) \u003cimg src=\"https://img.shields.io/github/stars/ultralytics/ultralytics?style=social\"/\u003e : NEW - YOLOv8 🚀 in PyTorch \u003e ONNX \u003e OpenVINO \u003e CoreML \u003e TFLite. [docs.ultralytics.com](https://docs.ultralytics.com/)\r\n\r\n    - [YOLOv9](https://github.com/WongKinYiu/yolov9) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/yolov9?style=social\"/\u003e : \"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information\". (**[arXiv 2024](https://arxiv.org/abs/2402.13616)**)\r\n\r\n    - [MultimediaTechLab/YOLO](https://github.com/MultimediaTechLab/YOLO) \u003cimg src=\"https://img.shields.io/github/stars/MultimediaTechLab/YOLO?style=social\"/\u003e : YOLO: Official Implementation of YOLOv9, YOLOv7, YOLO-RD. Welcome to the official implementation of YOLOv7 and YOLOv9, YOLO-RD. This repository will contains the complete codebase, pre-trained models, and detailed instructions for training and deploying YOLOv9.\r\n\r\n    - [YOLOv10](https://github.com/THU-MIG/yolov10) \u003cimg src=\"https://img.shields.io/github/stars/THU-MIG/yolov10?style=social\"/\u003e : \"YOLOv10: Real-Time End-to-End Object Detection\". (**[arXiv 2024](https://arxiv.org/abs/2405.14458v1)**)\r\n\r\n    - [YOLOv11](https://github.com/ultralytics/ultralytics) \u003cimg src=\"https://img.shields.io/github/stars/ultralytics/ultralytics?style=social\"/\u003e : NEW - YOLOv8 🚀 in PyTorch \u003e ONNX \u003e OpenVINO \u003e CoreML \u003e TFLite. [Ultralytics](https://www.ultralytics.com/) [YOLOv11](https://github.com/ultralytics/ultralytics) s a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLO11 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks. [docs.ultralytics.com](https://docs.ultralytics.com/)\r\n\r\n    - [YOLOv12](https://github.com/sunsmarterjie/yolov12) \u003cimg src=\"https://img.shields.io/github/stars/sunsmarterjie/yolov12?style=social\"/\u003e : \"YOLOv12: Attention-Centric Real-Time Object Detectors\". (**[arXiv 2025](https://arxiv.org/abs/2502.12524)**)\r\n\r\n    - [YOLO-World | YOLO-World-v2](https://github.com/AILab-CVC/YOLO-World) \u003cimg src=\"https://img.shields.io/github/stars/AILab-CVC/YOLO-World?style=social\"/\u003e : \"YOLO-World: Real-Time Open-Vocabulary Object Detection\". (**[CVPR 2024](https://arxiv.org/abs/2401.17270)**). [www.yoloworld.cc](https://www.yoloworld.cc/)\r\n\r\n    - [YOLOE](https://github.com/THU-MIG/yoloe) \u003cimg src=\"https://img.shields.io/github/stars/THU-MIG/yoloe?style=social\"/\u003e : \"YOLOE: Real-Time Seeing Anything\". (**[arXiv 2025](https://arxiv.org/abs/2503.07465)**).\r\n\r\n\r\n\r\n  - ### Extensional Frameworks\r\n\r\n    - [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL) \u003cimg src=\"https://img.shields.io/github/stars/QwenLM/Qwen2-VL?style=social\"/\u003e : Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud. \"Qwen2.5-VL Technical Report\". (**[arXiv 2025](https://arxiv.org/abs/2502.13923)**). [2025-01-26，Qwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL!](https://qwenlm.github.io/blog/qwen2.5-vl/). \"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution\". (**[arXiv 2024](https://arxiv.org/abs/2409.12191)**). \"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond\". (**[arXiv 2023](https://arxiv.org/abs/2308.12966)**).\r\n\r\n    - [Kimi-VL](https://github.com/MoonshotAI/Kimi-VL) \u003cimg src=\"https://img.shields.io/github/stars/MoonshotAI/Kimi-VL?style=social\"/\u003e : Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities. \"Kimi-VL Technical Report\". (**[arXiv 2025](https://arxiv.org/abs/2504.07491)**).\r\n\r\n    - [Visual-RFT](https://github.com/Liuziyu77/Visual-RFT) \u003cimg src=\"https://img.shields.io/github/stars/Liuziyu77/Visual-RFT?style=social\"/\u003e : 🌈We introduce Visual Reinforcement Fine-tuning (Visual-RFT), the first comprehensive adaptation of Deepseek-R1's RL strategy to the multimodal field. We use the Qwen2-VL-2/7B model as our base model and design a rule-based verifiable reward, which is integrated into a GRPO-based reinforcement fine-tuning framework to enhance the performance of LVLMs across various visual perception tasks. ViRFT extends R1's reasoning capabilities to multiple visual perception tasks, including various detection tasks like Open Vocabulary Detection, Few-shot Detection, Reasoning Grounding, and Fine-grained Image Classification. \"Visual-RFT: Visual Reinforcement Fine-Tuning\". (**[arXiv 2025](https://arxiv.org/abs/2503.01785)**).\r\n\r\n    - [VLM-R1](https://github.com/om-ai-lab/VLM-R1) \u003cimg src=\"https://img.shields.io/github/stars/om-ai-lab/VLM-R1?style=social\"/\u003e : VLM-R1: A stable and generalizable R1-style Large Vision-Language Model. Solve Visual Understanding with Reinforced VLMs. [2025-03-20，Improving Object Detection through Reinforcement Learning with VLM-R1](https://om-ai-lab.github.io/2025_03_20.html).\r\n\r\n    - Florence-2 : \"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks\". (**[CVPR 2024](https://arxiv.org/abs/2311.06242)**).\r\n\r\n    - [maestro](https://github.com/roboflow/maestro) \u003cimg src=\"https://img.shields.io/github/stars/roboflow/maestro?style=social\"/\u003e : VLM fine-tuning for everyone. maestro is a streamlined tool to accelerate the fine-tuning of multimodal models. By encapsulating best practices from our core modules, maestro handles configuration, data loading, reproducibility, and training loop setup. It currently offers ready-to-use recipes for popular vision-language models such as [Florence-2](https://arxiv.org/abs/2311.06242), PaliGemma 2, and [Qwen2.5-VL](https://github.com/QwenLM/Qwen2.5-VL). [maestro.roboflow.com](https://maestro.roboflow.com/latest/)\r\n\r\n    - [Autodistill](https://github.com/autodistill/autodistill) \u003cimg src=\"https://img.shields.io/github/stars/autodistill/autodistill?style=social\"/\u003e : Images to inference with no labeling (use foundation models to train supervised models). Autodistill uses big, slower foundation models to train small, faster supervised models. Using autodistill, you can go from unlabeled images to inference on a custom model running at the edge with no human intervention in between. [docs.autodistill.com](https://docs.autodistill.com/)\r\n\r\n    - [EdgeYOLO](https://github.com/LSH9832/edgeyolo) \u003cimg src=\"https://img.shields.io/github/stars/LSH9832/edgeyolo?style=social\"/\u003e : an edge-real-time anchor-free object detector with decent performance. \"Edge YOLO: Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles\". (**[IEEE Transactions on Intelligent Transportation Systems, 2022](https://ieeexplore.ieee.org/abstract/document/9740044)**). \"EdgeYOLO: An Edge-Real-Time Object Detector\". (**[arXiv 2023](https://arxiv.org/abs/2302.07483)**)\r\n\r\n    - [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) \u003cimg src=\"https://img.shields.io/github/stars/Megvii-BaseDetection/YOLOX?style=social\"/\u003e : \"YOLOX: Exceeding YOLO Series in 2021\". (**[arXiv 2021](https://arxiv.org/abs/2107.08430)**)\r\n\r\n    - [YOLOR](https://github.com/WongKinYiu/yolor) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/yolor?style=social\"/\u003e : \"You Only Learn One Representation: Unified Network for Multiple Tasks\". (**[arXiv 2021](https://arxiv.org/abs/2105.04206)**)\r\n\r\n    - [YOLOF](https://github.com/megvii-model/YOLOF) \u003cimg src=\"https://img.shields.io/github/stars/megvii-model/YOLOF?style=social\"/\u003e : \"You Only Look One-level Feature\". (**[CVPR 2021](https://openaccess.thecvf.com/content/CVPR2021/html/Chen_You_Only_Look_One-Level_Feature_CVPR_2021_paper.html)**).\r\n\r\n    - [YOLOS](https://github.com/hustvl/YOLOS) \u003cimg src=\"https://img.shields.io/github/stars/hustvl/YOLOS?style=social\"/\u003e : \"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection\". (**[NeurIPS 2021](https://proceedings.neurips.cc//paper/2021/hash/dc912a253d1e9ba40e2c597ed2376640-Abstract.html)**)\r\n\r\n    - [DAMO-YOLO](https://github.com/tinyvision/DAMO-YOLO) \u003cimg src=\"https://img.shields.io/github/stars/tinyvision/DAMO-YOLO?style=social\"/\u003e : DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement. \"DAMO-YOLO : A Report on Real-Time Object Detection Design\". (**[arXiv 2022](https://arxiv.org/abs/2211.15444)**)\r\n\r\n    - [YOLO-NAS](https://github.com/Deci-AI/super-gradients) \u003cimg src=\"https://img.shields.io/github/stars/Deci-AI/super-gradients?style=social\"/\u003e : Easily train or fine-tune SOTA computer vision models with one open source training library. The home of [Yolo-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md). [www.supergradients.com](https://www.supergradients.com/). YOLO-NAS and YOLO-NAS-POSE architectures are out! The new YOLO-NAS delivers state-of-the-art performance with the unparalleled accuracy-speed performance, outperforming other models such as YOLOv5, YOLOv6, YOLOv7 and YOLOv8.\r\n\r\n    - [LeYOLO](https://github.com/LilianHollard/LeYOLO) \u003cimg src=\"https://img.shields.io/github/stars/LilianHollard/LeYOLO?style=social\"/\u003e : \"LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection\". (**[arXiv 2024](https://arxiv.org/abs/2406.14239)**)\r\n\r\n    - [DynamicDet](https://github.com/VDIGPKU/DynamicDet) \u003cimg src=\"https://img.shields.io/github/stars/VDIGPKU/DynamicDet?style=social\"/\u003e : \"DynamicDet: A Unified Dynamic Architecture for Object Detection\". (**[CVPR 2023](https://arxiv.org/abs/2304.05552)**)\r\n\r\n    - [DINO](https://github.com/IDEA-Research/DINO) \u003cimg src=\"https://img.shields.io/github/stars/IDEA-Research/DINO?style=social\"/\u003e : \"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection\". (**[ICLR 2023](https://arxiv.org/abs/2203.03605)**).\r\n\r\n    - [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO) \u003cimg src=\"https://img.shields.io/github/stars/IDEA-Research/GroundingDINO?style=social\"/\u003e : \"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection\". (**[ECCV 2024](https://arxiv.org/abs/2303.05499)**).\r\n\r\n    - [RT-DETR | RT-DETRv2](https://github.com/lyuwenyu/RT-DETR) \u003cimg src=\"https://img.shields.io/github/stars/lyuwenyu/RT-DETR?style=social\"/\u003e : \"DETRs Beat YOLOs on Real-time Object Detection\". (**[CVPR 2024](https://arxiv.org/abs/2304.08069)**). \"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer\". (**[arXiv 2024](https://arxiv.org/abs/2407.17140)**).\r\n\r\n    - [EasyCV](https://github.com/alibaba/EasyCV) \u003cimg src=\"https://img.shields.io/github/stars/alibaba/EasyCV?style=social\"/\u003e : An all-in-one toolkit for computer vision. \"YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6\". (**[arXiv 2022](https://arxiv.org/abs/2208.13040)**).\r\n\r\n    - [YOLACT \u0026 YOLACT++](https://github.com/dbolya/yolact) \u003cimg src=\"https://img.shields.io/github/stars/dbolya/yolact?style=social\"/\u003e : You Only Look At CoefficienTs. (**[ICCV 2019](https://openaccess.thecvf.com/content_ICCV_2019/html/Bolya_YOLACT_Real-Time_Instance_Segmentation_ICCV_2019_paper.html), [IEEE TPAMI 2020](https://ieeexplore.ieee.org/abstract/document/9159935)**)\r\n\r\n    - [Alpha-IoU](https://github.com/Jacobi93/Alpha-IoU) \u003cimg src=\"https://img.shields.io/github/stars/Jacobi93/Alpha-IoU?style=social\"/\u003e : \"Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression\". (**[NeurIPS 2021](https://proceedings.neurips.cc//paper/2021/hash/a8f15eda80c50adb0e71943adc8015cf-Abstract.html)**)\r\n\r\n    - [CIoU](https://github.com/Zzh-tju/CIoU) \u003cimg src=\"https://img.shields.io/github/stars/Zzh-tju/CIoU?style=social\"/\u003e : Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT). (**[AAAI 2020](https://ojs.aaai.org/index.php/AAAI/article/view/6999), [IEEE TCYB 2021](https://ieeexplore.ieee.org/abstract/document/9523600)**)\r\n\r\n    - [Albumentations](https://github.com/albumentations-team/albumentations) \u003cimg src=\"https://img.shields.io/github/stars/albumentations-team/albumentations?style=social\"/\u003e : Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to increase the quality of trained models. The purpose of image augmentation is to create new training samples from the existing data. \"Albumentations: Fast and Flexible Image Augmentations\". (**[Information 2020](https://www.mdpi.com/2078-2489/11/2/125)**)\r\n\r\n    - [doubleZ0108/Data-Augmentation](https://github.com/doubleZ0108/Data-Augmentation) \u003cimg src=\"https://img.shields.io/github/stars/doubleZ0108/Data-Augmentation?style=social\"/\u003e : General Data Augmentation Algorithms for Object Detection(esp. Yolo).\r\n\r\n\r\n\r\n\r\n  - ### Awesome List\r\n\r\n    - [awesome-yolo-object-detection](https://github.com/coderonion/awesome-yolo-object-detection) \u003cimg src=\"https://img.shields.io/github/stars/coderonion/awesome-yolo-object-detection?style=social\"/\u003e : 🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.\r\n\r\n    - [srebroa/awesome-yolo](https://github.com/srebroa/awesome-yolo) \u003cimg src=\"https://img.shields.io/github/stars/srebroa/awesome-yolo?style=social\"/\u003e : 🚀 ⭐ The list of the most popular YOLO algorithms - awesome YOLO.\r\n\r\n    - [Bubble-water/YOLO-Summary](https://github.com/Bubble-water/YOLO-Summary) \u003cimg src=\"https://img.shields.io/github/stars/Bubble-water/YOLO-Summary?style=social\"/\u003e : YOLO-Summary.\r\n\r\n    - [WZMIAOMIAO/deep-learning-for-image-processing](https://github.com/WZMIAOMIAO/deep-learning-for-image-processing) \u003cimg src=\"https://img.shields.io/github/stars/WZMIAOMIAO/deep-learning-for-image-processing?style=social\"/\u003e : deep learning for image processing including classification and object-detection etc.\r\n\r\n    - [hoya012/deep_learning_object_detection](https://github.com/hoya012/deep_learning_object_detection) \u003cimg src=\"https://img.shields.io/github/stars/hoya012/deep_learning_object_detection?style=social\"/\u003e : A paper list of object detection using deep learning.\r\n\r\n    - [amusi/awesome-object-detection](https://github.com/amusi/awesome-object-detection) \u003cimg src=\"https://img.shields.io/github/stars/amusi/awesome-object-detection?style=social\"/\u003e : Awesome Object Detection.\r\n\r\n\r\n    - [wenhwu/awesome-remote-sensing-change-detection](https://github.com/wenhwu/awesome-remote-sensing-change-detection) \u003cimg src=\"https://img.shields.io/github/stars/wenhwu/awesome-remote-sensing-change-detection?style=social\"/\u003e : List of datasets, codes, and contests related to remote sensing change detection.\r\n\r\n    - [ZHOUYI1023/awesome-radar-perception](https://github.com/ZHOUYI1023/awesome-radar-perception) \u003cimg src=\"https://img.shields.io/github/stars/ZHOUYI1023/awesome-radar-perception?style=social\"/\u003e : A curated list of radar datasets, detection, tracking and fusion.\r\n\r\n    - [lartpang/awesome-segmentation-saliency-dataset](https://github.com/lartpang/awesome-segmentation-saliency-dataset) \u003cimg src=\"https://img.shields.io/github/stars/lartpang/awesome-segmentation-saliency-dataset?style=social\"/\u003e : A collection of some datasets for segmentation / saliency detection. Welcome to PR...😄\r\n\r\n    - [TianhaoFu/Awesome-3D-Object-Detection](https://github.com/TianhaoFu/Awesome-3D-Object-Detection) \u003cimg src=\"https://img.shields.io/github/stars/TianhaoFu/Awesome-3D-Object-Detection?style=social\"/\u003e : Papers, code and datasets about deep learning for 3D Object Detection.\r\n\r\n    - [xahidbuffon/Awesome_Underwater_Datasets](https://github.com/xahidbuffon/Awesome_Underwater_Datasets) \u003cimg src=\"https://img.shields.io/github/stars/xahidbuffon/Awesome_Underwater_Datasets?style=social\"/\u003e : Pointers to large-scale underwater datasets and relevant resources.\r\n\r\n    - [M-3LAB/awesome-industrial-anomaly-detection](https://github.com/M-3LAB/awesome-industrial-anomaly-detection) \u003cimg src=\"https://img.shields.io/github/stars/M-3LAB/awesome-industrial-anomaly-detection?style=social\"/\u003e : Paper list and datasets for industrial image anomaly detection.\r\n\r\n    - [ZhangXiwuu/Awesome_visual_place_recognition_datasets](https://github.com/ZhangXiwuu/Awesome_visual_place_recognition_datasets) \u003cimg src=\"https://img.shields.io/github/stars/ZhangXiwuu/Awesome_visual_place_recognition_datasets?style=social\"/\u003e : A curated list of Visual Place Recognition (VPR)/ loop closure detection (LCD) datasets.\r\n\r\n    - [ari-dasci/OD-WeaponDetection](https://github.com/ari-dasci/OD-WeaponDetection) \u003cimg src=\"https://img.shields.io/github/stars/ari-dasci/OD-WeaponDetection?style=social\"/\u003e : Datasets for weapon detection based on image classification and object detection tasks.\r\n\r\n    - [DLLXW/objectDetectionDatasets](https://github.com/DLLXW/objectDetectionDatasets) \u003cimg src=\"https://img.shields.io/github/stars/DLLXW/objectDetectionDatasets?style=social\"/\u003e : 目标检测数据集制作:VOC,COCO,YOLO等常用数据集格式的制作和互相转换脚本。\r\n\r\n    - [kuanhungchen/awesome-tiny-object-detection](https://github.com/kuanhungchen/awesome-tiny-object-detection) \u003cimg src=\"https://img.shields.io/github/stars/kuanhungchen/awesome-tiny-object-detection?style=social\"/\u003e : 🕶 A curated list of Tiny Object Detection papers and related resources.\r\n\r\n\r\n\r\n\r\n  - ### Paper and Code Overview\r\n\r\n    - #### Paper Review\r\n\r\n      - [52CV/CV-Surveys](https://github.com/52CV/CV-Surveys) \u003cimg src=\"https://img.shields.io/github/stars/52CV/CV-Surveys?style=social\"/\u003e : 计算机视觉相关综述。包括目标检测、跟踪........\r\n\r\n      - [GreenTeaHua/YOLO-Review](https://github.com/GreenTeaHua/YOLO-Review) \u003cimg src=\"https://img.shields.io/github/stars/GreenTeaHua/YOLO-Review?style=social\"/\u003e : \"A Review of YOLO Object Detection Based on Deep Learning\". \"基于深度学习的YOLO目标检测综述\". (**[Journal of Electronics \u0026 Information Technology 2022](https://jeit.ac.cn/cn/article/doi/10.11999/JEIT210790)**)\r\n\r\n      - \"A Review of Yolo Algorithm Developments\". (**[Procedia Computer Science 2022](https://www.sciencedirect.com/science/article/pii/S1877050922001363)**)\r\n\r\n\r\n\r\n    - #### Code Review\r\n\r\n      - [iscyy/ultralyticsPro](https://github.com/iscyy/ultralyticsPro) \u003cimg src=\"https://img.shields.io/github/stars/iscyy/ultralyticsPro?style=social\"/\u003e : 🔥🔥🔥 专注于YOLO11，YOLOv8、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀\r\n\r\n      - [MMDetection](https://github.com/open-mmlab/mmdetection) \u003cimg src=\"https://img.shields.io/github/stars/open-mmlab/mmdetection?style=social\"/\u003e : OpenMMLab Detection Toolbox and Benchmark. [mmdetection.readthedocs.io](https://mmdetection.readthedocs.io/en/latest/). (**[arXiv 2019](https://arxiv.org/abs/1906.07155)**)\r\n\r\n      - [MMYOLO](https://github.com/open-mmlab/mmyolo) \u003cimg src=\"https://img.shields.io/github/stars/open-mmlab/mmyolo?style=social\"/\u003e : OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOX, PPYOLOE, etc. [mmyolo.readthedocs.io/zh_CN/dev/](https://mmyolo.readthedocs.io/zh_CN/dev/)\r\n\r\n      - [iscyy/yoloair](https://github.com/iscyy/yoloair) \u003cimg src=\"https://img.shields.io/github/stars/iscyy/yoloair?style=social\"/\u003e :  🔥🔥🔥 专注于YOLO改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀.  YOLOAir是一个基于PyTorch的YOLO算法库。统一模型代码框架、统一应用、统一改进、易于模块组合、构建更强大的网络模型。\r\n\r\n      - [iscyy/yoloair2](https://github.com/iscyy/yoloair2) \u003cimg src=\"https://img.shields.io/github/stars/iscyy/yoloair2?style=social\"/\u003e : ☁️💡🎈专注于改进YOLOv7，Support to improve Backbone, Neck, Head, Loss, IoU, NMS and other modules.\r\n\r\n      - [jizhishutong/YOLOU](https://github.com/jizhishutong/YOLOU) \u003cimg src=\"https://img.shields.io/github/stars/jizhishutong/YOLOU?style=social\"/\u003e : YOLOU：United, Study and easier to Deploy. ​ The purpose of our creation of YOLOU is to better learn the algorithms of the YOLO series and pay tribute to our predecessors. YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6-v1、YOLOv6-v2、YOLOv7、YOLOX、YOLOX-Lite、PP-YOLOE、PP-PicoDet-Plus、YOLO-Fastest v2、FastestDet、YOLOv5-SPD、TensorRT、NCNN、Tengine、OpenVINO. \"微信公众号「集智书童」《[YOLOU开源 | 汇集YOLO系列所有算法，集算法学习、科研改进、落地于一身！](https://mp.weixin.qq.com/s/clupheQ8iHnhR4FJcTtB8A)》\"\r\n\r\n      - [WangQvQ/Yolov5_Magic](https://github.com/WangQvQ/Yolov5_Magic) \u003cimg src=\"https://img.shields.io/github/stars/WangQvQ/Yolov5_Magic?style=social\"/\u003e : YOLO Magic🪄 is an extension based on Ultralytics' YOLOv5, designed to provide more powerful functionality and simpler operations for visual tasks.\r\n\r\n      - [positive666/yolo_research](https://github.com/positive666/yolo_research) \u003cimg src=\"https://img.shields.io/github/stars/positive666/yolo_research?style=social\"/\u003e : 🚀 yolo_reserach PLUS High-level. based on yolo-high-level project (detect\\pose\\classify\\segment\\):include yolov5\\yolov7\\yolov8\\ core ,improvement research ,SwintransformV2 and Attention Series. training skills, business customization, engineering deployment.\r\n\r\n      - [augmentedstartups/AS-One](https://github.com/augmentedstartups/AS-One) \u003cimg src=\"https://img.shields.io/github/stars/augmentedstartups/AS-One?style=social\"/\u003e : Easy \u0026 Modular Computer Vision Detectors and Trackers - Run YOLO-NAS,v8,v7,v6,v5,R,X in under 20 lines of code. [www.augmentedstartups.com](https://www.augmentedstartups.com/)\r\n\r\n      - [Oneflow-Inc/one-yolov5](https://github.com/Oneflow-Inc/one-yolov5) \u003cimg src=\"https://img.shields.io/github/stars/Oneflow-Inc/one-yolov5?style=social\"/\u003e : A more efficient yolov5 with oneflow backend 🎉🎉🎉. \"微信公众号「GiantPandaCV」《[One-YOLOv5 发布，一个训得更快的YOLOv5](https://mp.weixin.qq.com/s/tZ7swUd0biz7G3CiRkHHfw)》\"\r\n\r\n      - [PaddlePaddle/PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO) \u003cimg src=\"https://img.shields.io/github/stars/PaddlePaddle/PaddleYOLO?style=social\"/\u003e :  🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOX, YOLOv5u, YOLOv7u, RTMDet and so on. 🚀🚀🚀\r\n\r\n      - [WangRongsheng/BestYOLO](https://github.com/WangRongsheng/BestYOLO) \u003cimg src=\"https://img.shields.io/github/stars/WangRongsheng/BestYOLO?style=social\"/\u003e : 🌟Change the world, it will become a better place. | 以科研和竞赛为导向的最好的YOLO实践框架!\r\n\r\n      - [KangChou/Cver4s](https://github.com/KangChou/Cver4s) \u003cimg src=\"https://img.shields.io/github/stars/KangChou/Cver4s?style=social\"/\u003e : Cver4s：Computer vision algorithm code base.\r\n\r\n      - [chaizwj/yolov8-tricks](https://github.com/chaizwj/yolov8-tricks) \u003cimg src=\"https://img.shields.io/github/stars/chaizwj/yolov8-tricks?style=social\"/\u003e : 目标检测，采用yolov8作为基准模型，数据集采用VisDrone2019，带有自己的改进策略。\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n  - ### Learning Resources\r\n\r\n    - [zjhellofss/KuiperLLama](https://github.com/zjhellofss/KuiperLLama) \u003cimg src=\"https://img.shields.io/github/stars/zjhellofss/KuiperLLama?style=social\"/\u003e : 《动手自制大模型推理框架》。KuiperLLama 动手自制大模型推理框架，支持LLama2/3和Qwen2.5。校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。\r\n\r\n    - [zjhellofss/KuiperInfer](https://github.com/zjhellofss/KuiperInfer) \u003cimg src=\"https://img.shields.io/github/stars/zjhellofss/KuiperInfer?style=social\"/\u003e :  校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step。\r\n\r\n    - [zjhellofss/kuiperdatawhale](https://github.com/zjhellofss/kuiperdatawhale) \u003cimg src=\"https://img.shields.io/github/stars/zjhellofss/kuiperdatawhale?style=social\"/\u003e :  从零自制深度学习推理框架。\r\n\r\n    - [roboflow/notebooks](https://github.com/roboflow/notebooks) \u003cimg src=\"https://img.shields.io/github/stars/roboflow/notebooks?style=social\"/\u003e : Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM. [roboflow.com/models](https://roboflow.com/models)\r\n\r\n    - [yjh0410/PyTorch_YOLO_Tutorial](https://github.com/yjh0410/PyTorch_YOLO_Tutorial) \u003cimg src=\"https://img.shields.io/github/stars/yjh0410/PyTorch_YOLO_Tutorial?style=social\"/\u003e : YOLO Tutorial.\r\n\r\n    - [HuKai97/yolov5-5.x-annotations](https://github.com/HuKai97/yolov5-5.x-annotations) \u003cimg src=\"https://img.shields.io/github/stars/HuKai97/yolov5-5.x-annotations?style=social\"/\u003e : 一个基于yolov5-5.0的中文注释版本！\r\n\r\n    - [crkk-feng/yolov5-annotations](https://github.com/crkk-feng/yolov5-annotations) \u003cimg src=\"https://img.shields.io/github/stars/crkk-feng/yolov5-annotations?style=social\"/\u003e : A Chinese annotated version of yolov5-5.0.\r\n\r\n    - [XiaoJiNu/yolov5-v6-chinese-comment](https://github.com/XiaoJiNu/yolov5-v6-chinese-comment) \u003cimg src=\"https://img.shields.io/github/stars/XiaoJiNu/yolov5-v6-chinese-comment?style=social\"/\u003e : yolov5-v6版本注释。\r\n\r\n    - [1131624548/About-YOLOv5-7-0](https://github.com/1131624548/About-YOLOv5-7-0) \u003cimg src=\"https://img.shields.io/github/stars/XiaoJiNu/yolov5-v6-chinese-comment?style=social\"/\u003e : YOLOv5代码注释。\r\n\r\n    - [zyds/yolov5-code](https://github.com/zyds/yolov5-code) \u003cimg src=\"https://img.shields.io/github/stars/zyds/yolov5-code?style=social\"/\u003e : 手把手带你实战 YOLOv5。\r\n\r\n\r\n\r\n\r\n## Other Versions of YOLO\r\n\r\n  - ### PyTorch Implementation\r\n\r\n    - [ultralytics/yolov3](https://github.com/ultralytics/yolov3) \u003cimg src=\"https://img.shields.io/github/stars/ultralytics/yolov3?style=social\"/\u003e : YOLOv3 in PyTorch \u003e ONNX \u003e CoreML \u003e TFLite.\r\n\r\n    - [eriklindernoren/PyTorch-YOLOv3](https://github.com/eriklindernoren/PyTorch-YOLOv3) \u003cimg src=\"https://img.shields.io/github/stars/eriklindernoren/PyTorch-YOLOv3?style=social\"/\u003e : Minimal PyTorch implementation of YOLOv3.\r\n\r\n    - [Tianxiaomo/pytorch-YOLOv4](https://github.com/Tianxiaomo/pytorch-YOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/Tianxiaomo/pytorch-YOLOv4?style=social\"/\u003e : PyTorch ,ONNX and TensorRT implementation of YOLOv4.\r\n\r\n    - [ayooshkathuria/pytorch-yolo-v3](https://github.com/ayooshkathuria/pytorch-yolo-v3) \u003cimg src=\"https://img.shields.io/github/stars/ayooshkathuria/pytorch-yolo-v3?style=social\"/\u003e : A PyTorch implementation of the YOLO v3 object detection algorithm.\r\n\r\n    - [WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/WongKinYiu/PyTorch_YOLOv4?style=social\"/\u003e : PyTorch implementation of YOLOv4.\r\n\r\n    - [argusswift/YOLOv4-pytorch](https://github.com/argusswift/YOLOv4-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/argusswift/YOLOv4-pytorch?style=social\"/\u003e : This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO.\r\n\r\n    - [longcw/yolo2-pytorch](https://github.com/longcw/yolo2-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/longcw/yolo2-pytorch?style=social\"/\u003e : YOLOv2 in PyTorch.\r\n\r\n    - [bubbliiiing/yolov5-v6.1-pytorch](https://github.com/bubbliiiing/yolov5-v6.1-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov5-v6.1-pytorch?style=social\"/\u003e : 这是一个yolov5-v6.1-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov5-pytorch](https://github.com/bubbliiiing/yolov5-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov5-pytorch?style=social\"/\u003e : 这是一个YoloV5-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov4-pytorch](https://github.com/bubbliiiing/yolov4-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov4-pytorch?style=social\"/\u003e : 这是一个YoloV4-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov4-tiny-pytorch](https://github.com/bubbliiiing/yolov4-tiny-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov4-tiny-pytorch?style=social\"/\u003e : 这是一个YoloV4-tiny-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov3-pytorch](https://github.com/bubbliiiing/yolo3-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolo3-pytorch?style=social\"/\u003e : 这是一个yolo3-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolox-pytorch](https://github.com/bubbliiiing/yolox-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolox-pytorch?style=social\"/\u003e : 这是一个yolox-pytorch的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov7-pytorch](https://github.com/bubbliiiing/yolov7-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov7-pytorch?style=social\"/\u003e : 这是一个yolov7的库，可以用于训练自己的数据集。\r\n\r\n    - [bubbliiiing/yolov8-pytorch](https://github.com/bubbliiiing/yolov8-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov8-pytorch?style=social\"/\u003e : 这是一个yolov8-pytorch的仓库，可以用于训练自己的数据集。\r\n\r\n    - [BobLiu20/YOLOv3_PyTorch](https://github.com/BobLiu20/YOLOv3_PyTorch) \u003cimg src=\"https://img.shields.io/github/stars/BobLiu20/YOLOv3_PyTorch?style=social\"/\u003e : Full implementation of YOLOv3 in PyTorch.\r\n\r\n    - [ruiminshen/yolo2-pytorch](https://github.com/ruiminshen/yolo2-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/ruiminshen/yolo2-pytorch?style=social\"/\u003e : PyTorch implementation of the YOLO (You Only Look Once) v2.\r\n\r\n    - [DeNA/PyTorch_YOLOv3](https://github.com/DeNA/PyTorch_YOLOv3) \u003cimg src=\"https://img.shields.io/github/stars/DeNA/PyTorch_YOLOv3?style=social\"/\u003e : Implementation of YOLOv3 in PyTorch.\r\n\r\n    - [abeardear/pytorch-YOLO-v1](https://github.com/abeardear/pytorch-YOLO-v1) \u003cimg src=\"https://img.shields.io/github/stars/abeardear/pytorch-YOLO-v1?style=social\"/\u003e : an experiment for yolo-v1, including training and testing.\r\n\r\n    - [wuzhihao7788/yolodet-pytorch](https://github.com/wuzhihao7788/yolodet-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/wuzhihao7788/yolodet-pytorch?style=social\"/\u003e : reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5，YOLOv3, etc.\r\n\r\n    - [uvipen/Yolo-v2-pytorch](https://github.com/uvipen/Yolo-v2-pytorch) \u003cimg src=\"https://img.shields.io/github/stars/uvipen/Yolo-v2-pytorch?style=social\"/\u003e : YOLO for object detection tasks.\r\n\r\n    - [Peterisfar/YOLOV3](https://github.com/Peterisfar/YOLOV3) \u003cimg src=\"https://img.shields.io/github/stars/Peterisfar/YOLOV3?style=social\"/\u003e : yolov3 by pytorch.\r\n\r\n    - [misads/easy_detection](https://github.com/misads/easy_detection) \u003cimg src=\"https://img.shields.io/github/stars/misads/easy_detection?style=social\"/\u003e : 一个简单方便的目标检测框架(PyTorch环境可直接运行，不需要cuda编译)，支持Faster_RCNN、Yolo系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等经典网络。\r\n\r\n    - [miemiedetection](https://github.com/miemie2013/miemiedetection) \u003cimg src=\"https://img.shields.io/github/stars/miemie2013/miemiedetection?style=social\"/\u003e : Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、SOLOv2 an so on.\r\n\r\n    - [pjh5672/YOLOv1](https://github.com/pjh5672/YOLOv1) \u003cimg src=\"https://img.shields.io/github/stars/pjh5672/YOLOv1?style=social\"/\u003e : YOLOv1 implementation using PyTorch.\r\n\r\n    - [pjh5672/YOLOv2](https://github.com/pjh5672/YOLOv2) \u003cimg src=\"https://img.shields.io/github/stars/pjh5672/YOLOv2?style=social\"/\u003e : YOLOv2 implementation using PyTorch.\r\n\r\n    - [pjh5672/YOLOv3](https://github.com/pjh5672/YOLOv3) \u003cimg src=\"https://img.shields.io/github/stars/pjh5672/YOLOv3?style=social\"/\u003e : YOLOv3 implementation using PyTorch.\r\n\r\n    - [Iywie/pl_YOLO](https://github.com/Iywie/pl_YOLO) \u003cimg src=\"https://img.shields.io/github/stars/Iywie/pl_YOLO?style=social\"/\u003e : YOLOv7, YOLOX and YOLOv5 are working right now.\r\n\r\n    - [DavidLandup0/deepvision](https://github.com/DavidLandup0/deepvision) \u003cimg src=\"https://img.shields.io/github/stars/DavidLandup0/deepvision?style=social\"/\u003e : PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, NeRF, etc.\r\n\r\n    - [theos-ai/easy-yolov7](https://github.com/theos-ai/easy-yolov7) \u003cimg src=\"https://img.shields.io/github/stars/theos-ai/easy-yolov7?style=social\"/\u003e : This a clean and easy-to-use implementation of YOLOv7 in PyTorch, made with ❤️ by Theos AI.\r\n\r\n  - ### C Implementation\r\n\r\n    - [ggml](https://github.com/ggerganov/ggml) \u003cimg src=\"https://img.shields.io/github/stars/ggerganov/ggml?style=social\"/\u003e : Tensor library for machine learning. Written in C.\r\n\r\n    - [rockcarry/ffcnn](https://github.com/rockcarry/ffcnn) \u003cimg src=\"https://img.shields.io/github/stars/rockcarry/ffcnn?style=social\"/\u003e : ffcnn is a cnn neural network inference framework, written in 600 lines C language.\r\n\r\n    - [ar7775/Object-Detection-System-Yolo](https://github.com/ar7775/Object-Detection-System-Yolo) \u003cimg src=\"https://img.shields.io/github/stars/ar7775/Object-Detection-System-Yolo?style=social\"/\u003e : Object Detection System.\r\n\r\n    - [lstuma/YOLO_utils](https://github.com/lstuma/YOLO_utils) \u003cimg src=\"https://img.shields.io/github/stars/lstuma/YOLO_utils?style=social\"/\u003e : A few utilities for the YOLO project implemented in C for extra speed.\r\n\r\n    - [RajneeshKumar12/yolo-detection-app](https://github.com/RajneeshKumar12/yolo-detection-app) \u003cimg src=\"https://img.shields.io/github/stars/RajneeshKumar12/yolo-detection-app?style=social\"/\u003e : Yolo app for object detection.\r\n\r\n    - [Deyht/CIANNA](https://github.com/Deyht/CIANNA) \u003cimg src=\"https://img.shields.io/github/stars/Deyht/CIANNA?style=social\"/\u003e : CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists.\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n  - ### CPP Implementation\r\n\r\n    - [walktree/libtorch-yolov3](https://github.com/walktree/libtorch-yolov3) \u003cimg src=\"https://img.shields.io/github/stars/walktree/libtorch-yolov3?style=social\"/\u003e : A Libtorch implementation of the YOLO v3 object detection algorithm, written with pure C++.\r\n\r\n    - [yasenh/libtorch-yolov5](https://github.com/yasenh/libtorch-yolov5) \u003cimg src=\"https://img.shields.io/github/stars/yasenh/libtorch-yolov5?style=social\"/\u003e : A LibTorch inference implementation of the yolov5.\r\n\r\n    - [Nebula4869/YOLOv5-LibTorch](https://github.com/Nebula4869/YOLOv5-LibTorch) \u003cimg src=\"https://img.shields.io/github/stars/Nebula4869/YOLOv5-LibTorch?style=social\"/\u003e : Real time object detection with deployment of YOLOv5 through LibTorch C++ API.\r\n\r\n    - [ncdhz/YoloV5-LibTorch](https://github.com/ncdhz/YoloV5-LibTorch) \u003cimg src=\"https://img.shields.io/github/stars/ncdhz/YoloV5-LibTorch?style=social\"/\u003e : 一个 C++ 版本的 YoloV5 封装库.\r\n\r\n    - [Rane2021/yolov5_train_cpp_inference](https://github.com/Rane2021/yolov5_train_cpp_inference) \u003cimg src=\"https://img.shields.io/github/stars/Rane2021/yolov5_train_cpp_inference?style=social\"/\u003e : yolov5训练和c++推理代码，效果出色。\r\n\r\n    - [stephanecharette/DarkHelp](https://github.com/stephanecharette/DarkHelp) \u003cimg src=\"https://img.shields.io/github/stars/stephanecharette/DarkHelp?style=social\"/\u003e : The DarkHelp C++ API is a wrapper to make it easier to use the Darknet neural network framework within a C++ application.\r\n\r\n    - [UNeedCryDear/yolov5-opencv-dnn-cpp](https://github.com/UNeedCryDear/yolov5-opencv-dnn-cpp) \u003cimg src=\"https://img.shields.io/github/stars/UNeedCryDear/yolov5-opencv-dnn-cpp?style=social\"/\u003e : 使用opencv模块部署yolov5-6.0版本。\r\n\r\n    - [UNeedCryDear/yolov5-seg-opencv-onnxruntime-cpp](https://github.com/UNeedCryDear/yolov5-seg-opencv-onnxruntime-cpp) \u003cimg src=\"https://img.shields.io/github/stars/UNeedCryDear/yolov5-seg-opencv-onnxruntime-cpp?style=social\"/\u003e : yolov5 segmentation with onnxruntime and opencv.\r\n\r\n    - [hpc203/yolov5-dnn-cpp-python](https://github.com/hpc203/yolov5-dnn-cpp-python) \u003cimg src=\"https://img.shields.io/github/stars/hpc203/yolov5-dnn-cpp-python?style=social\"/\u003e : 用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序。\r\n\r\n    - [hpc203/yolox-opencv-dnn](https://github.com/hpc203/yolox-opencv-dnn) \u003cimg src=\"https://img.shields.io/github/stars/hpc203/yolox-opencv-dnn?style=social\"/\u003e : 使用OpenCV部署YOLOX，支持YOLOX-S、YOLOX-M、YOLOX-L、YOLOX-X、YOLOX-Darknet53五种结构，包含C++和Python两种版本的程序。\r\n\r\n    - [hpc203/yolov7-opencv-onnxrun-cpp-py](https://github.com/hpc203/yolov7-opencv-onnxrun-cpp-py) \u003cimg src=\"https://img.shields.io/github/stars/hpc203/yolov7-opencv-onnxrun-cpp-py?style=social\"/\u003e : 分别使用OpenCV、ONNXRuntime部署YOLOV7目标检测，一共包含12个onnx模型，依然是包含C++和Python两个版本的程序。\r\n\r\n    - [doleron/yolov5-opencv-cpp-python](https://github.com/doleron/yolov5-opencv-cpp-python) \u003cimg src=\"https://img.shields.io/github/stars/doleron/yolov5-opencv-cpp-python?style=social\"/\u003e : Example of using ultralytics YOLO V5 with OpenCV 4.5.4, C++ and Python.\r\n\r\n    - [UNeedCryDear/yolov8-opencv-onnxruntime-cpp](https://github.com/UNeedCryDear/yolov8-opencv-onnxruntime-cpp) \u003cimg src=\"https://img.shields.io/github/stars/UNeedCryDear/yolov8-opencv-onnxruntime-cpp?style=social\"/\u003e : detection and instance segmentation of yolov8,use onnxruntime and opencv.\r\n\r\n\r\n\r\n\r\n  - ### ROS Implementation\r\n\r\n    - [mgonzs13/yolov8_ros](https://github.com/mgonzs13/yolov8_ros) \u003cimg src=\"https://img.shields.io/github/stars/mgonzs13/yolov8_ros?style=social\"/\u003e : Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2.\r\n\r\n    - [leggedrobotics/darknet_ros](https://github.com/leggedrobotics/darknet_ros) \u003cimg src=\"https://img.shields.io/github/stars/leggedrobotics/darknet_ros?style=social\"/\u003e : Real-Time Object Detection for ROS.\r\n\r\n    - [engcang/ros-yolo-sort](https://github.com/engcang/ros-yolo-sort) \u003cimg src=\"https://img.shields.io/github/stars/engcang/ros-yolo-sort?style=social\"/\u003e : YOLO and SORT, and ROS versions of them.\r\n\r\n    - [chrisgundling/YoloLight](https://github.com/chrisgundling/YoloLight) \u003cimg src=\"https://img.shields.io/github/stars/chrisgundling/YoloLight?style=social\"/\u003e : Tiny-YOLO-v2 ROS Node for Traffic Light Detection.\r\n\r\n    - [Ar-Ray-code/YOLOX-ROS](https://github.com/Ar-Ray-code/YOLOX-ROS) \u003cimg src=\"https://img.shields.io/github/stars/Ar-Ray-code/YOLOX-ROS?style=social\"/\u003e : YOLOX + ROS2 object detection package.\r\n\r\n    - [Ar-Ray-code/YOLOv5-ROS](https://github.com/Ar-Ray-code/YOLOv5-ROS) \u003cimg src=\"https://img.shields.io/github/stars/Ar-Ray-code/YOLOv5-ROS?style=social\"/\u003e : YOLOv5 + ROS2 object detection package.\r\n\r\n    - [Tossy0423/yolov4-for-darknet_ros](https://github.com/Tossy0423/yolov4-for-darknet_ros) \u003cimg src=\"https://img.shields.io/github/stars/Tossy0423/yolov4-for-darknet_ros?style=social\"/\u003e : This is the environment in which YOLO V4 is ported to darknet_ros.\r\n\r\n    - [qianmin/yolov5_ROS](https://github.com/qianmin/yolov5_ROS) \u003cimg src=\"https://img.shields.io/github/stars/qianmin/yolov5_ROS?style=social\"/\u003e : run YOLOv5 in ROS，ROS使用YOLOv5。\r\n\r\n    - [ailllist/yolov5_ROS](https://github.com/ailllist/yolov5_ROS) \u003cimg src=\"https://img.shields.io/github/stars/ailllist/yolov5_ROS?style=social\"/\u003e : yolov5 for ros, not webcam.\r\n\r\n    - [Shua-Kang/ros_pytorch_yolov5](https://github.com/Shua-Kang/ros_pytorch_yolov5) \u003cimg src=\"https://img.shields.io/github/stars/Shua-Kang/ros_pytorch_yolov5?style=social\"/\u003e : A ROS wrapper for yolov5. (master branch is v5.0 of yolov5; for v6.1, see branch v6.1).\r\n\r\n    - [ziyan0302/Yolov5_DeepSort_Pytorch_ros](https://github.com/ziyan0302/Yolov5_DeepSort_Pytorch_ros) \u003cimg src=\"https://img.shields.io/github/stars/ziyan0302/Yolov5_DeepSort_Pytorch_ros?style=social\"/\u003e : Connect Yolov5 detection module and DeepSort tracking module via ROS.\r\n\r\n    - [U07157135/ROS2-with-YOLOv5](https://github.com/U07157135/ROS2-with-YOLOv5) \u003cimg src=\"https://img.shields.io/github/stars/U07157135/ROS2-with-YOLOv5?style=social\"/\u003e : 在無人機上以ROS2技術實現YOLOv5物件偵測。\r\n\r\n    - [lukazso/yolov6-ros](https://github.com/lukazso/yolov6-ros) \u003cimg src=\"https://img.shields.io/github/stars/lukazso/yolov6-ros?style=social\"/\u003e : ROS package for YOLOv6.\r\n\r\n    - [qq44642754a/Yolov5_ros](https://github.com/qq44642754a/Yolov5_ros) \u003cimg src=\"https://img.shields.io/github/stars/qq44642754a/Yolov5_ros?style=social\"/\u003e : Real-time object detection with ROS, based on YOLOv5 and PyTorch (基于 YOLOv5的ROS实时对象检测).\r\n\r\n    - [lukazso/yolov7-ros](https://github.com/lukazso/yolov7-ros) \u003cimg src=\"https://img.shields.io/github/stars/lukazso/yolov7-ros?style=social\"/\u003e : ROS package for official YOLOv7.\r\n\r\n    - [phuoc101/yolov7_ros](https://github.com/phuoc101/yolov7_ros) \u003cimg src=\"https://img.shields.io/github/stars/phuoc101/yolov7_ros?style=social\"/\u003e : ROS package for official YOLOv7.\r\n\r\n    - [ConfusionTechnologies/ros-yolov5-node](https://github.com/ConfusionTechnologies/ros-yolov5-node) \u003cimg src=\"https://img.shields.io/github/stars/ConfusionTechnologies/ros-yolov5-node?style=social\"/\u003e : For ROS2, uses ONNX GPU Runtime to inference YOLOv5.\r\n\r\n    - [Ar-Ray-code/darknet_ros_fp16](https://github.com/Ar-Ray-code/darknet_ros_fp16) \u003cimg src=\"https://img.shields.io/github/stars/Ar-Ray-code/darknet_ros_fp16?style=social\"/\u003e : darknet + ROS2 Humble + OpenCV4 + CUDA 11（cuDNN, Jetson Orin）.\r\n\r\n    - [wk123467/yolov5s_trt_ros](https://github.com/wk123467/yolov5s_trt_ros) \u003cimg src=\"https://img.shields.io/github/stars/wk123467/yolov5s_trt_ros?style=social\"/\u003e : 利用TensorRT对yolov5s进行加速，并将其应用于ROS，实现交通标志、红绿灯(直接输出路灯状态)、行人和车辆等交通场景的检测。\r\n\r\n    - [PardisTaghavi/yolov7_strongsort_ros](https://github.com/PardisTaghavi/yolov7_strongsort_ros) \u003cimg src=\"https://img.shields.io/github/stars/PardisTaghavi/yolov7_strongsort_ros?style=social\"/\u003e : Integration of \"Yolov7 StrongSort\" with ROS for real time object tracking.\r\n\r\n    - [af-doom/yolov8_ros_tensorrt-](https://github.com/af-doom/yolov8_ros_tensorrt-) \u003cimg src=\"https://img.shields.io/github/stars/af-doom/yolov8_ros_tensorrt-?style=social\"/\u003e : This is a YOLOv8 project based on ROS implementation, where YOLOv8 uses Tensorrt acceleration.\r\n\r\n    - [KoKoMier/ros_darknet_yolov4](https://github.com/KoKoMier/ros_darknet_yolov4) \u003cimg src=\"https://img.shields.io/github/stars/KoKoMier/ros_darknet_yolov4?style=social\"/\u003e : 这是机器人小组视觉与雷达的结合程序，首先通过yolo目标检测识别到物体，然后把识别到的数据发送给ros里面程序，用于雷达数据结合。\r\n\r\n    - [YellowAndGreen/Yolov5-OpenCV-Cpp-Python-ROS](https://github.com/YellowAndGreen/Yolov5-OpenCV-Cpp-Python-ROS) \u003cimg src=\"https://img.shields.io/github/stars/YellowAndGreen/Yolov5-OpenCV-Cpp-Python-ROS?style=social\"/\u003e : Inference with YOLOv5, OpenCV 4.5.4 DNN, C++, ROS and Python.\r\n\r\n    - [mgonzs13/yolov8_ros](https://github.com/mgonzs13/yolov8_ros) \u003cimg src=\"https://img.shields.io/github/stars/mgonzs13/yolov8_ros?style=social\"/\u003e : ROS 2 wrap for Ultralytics [YOLOv8](https://github.com/ultralytics/ultralytics) to perform object detection.\r\n\r\n    - [fishros/yolov5_ros2](https://github.com/fishros/yolov5_ros2) \u003cimg src=\"https://img.shields.io/github/stars/fishros/yolov5_ros2?style=social\"/\u003e : 基于YoloV5的ROS2功能包，可以快速完成物体识别与位姿发布。\r\n\r\n    - [fateshelled/EdgeYOLO-ROS](https://github.com/fateshelled/EdgeYOLO-ROS) \u003cimg src=\"https://img.shields.io/github/stars/fateshelled/EdgeYOLO-ROS?style=social\"/\u003e : EdgeYOLO + ROS2 object detection package.\r\n\r\n    - [vivaldini/yolov6-uav](https://github.com/vivaldini/yolov6-uav) \u003cimg src=\"https://img.shields.io/github/stars/vivaldini/yolov6-uav?style=social\"/\u003e : This repository contains a ROS noetic package for YOLOv6 to recognize objects from UAV and provide their positions.\r\n\r\n    - [Alpaca-zip/ultralytics_ros](https://github.com/Alpaca-zip/ultralytics_ros) \u003cimg src=\"https://img.shields.io/github/stars/Alpaca-zip/ultralytics_ros?style=social\"/\u003e : ROS/ROS2 package for Ultralytics YOLOv8 real-time object detection.\r\n\r\n\r\n- ### Mojo Implementation\r\n\r\n    - [taalhaataahir0102/Mojo-Yolo](https://github.com/taalhaataahir0102/Mojo-Yolo) \u003cimg src=\"https://img.shields.io/github/stars/taalhaataahir0102/Mojo-Yolo?style=social\"/\u003e : Mojo-Yolo.\r\n\r\n\r\n- ### Rust Implementation\r\n\r\n    - [Candle](https://github.com/huggingface/candle) \u003cimg src=\"https://img.shields.io/github/stars/huggingface/candle?style=social\"/\u003e : Minimalist ML framework for Rust.\r\n\r\n    - [Tokenizers](https://github.com/huggingface/tokenizers) \u003cimg src=\"https://img.shields.io/github/stars/huggingface/tokenizers?style=social\"/\u003e : 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production. [huggingface.co/docs/tokenizers](https://huggingface.co/docs/tokenizers/index)\r\n\r\n    - [Safetensors](https://github.com/huggingface/safetensors) \u003cimg src=\"https://img.shields.io/github/stars/huggingface/safetensors?style=social\"/\u003e : Simple, safe way to store and distribute tensors. [huggingface.co/docs/safetensors](https://huggingface.co/docs/safetensors/index)\r\n\r\n    - [Burn](https://github.com/burn-rs/burn) \u003cimg src=\"https://img.shields.io/github/stars/burn-rs/burn?style=social\"/\u003e : Burn - A Flexible and Comprehensive Deep Learning Framework in Rust. [burn-rs.github.io/](https://burn-rs.github.io/)\r\n\r\n    - [TensorFlow Rust](https://github.com/tensorflow/rust) \u003cimg src=\"https://img.shields.io/github/stars/tensorflow/rust?style=social\"/\u003e : Rust language bindings for TensorFlow.\r\n\r\n    - [tch-rs](https://github.com/LaurentMazare/tch-rs) \u003cimg src=\"https://img.shields.io/github/stars/LaurentMazare/tch-rs?style=social\"/\u003e : Rust bindings for the C++ api of PyTorch.\r\n\r\n    - [dfdx](https://github.com/coreylowman/dfdx) \u003cimg src=\"https://img.shields.io/github/stars/coreylowman/dfdx?style=social\"/\u003e : Deep learning in Rust, with shape checked tensors and neural networks.\r\n\r\n    - [tract](https://github.com/sonos/tract) \u003cimg src=\"https://img.shields.io/github/stars/sonos/tract?style=social\"/\u003e : Sonos' Neural Network inference engine. Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference\r\n\r\n    - [ort](https://github.com/pykeio/ort) \u003cimg src=\"https://img.shields.io/github/stars/pykeio/ort?style=social\"/\u003e : A Rust wrapper for ONNX Runtime. [docs.rs/ort](https://docs.rs/ort/latest/ort/)\r\n\r\n    - [usls](https://github.com/jamjamjon/usls) \u003cimg src=\"https://img.shields.io/github/stars/jamjamjon/usls?style=social\"/\u003e : A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.\r\n\r\n    - [ptaxom/pnn](https://github.com/ptaxom/pnn) \u003cimg src=\"https://img.shields.io/github/stars/ptaxom/pnn?style=social\"/\u003e : pnn is [Darknet](https://github.com/alexeyAB/darknet) compatible neural nets inference engine implemented in Rust. By optimizing was achieved significant performance increment(especially in FP16 mode). pnn provide CUDNN-based and TensorRT-based inference engines.\r\n\r\n    - [bencevans/rust-opencv-yolov5](https://github.com/bencevans/rust-opencv-yolov5) \u003cimg src=\"https://img.shields.io/github/stars/bencevans/rust-opencv-yolov5?style=social\"/\u003e : YOLOv5 Inference with ONNX \u0026 OpenCV in Rust.\r\n\r\n    - [masc-it/yolov5-api-rust](https://github.com/masc-it/yolov5-api-rust) \u003cimg src=\"https://img.shields.io/github/stars/masc-it/yolov5-api-rust?style=social\"/\u003e : Rust API to run predictions with YoloV5 models.\r\n\r\n    - [AndreyGermanov/yolov8_onnx_rust](https://github.com/AndreyGermanov/yolov8_onnx_rust) \u003cimg src=\"https://img.shields.io/github/stars/AndreyGermanov/yolov8_onnx_rust?style=social\"/\u003e : YOLOv8 inference using Rust.\r\n\r\n    - [igor-yusupov/rusty-yolo](https://github.com/igor-yusupov/rusty-yolo) \u003cimg src=\"https://img.shields.io/github/stars/igor-yusupov/rusty-yolo?style=social\"/\u003e : rusty-yolo.\r\n\r\n    - [gsuyemoto/yolo-rust](https://github.com/gsuyemoto/yolo-rust) \u003cimg src=\"https://img.shields.io/github/stars/gsuyemoto/yolo-rust?style=social\"/\u003e : Run YOLO computer vision model using Rust and OpenCV and/or Torch.\r\n\r\n    - [alianse777/darknet-rust](https://github.com/alianse777/darknet-rust) \u003cimg src=\"https://img.shields.io/github/stars/alianse777/darknet-rust?style=social\"/\u003e : A Rust wrapper for Darknet, an open source neural network framework written in C and CUDA. [pjreddie.com/darknet/](https://pjreddie.com/darknet/)\r\n\r\n    - [12101111/yolo-rs](https://github.com/12101111/yolo-rs) \u003cimg src=\"https://img.shields.io/github/stars/12101111/yolo-rs?style=social\"/\u003e : Yolov3 \u0026 Yolov4 with TVM and rust.\r\n\r\n    - [TKGgunter/yolov4_tiny_rs](https://github.com/TKGgunter/yolov4_tiny_rs) \u003cimg src=\"https://img.shields.io/github/stars/TKGgunter/yolov4_tiny_rs?style=social\"/\u003e : A rust implementation of yolov4_tiny algorithm.\r\n\r\n    - [flixstn/You-Only-Look-Once](https://github.com/flixstn/You-Only-Look-Once) \u003cimg src=\"https://img.shields.io/github/stars/flixstn/You-Only-Look-Once?style=social\"/\u003e : A Rust implementation of Yolo for object detection and tracking.\r\n\r\n    - [lenna-project/yolo-plugin](https://github.com/lenna-project/yolo-plugin) \u003cimg src=\"https://img.shields.io/github/stars/lenna-project/yolo-plugin?style=social\"/\u003e : Yolo Object Detection Plugin for Lenna.\r\n\r\n    - [laclouis5/globox-rs](https://github.com/laclouis5/globox-rs) \u003cimg src=\"https://img.shields.io/github/stars/laclouis5/globox-rs?style=social\"/\u003e : Object detection toolbox for parsing, converting and evaluating bounding box annotations.\r\n\r\n    - [metobom/tchrs-opencv-webcam-inference](https://github.com/metobom/tchrs-opencv-webcam-inference) \u003cimg src=\"https://img.shields.io/github/stars/metobom/tchrs-opencv-webcam-inference?style=social\"/\u003e : This example shows steps for running a Python trained model on webcam feed with opencv and tch-rs. Model will run on GPU.\r\n\r\n\r\n\r\n  - ### Go Implementation\r\n\r\n    - [LdDl/go-darknet](https://github.com/LdDl/go-darknet) \u003cimg src=\"https://img.shields.io/github/stars/LdDl/go-darknet?style=social\"/\u003e : go-darknet: Go bindings for Darknet (Yolo V4, Yolo V7-tiny, Yolo V3).\r\n\r\n    - [adalkiran/distributed-inference](https://github.com/adalkiran/distributed-inference) \u003cimg src=\"https://img.shields.io/github/stars/adalkiran/distributed-inference?style=social\"/\u003e : Cross-language and distributed deep learning inference pipeline for WebRTC video streams over Redis Streams. Currently supports YOLOX model, which can run well on CPU.\r\n\r\n    - [wimspaargaren/yolov3](https://github.com/wimspaargaren/yolov3) \u003cimg src=\"https://img.shields.io/github/stars/wimspaargaren/yolov3?style=social\"/\u003e : Go implementation of the yolo v3 object detection system.\r\n\r\n    - [wimspaargaren/yolov5](https://github.com/wimspaargaren/yolov5) \u003cimg src=\"https://img.shields.io/github/stars/wimspaargaren/yolov5?style=social\"/\u003e : Go implementation of the yolo v5 object detection system.\r\n\r\n    - [genert/real_time_object_detection_go](https://github.com/genert/real_time_object_detection_go) \u003cimg src=\"https://img.shields.io/github/stars/genert/real_time_object_detection_go?style=social\"/\u003e : Real Time Object Detection with OpenCV, Go, and Yolo v4.\r\n\r\n\r\n\r\n  - ### CSharp Implementation\r\n\r\n    - [ML.NET](https://github.com/dotnet/machinelearning) \u003cimg src=\"https://img.shields.io/github/stars/dotnet/machinelearning?style=social\"/\u003e : ML.NET is an open source and cross-platform machine learning framework for .NET.\r\n\r\n    - [TorchSharp](https://github.com/dotnet/TorchSharp) \u003cimg src=\"https://img.shields.io/github/stars/dotnet/TorchSharp?style=social\"/\u003e : A .NET library that provides access to the library that powers PyTorch.\r\n\r\n    - [TensorFlow.NET](https://github.com/SciSharp/TensorFlow.NET) \u003cimg src=\"https://img.shields.io/github/stars/SciSharp/TensorFlow.NET?style=social\"/\u003e : .NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.\r\n\r\n    - [DlibDotNet](https://github.com/takuya-takeuchi/DlibDotNet) \u003cimg src=\"https://img.shields.io/github/stars/takuya-takeuchi/DlibDotNet?style=social\"/\u003e : Dlib .NET wrapper written in C++ and C# for Windows, MacOS, Linux and iOS.\r\n\r\n    - [DiffSharp](https://github.com/DiffSharp/DiffSharp) \u003cimg src=\"https://img.shields.io/github/stars/DiffSharp/DiffSharp?style=social\"/\u003e : DiffSharp: Differentiable Functional Programming.\r\n\r\n    - [dme-compunet/YOLOv8](https://github.com/dme-compunet/YOLOv8) \u003cimg src=\"https://img.shields.io/github/stars/dme-compunet/YOLOv8?style=social\"/\u003e : Use YOLOv8 in real-time, for object detection, instance segmentation, pose estimation and image classification, via ONNX Runtime. [www.nuget.org/packages/YoloV8](https://www.nuget.org/packages/YoloV8)\r\n\r\n    - [techwingslab/yolov5-net](https://github.com/techwingslab/yolov5-net) \u003cimg src=\"https://img.shields.io/github/stars/techwingslab/yolov5-net?style=social\"/\u003e : YOLOv5 object detection with C#, ML.NET, ONNX.\r\n\r\n    - [sstainba/Yolov8.Net](https://github.com/sstainba/Yolov8.Net) \u003cimg src=\"https://img.shields.io/github/stars/sstainba/Yolov8.Net?style=social\"/\u003e : A .net 6 implementation to use Yolov5 and Yolov8 models via the ONNX Runtime.\r\n\r\n    - [Alturos.Yolo](https://github.com/AlturosDestinations/Alturos.Yolo) \u003cimg src=\"https://img.shields.io/github/stars/AlturosDestinations/Alturos.Yolo?style=social\"/\u003e : C# Yolo Darknet Wrapper (real-time object detection).\r\n\r\n    - [ivilson/Yolov7net](https://github.com/ivilson/Yolov7net) \u003cimg src=\"https://img.shields.io/github/stars/ivilson/Yolov7net?style=social\"/\u003e : Yolov7 Detector for .Net 6.\r\n\r\n    - [sangyuxiaowu/ml_yolov7](https://github.com/sangyuxiaowu/ml_yolov7) \u003cimg src=\"https://img.shields.io/github/stars/sangyuxiaowu/ml_yolov7?style=social\"/\u003e : ML.NET Yolov7. \"微信公众号「桑榆肖物」《[YOLOv7 在 ML.NET 中使用 ONNX 检测对象](https://mp.weixin.qq.com/s/vXz6gavYJR2mh5KuJO_slA)》\"\r\n\r\n    - [keijiro/TinyYOLOv2Barracuda](https://github.com/keijiro/TinyYOLOv2Barracuda) \u003cimg src=\"https://img.shields.io/github/stars/keijiro/TinyYOLOv2Barracuda?style=social\"/\u003e : Tiny YOLOv2 on Unity Barracuda.\r\n\r\n    - [derenlei/Unity_Detection2AR](https://github.com/derenlei/Unity_Detection2AR) \u003cimg src=\"https://img.shields.io/github/stars/derenlei/Unity_Detection2AR?style=social\"/\u003e : Localize 2D image object detection in 3D Scene with Yolo in Unity Barracuda and ARFoundation.\r\n\r\n    - [died/YOLO3-With-OpenCvSharp4](https://github.com/died/YOLO3-With-OpenCvSharp4) \u003cimg src=\"https://img.shields.io/github/stars/died/YOLO3-With-OpenCvSharp4?style=social\"/\u003e : Demo of implement YOLO v3 with OpenCvSharp v4 on C#.\r\n\r\n    - [mbaske/yolo-unity](https://github.com/mbaske/yolo-unity) \u003cimg src=\"https://img.shields.io/github/stars/mbaske/yolo-unity?style=social\"/\u003e : YOLO In-Game Object Detection for Unity (Windows).\r\n\r\n    - [BobLd/YOLOv4MLNet](https://github.com/BobLd/YOLOv4MLNet) \u003cimg src=\"https://img.shields.io/github/stars/BobLd/YOLOv4MLNet?style=social\"/\u003e : Use the YOLO v4 and v5 (ONNX) models for object detection in C# using ML.Net.\r\n\r\n    - [keijiro/YoloV4TinyBarracuda](https://github.com/keijiro/YoloV4TinyBarracuda) \u003cimg src=\"https://img.shields.io/github/stars/keijiro/YoloV4TinyBarracuda?style=social\"/\u003e : YoloV4TinyBarracuda is an implementation of the YOLOv4-tiny object detection model on the Unity Barracuda neural network inference library.\r\n\r\n    - [zhang8043/YoloWrapper](https://github.com/zhang8043/YoloWrapper) \u003cimg src=\"https://img.shields.io/github/stars/zhang8043/YoloWrapper?style=social\"/\u003e : C#封装YOLOv4算法进行目标检测。\r\n\r\n    - [maalik0786/FastYolo](https://github.com/maalik0786/FastYolo) \u003cimg src=\"https://img.shields.io/github/stars/maalik0786/FastYolo?style=social\"/\u003e : Fast Yolo for fast initializing, object detection and tracking.\r\n\r\n    - [Uehwan/CSharp-Yolo-Video](https://github.com/Uehwan/CSharp-Yolo-Video) \u003cimg src=\"https://img.shields.io/github/stars/Uehwan/CSharp-Yolo-Video?style=social\"/\u003e : C# Yolo for Video.\r\n\r\n    - [HTTP123-A/HumanDetection_Yolov5NET](https://github.com/https://github.com/HTTP123-A/HumanDetection_Yolov5NET) \u003cimg src=\"https://img.shields.io/github/stars/HTTP123-A/HumanDetection_Yolov5NET?style=social\"/\u003e : YOLOv5 object detection with ML.NET, ONNX.\r\n\r\n    - [Celine-Hsieh/Hand_Gesture_Training--yolov4](https://github.com/Celine-Hsieh/Hand_Gesture_Training--yolov4) \u003cimg src=\"https://img.shields.io/github/stars/Celine-Hsieh/Hand_Gesture_Training--yolov4?style=social\"/\u003e : Recognize the gestures' features using the YOLOv4 algorithm.\r\n\r\n    - [lin-tea/YOLOv5DetectionWithCSharp](https://github.com/lin-tea/YOLOv5DetectionWithCSharp) \u003cimg src=\"https://img.shields.io/github/stars/lin-tea/YOLOv5DetectionWithCSharp?style=social\"/\u003e : YOLOv5s inference In C# and Training In Python.\r\n\r\n    - [MirCore/Unity-Object-Detection-and-Localization-with-VR](https://github.com/MirCore/Unity-Object-Detection-and-Localization-with-VR) \u003cimg src=\"https://img.shields.io/github/stars/MirCore/Unity-Object-Detection-and-Localization-with-VR?style=social\"/\u003e : Detect and localize objects from the front-facing camera image of a VR Headset in a 3D Scene in Unity using Yolo and Barracuda.\r\n\r\n    - [CarlAreDHopen-eaton/YoloObjectDetection](https://github.com/CarlAreDHopen-eaton/YoloObjectDetection) \u003cimg src=\"https://img.shields.io/github/stars/CarlAreDHopen-eaton/YoloObjectDetection?style=social\"/\u003e : Yolo Object Detection Application for RTSP streams.\r\n\r\n    - [TimothyMeadows/Yolo6.NetCore](https://github.com/TimothyMeadows/Yolo6.NetCore) \u003cimg src=\"https://img.shields.io/github/stars/TimothyMeadows/Yolo6.NetCore?style=social\"/\u003e : You Only Look Once (v6) for .NET Core LTS.\r\n\r\n    - [mwetzko/EasyYoloDarknet](https://github.com/mwetzko/EasyYoloDarknet) \u003cimg src=\"https://img.shields.io/github/stars/mwetzko/EasyYoloDarknet?style=social\"/\u003e : EasyYoloDarknet.\r\n\r\n    - [mwetzko/EasyYoloDarknet](https://github.com/mwetzko/EasyYoloDarknet) \u003cimg src=\"https://img.shields.io/github/stars/mwetzko/EasyYoloDarknet?style=social\"/\u003e : Windows optimized Yolo / Darknet Compile, Train and Detect.\r\n\r\n    - [cj-mills/Unity-OpenVINO-YOLOX](https://github.com/cj-mills/Unity-OpenVINO-YOLOX) \u003cimg src=\"https://img.shields.io/github/stars/cj-mills/Unity-OpenVINO-YOLOX?style=social\"/\u003e : This tutorial series covers how to perform object detection in the Unity game engine with the OpenVINO™ Toolkit.\r\n\r\n    - [natml-hub/YOLOX](https://github.com/natml-hub/YOLOX) \u003cimg src=\"https://img.shields.io/github/stars/natml-hub/YOLOX?style=social\"/\u003e : High performance object detector based on YOLO series.\r\n\r\n    - [thisistherealdiana/YOLO_project](https://github.com/thisistherealdiana/YOLO_project) \u003cimg src=\"https://img.shields.io/github/stars/thisistherealdiana/YOLO_project?style=social\"/\u003e : YOLO project made by Diana Kereselidze.\r\n\r\n    - [oujunke/Yolo5Net](https://github.com/oujunke/Yolo5Net) \u003cimg src=\"https://img.shields.io/github/stars/oujunke/Yolo5Net?style=social\"/\u003e : Yolo5实现于TensorFlow.Net.\r\n\r\n    - [wojciechp6/YOLO-UnityBarracuda](https://github.com/wojciechp6/YOLO-UnityBarracuda) \u003cimg src=\"https://img.shields.io/github/stars/wojciechp6/YOLO-UnityBarracuda?style=social\"/\u003e : Object detection app build on Unity Barracuda and YOLOv2 Tiny.\r\n\r\n    - [RaminAbbaszadi/YoloWrapper-WPF](https://github.com/RaminAbbaszadi/YoloWrapper-WPF) \u003cimg src=\"https://img.shields.io/github/stars/RaminAbbaszadi/YoloWrapper-WPF?style=social\"/\u003e : WPF (C#) Yolo Darknet Wrapper.\r\n\r\n    - [fengyhack/YoloWpf](https://github.com/fengyhack/YoloWpf) \u003cimg src=\"https://img.shields.io/github/stars/fengyhack/YoloWpf?style=social\"/\u003e : GUI demo for Object Detection with YOLO and OpenCVSharp.\r\n\r\n    - [hanzhuang111/Yolov5Wpf](https://github.com/hanzhuang111/Yolov5Wpf) \u003cimg src=\"https://img.shields.io/github/stars/hanzhuang111/Yolov5Wpf?style=social\"/\u003e : 使用ML.NET部署YOLOV5 的ONNX模型。\r\n\r\n    - [MaikoKingma/yolo-winforms-test](https://github.com/MaikoKingma/yolo-winforms-test) \u003cimg src=\"https://img.shields.io/github/stars/MaikoKingma/yolo-winforms-test?style=social\"/\u003e : A Windows forms application that can execute pre-trained object detection models via ML.NET. In this instance the You Only Look Once version 4 (yolov4) is used.\r\n\r\n    - [SeanAnd/WebcamObjectDetection](https://github.com/SeanAnd/WebcamObjectDetection) \u003cimg src=\"https://img.shields.io/github/stars/SeanAnd/WebcamObjectDetection?style=social\"/\u003e : YOLO object detection using webcam in winforms.\r\n\r\n    - [Devmawi/BlazorObjectDetection-Sample](https://github.com/Devmawi/BlazorObjectDetection-Sample) \u003cimg src=\"https://img.shields.io/github/stars/Devmawi/BlazorObjectDetection-Sample?style=social\"/\u003e : Simple project for demonstrating how to embed a continuously object detection with Yolo on a video in a hybrid Blazor app (WebView2).\r\n\r\n    - [Soju06/yolov5-annotation-viewer](https://github.com/Soju06/yolov5-annotation-viewer) \u003cimg src=\"https://img.shields.io/github/stars/Soju06/yolov5-annotation-viewer?style=social\"/\u003e : yolov5 annotation viewer.\r\n\r\n    - [developer-ken/YoloPredictorMLDotNet](https://github.com/developer-ken/YoloPredictorMLDotNet) \u003cimg src=\"https://img.shields.io/github/stars/developer-ken/YoloPredictorMLDotNet?style=social\"/\u003e : YoloPredictorMLDotNet.\r\n\r\n    - [LionelC-Kyo/CSharp_YoloV5_Torch](https://github.com/LionelC-Kyo/CSharp_YoloV5_Torch) \u003cimg src=\"https://img.shields.io/github/stars/LionelC-Kyo/CSharp_YoloV5_Torch?style=social\"/\u003e : Run Yolo V5 in C# By Torch.\r\n\r\n    - [wanglvhang/OnnxYoloDemo](https://github.com/wanglvhang/OnnxYoloDemo) \u003cimg src=\"https://img.shields.io/github/stars/wanglvhang/OnnxYoloDemo?style=social\"/\u003e : demo of using c# to run yolo onnx model with onnx runtime, and contains a windows capture tool to get bitmap from windows desktop and window.\r\n\r\n    - [BobLd/YOLOv3MLNet](https://github.com/BobLd/YOLOv3MLNet) \u003cimg src=\"https://img.shields.io/github/stars/BobLd/YOLOv3MLNet?style=social\"/\u003e : Use the YOLO v3 (ONNX) model for object detection in C# using ML.Net.\r\n\r\n    - [zgabi/Yolo.Net](https://github.com/zgabi/Yolo.Net) \u003cimg src=\"https://img.shields.io/github/stars/zgabi/Yolo.Net?style=social\"/\u003e : zgabi/Yolo.Net\r\n\r\n    - [aliardan/RoadMarkingDetection](https://github.com/aliardan/RoadMarkingDetection) \u003cimg src=\"https://img.shields.io/github/stars/aliardan/RoadMarkingDetection?style=social\"/\u003e : Road markings detection using yolov5 model based on ONNX.\r\n\r\n    - [TimothyMeadows/Yolo5.NetCore](https://github.com/TimothyMeadows/Yolo5.NetCore) \u003cimg src=\"https://img.shields.io/github/stars/TimothyMeadows/Yolo5.NetCore?style=social\"/\u003e : You Only Look Once (v5) for .NET Core LTS.\r\n\r\n    - [AD-HO/YOLOv5-ML.NET](https://github.com/AD-HO/YOLOv5-ML.NET) \u003cimg src=\"https://img.shields.io/github/stars/AD-HO/YOLOv5-ML.NET?style=social\"/\u003e : Inferencing Yolov5 ONNX model using ML.NET and ONNX Runtime.\r\n\r\n    - [ToxicSkill/YOLOV7-Webcam-inference](https://github.com/ToxicSkill/YOLOV7-Webcam-inference) \u003cimg src=\"https://img.shields.io/github/stars/ToxicSkill/YOLOV7-Webcam-inference?style=social\"/\u003e : Simple WPF program for webcam inference with yoloV7 models.\r\n\r\n    - [aliardan/RoadMarkingDetection](https://github.com/aliardan/RoadMarkingDetection) \u003cimg src=\"https://img.shields.io/github/stars/aliardan/RoadMarkingDetection?style=social\"/\u003e : Road markings detection using yolov5 model based on ONNX.\r\n\r\n    - [rabbitsun2/csharp_and_microsoft_ml_and_yolo_v5_sample](https://github.com/rabbitsun2/csharp_and_microsoft_ml_and_yolo_v5_sample) \u003cimg src=\"https://img.shields.io/github/stars/rabbitsun2/csharp_and_microsoft_ml_and_yolo_v5_sample?style=social\"/\u003e : C#, Microsoft ML, Yolo v5, Microsoft ML.DNN, OpenCVSharp4 연계 프로젝트.\r\n\r\n    - [hsysfan/YOLOv5-Seg-OnnxRuntime](https://github.com/hsysfan/YOLOv5-Seg-OnnxRuntime) \u003cimg src=\"https://img.shields.io/github/stars/hsysfan/YOLOv5-Seg-OnnxRuntime?style=social\"/\u003e : YOLOv5 Segmenation Implementation in C# and OnnxRuntime.\r\n\r\n    - [dme-compunet/YOLOv8](https://github.com/dme-compunet/YOLOv8) \u003cimg src=\"https://img.shields.io/github/stars/dme-compunet/YOLOv8?style=social\"/\u003e : Use YOLOv8 in real-time, for object detection, instance segmentation, pose estimation and image classification, via ONNX Runtime.\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n  - ### Tensorflow and Keras Implementation\r\n\r\n    - [YunYang1994/tensorflow-yolov3](https://github.com/YunYang1994/tensorflow-yolov3) \u003cimg src=\"https://img.shields.io/github/stars/YunYang1994/tensorflow-yolov3?style=social\"/\u003e : 🔥 TensorFlow Code for technical report: \"YOLOv3: An Incremental Improvement\".\r\n\r\n    - [zzh8829/yolov3-tf2](https://github.com/zzh8829/yolov3-tf2) \u003cimg src=\"https://img.shields.io/github/stars/zzh8829/yolov3-tf2?style=social\"/\u003e : YoloV3 Implemented in Tensorflow 2.0.\r\n\r\n    - [hunglc007/tensorflow-yolov4-tflite](https://github.com/hunglc007/tensorflow-yolov4-tflite) \u003cimg src=\"https://img.shields.io/github/stars/hunglc007/tensorflow-yolov4-tflite?style=social\"/\u003e : YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite.\r\n\r\n    - [gliese581gg/YOLO_tensorflow](https://github.com/gliese581gg/YOLO_tensorflow) \u003cimg src=\"https://img.shields.io/github/stars/gliese581gg/YOLO_tensorflow?style=social\"/\u003e : tensorflow implementation of 'YOLO : Real-Time Object Detection'.\r\n\r\n    - [llSourcell/YOLO_Object_Detection](https://github.com/llSourcell/YOLO_Object_Detection) \u003cimg src=\"https://img.shields.io/github/stars/llSourcell/YOLO_Object_Detection?style=social\"/\u003e : This is the code for \"YOLO Object Detection\" by Siraj Raval on Youtube.\r\n\r\n    - [wizyoung/YOLOv3_TensorFlow](https://github.com/wizyoung/YOLOv3_TensorFlow) \u003cimg src=\"https://img.shields.io/github/stars/wizyoung/YOLOv3_TensorFlow?style=social\"/\u003e : Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.\r\n\r\n    - [theAIGuysCode/yolov4-deepsort](https://github.com/theAIGuysCode/yolov4-deepsort) \u003cimg src=\"https://img.shields.io/github/stars/theAIGuysCode/yolov4-deepsort?style=social\"/\u003e : Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.\r\n\r\n    - [mystic123/tensorflow-yolo-v3](https://github.com/mystic123/tensorflow-yolo-v3) \u003cimg src=\"https://img.shields.io/github/stars/mystic123/tensorflow-yolo-v3?style=social\"/\u003e : Implementation of YOLO v3 object detector in Tensorflow (TF-Slim).\r\n\r\n    - [hizhangp/yolo_tensorflow](https://github.com/hizhangp/yolo_tensorflow) \u003cimg src=\"https://img.shields.io/github/stars/hizhangp/yolo_tensorflow?style=social\"/\u003e : Tensorflow implementation of YOLO, including training and test phase.\r\n\r\n    - [nilboy/tensorflow-yolo](https://github.com/nilboy/tensorflow-yolo) \u003cimg src=\"https://img.shields.io/github/stars/nilboy/tensorflow-yolo?style=social\"/\u003e : tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test).\r\n\r\n    - [qqwweee/keras-yolo3](https://github.com/qqwweee/keras-yolo3) \u003cimg src=\"https://img.shields.io/github/stars/qqwweee/keras-yolo3?style=social\"/\u003e : A Keras implementation of YOLOv3 (Tensorflow backend).\r\n\r\n    - [allanzelener/YAD2K](https://github.com/allanzelener/YAD2K) \u003cimg src=\"https://img.shields.io/github/stars/allanzelener/YAD2K?style=social\"/\u003e : YAD2K: Yet Another Darknet 2 Keras.\r\n\r\n    - [experiencor/keras-yolo2](https://github.com/experiencor/keras-yolo2) \u003cimg src=\"https://img.shields.io/github/stars/experiencor/keras-yolo2?style=social\"/\u003e : YOLOv2 in Keras and Applications.\r\n\r\n    - [experiencor/keras-yolo3](https://github.com/experiencor/keras-yolo3) \u003cimg src=\"https://img.shields.io/github/stars/experiencor/keras-yolo3?style=social\"/\u003e : Training and Detecting Objects with YOLO3.\r\n\r\n    - [SpikeKing/keras-yolo3-detection](https://github.com/SpikeKing/keras-yolo3-detection) \u003cimg src=\"https://img.shields.io/github/stars/SpikeKing/keras-yolo3-detection?style=social\"/\u003e : YOLO v3 物体检测算法。\r\n\r\n    - [xiaochus/YOLOv3](https://github.com/xiaochus/YOLOv3) \u003cimg src=\"https://img.shields.io/github/stars/xiaochus/YOLOv3?style=social\"/\u003e : Keras implementation of yolo v3 object detection.\r\n\r\n    - [bubbliiiing/yolo3-keras](https://github.com/bubbliiiing/yolo3-keras) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolo3-keras?style=social\"/\u003e : 这是一个yolo3-keras的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov4-keras](https://github.com/bubbliiiing/yolov4-keras) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov4-keras?style=social\"/\u003e : 这是一个YoloV4-keras的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov4-tf2](https://github.com/bubbliiiing/yolov4-tf2) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov4-tf2?style=social\"/\u003e : 这是一个yolo4-tf2（tensorflow2）的源码，可以用于训练自己的模型。\r\n\r\n    - [bubbliiiing/yolov4-tiny-tf2](https://github.com/bubbliiiing/yolov4-tiny-tf2) \u003cimg src=\"https://img.shields.io/github/stars/bubbliiiing/yolov4-tiny-tf2?style=social\"/\u003e : 这是一个YoloV4-tiny-tf2的源码，可以用于训练自己的模型。\r\n\r\n    - [pythonlessons/TensorFlow-2.x-YOLOv3](https://github.com/pythonlessons/TensorFlow-2.x-YOLOv3) \u003cimg src=\"https://img.shields.io/github/stars/pythonlessons/TensorFlow-2.x-YOLOv3?style=social\"/\u003e : YOLOv3 implementation in TensorFlow 2.3.1.\r\n\r\n    - [miemie2013/Keras-YOLOv4](https://github.com/miemie2013/Keras-YOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/miemie2013/Keras-YOLOv4?style=social\"/\u003e : PPYOLO AND YOLOv4.\r\n\r\n    - [Ma-Dan/keras-yolo4](https://github.com/Ma-Dan/keras-yolo4) \u003cimg src=\"https://img.shields.io/github/stars/Ma-Dan/keras-yolo4?style=social\"/\u003e : A Keras implementation of YOLOv4 (Tensorflow backend).\r\n\r\n    - [miranthajayatilake/YOLOw-Keras](https://github.com/miranthajayatilake/YOLOw-Keras) \u003cimg src=\"https://img.shields.io/github/stars/miranthajayatilake/YOLOw-Keras?style=social\"/\u003e : YOLOv2 Object Detection w/ Keras (in just 20 lines of code).\r\n\r\n    - [maiminh1996/YOLOv3-tensorflow](https://github.com/maiminh1996/YOLOv3-tensorflow) \u003cimg src=\"https://img.shields.io/github/stars/maiminh1996/YOLOv3-tensorflow?style=social\"/\u003e : Re-implement YOLOv3 with TensorFlow.\r\n\r\n    - [Stick-To/Object-Detection-Tensorflow](https://github.com/Stick-To/Object-Detection-Tensorflow) \u003cimg src=\"https://img.shields.io/github/stars/Stick-To/Object-Detection-Tensorflow?style=social\"/\u003e : Object Detection API Tensorflow.\r\n\r\n    - [avBuffer/Yolov5_tf](https://github.com/avBuffer/Yolov5_tf) \u003cimg src=\"https://img.shields.io/github/stars/avBuffer/Yolov5_tf?style=social\"/\u003e : Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow.\r\n\r\n    - [ruiminshen/yolo-tf](https://github.com/ruiminshen/yolo-tf) \u003cimg src=\"https://img.shields.io/github/stars/ruiminshen/yolo-tf?style=social\"/\u003e : TensorFlow implementation of the YOLO (You Only Look Once).\r\n\r\n    - [xiao9616/yolo4_tensorflow2](https://github.com/xiao9616/yolo4_tensorflow2) \u003cimg src=\"https://img.shields.io/github/stars/xiao9616/yolo4_tensorflow2?style=social\"/\u003e : yolo 4th edition implemented by tensorflow2.0.\r\n\r\n    - [sicara/tf2-yolov4](https://github.com/sicara/tf2-yolov4) \u003cimg src=\"https://img.shields.io/github/stars/sicara/tf2-yolov4?style=social\"/\u003e : A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection.\r\n\r\n    - [LongxingTan/Yolov5](https://github.com/LongxingTan/Yolov5) \u003cimg src=\"https://img.shields.io/github/stars/LongxingTan/Yolov5?style=social\"/\u003e : Efficient implementation of YOLOV5 in TensorFlow2.\r\n\r\n    - [geekjr/quickai](https://github.com/geekjr/quickai) \u003cimg src=\"https://img.shields.io/github/stars/geekjr/quickai?style=social\"/\u003e : QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.\r\n\r\n    - [CV_Lab/yolov5_rt_tfjs](https://gitee.com/CV_Lab/yolov5_rt_tfjs) : 🚀 基于TensorFlow.js的YOLOv5实时目标检测项目。\r\n\r\n    - [Burf/TFDetection](https://github.com/Burf/TFDetection) \u003cimg src=\"https://img.shields.io/github/stars/Burf/TFDetection?style=social\"/\u003e : A Detection Toolbox for Tensorflow2.\r\n\r\n    - [taipingeric/yolo-v4-tf.keras](https://github.com/taipingeric/yolo-v4-tf.keras) \u003cimg src=\"https://img.shields.io/github/stars/taipingeric/yolo-v4-tf.keras?style=social\"/\u003e : A simple tf.keras implementation of YOLO v4.\r\n\r\n    - [david8862/keras-YOLOv3-model-set](https://github.com/david8862/keras-YOLOv3-model-set) \u003cimg src=\"https://img.shields.io/github/stars/david8862/keras-YOLOv3-model-set?style=social\"/\u003e : end-to-end YOLOv4/v3/v2 object detection pipeline, implemented on tf.keras with different technologies.\r\n\r\n\r\n  - ### PaddlePaddle Implementation\r\n\r\n    - [PaddlePaddle/PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) \u003cimg src=\"https://img.shields.io/github/stars/PaddlePaddle/PaddleDetection?style=social\"/\u003e : Object Detection toolkit based on PaddlePaddle. \"PP-YOLO: An Effective and Efficient Implementation of Object Detector\". (**[arXiv 2020](https://arxiv.org/abs/2007.12099)**)\r\n\r\n    - [nemonameless/PaddleDetection_YOLOv5](https://github.com/nemonameless/PaddleDetection_YOLOv5) \u003cimg src=\"https://img.shields.io/github/stars/nemonameless/PaddleDetection_YOLOv5?style=social\"/\u003e : YOLOv5 of PaddleDetection, Paddle implementation of YOLOv5.\r\n\r\n    - [nemonameless/PaddleDetection_YOLOX](https://github.com/nemonameless/PaddleDetection_YOLOX) \u003cimg src=\"https://img.shields.io/github/stars/nemonameless/PaddleDetection_YOLOX?style=social\"/\u003e : Paddle YOLOX, 51.8% on COCO val by YOLOX-x, 44.6% on YOLOX-ConvNeXt-s.\r\n\r\n    - [nemonameless/PaddleDetection_YOLOset](https://github.com/nemonameless/PaddleDetection_YOLOset) \u003cimg src=\"https://img.shields.io/github/stars/nemonameless/PaddleDetection_YOLOset?style=social\"/\u003e : Paddle YOLO set: YOLOv3, PPYOLO, PPYOLOE, YOLOX, YOLOv5, YOLOv7 and so on.\r\n\r\n    - [miemie2013/Paddle-YOLOv4](https://github.com/miemie2013/Paddle-YOLOv4) \u003cimg src=\"https://img.shields.io/github/stars/miemie2013/Paddle-YOLOv4?style=social\"/\u003e : Paddle-YOLOv4.\r\n\r\n    - [Sharpiless/PaddleDetection-Yolov5](https://github.com/Sharpiless/PaddleDetection-Yolov5) \u003cimg src=\"https://img.shields.io/github/stars/Sharpiless/PaddleDetection-Yolov5?style=social\"/\u003e : 基于Paddlepaddle复现yolov5，支持PaddleDetection接口。\r\n\r\n    - [Nioolek/PPYOLOE_pytorch](https://github.com/Nioolek/PPYOLOE_pytorch) \u003cimg src=\"https://img.shields.io/github/stars/Nioolek/PPYOLOE_pytorch?style=social\"/\u003e : An unofficial implementation of Pytorch version PP-YOLOE,based on Megvii YOLOX training code.\r\n\r\n\r\n  - ### Caffe Implementation\r\n\r\n    - [ChenYingpeng/caffe-yolov3](https://github.com/ChenYingpeng/caffe-yolov3) \u003cimg src=\"https://img.shields.io/github/stars/ChenYingpeng/caffe-yolov3?style=social\"/\u003e : A real-time object detection framework of Yolov3/v4 based on caffe.\r\n\r\n    - [ChenYingpeng/darknet2caffe](https://github.com/ChenYingpeng/darknet2caffe) \u003cimg src=\"https://img.shields.io/github/stars/ChenYingpeng/darknet2caffe?style=social\"/\u003e : Convert darknet weights to caffemodel.\r\n\r\n    - [eric612/Caffe-YOLOv3-Windows](https://github.com/eric612/Caffe-YOLOv3-Windows) \u003cimg src=\"https://img.shields.io/github/stars/eric612/Caffe-YOLOv3-Windows?style=social\"/\u003e : A windows caffe implementation of YOLO detection network.\r\n\r\n    - [Harick1/caffe-yolo](https://github.com/Harick1/caffe-yolo) \u003cimg src=\"https://img.shields.io/github/stars/Harick1/caffe-yolo?style=social\"/\u003e : Caffe for YOLO.\r\n\r\n    - [choasup/caffe-yolo9000](https://github.com/choasup/caffe-yolo9000) \u003cimg src=\"https://img.shields.io/github/stars/choasup/caffe-yolo9000?style=social\"/\u003e : Caffe for YOLOv2 \u0026 YOLO9000.\r\n\r\n    - [gklz1982/caffe-yolov2](https://github.com/gklz1982/caffe-yolov2) \u003cimg src=\"https://img.shields.io/github/stars/gklz1982/caffe-yolov2?style=social\"/\u003e : caffe-yolov2.\r\n\r\n\r\n  - ### MXNet Implementation\r\n\r\n    - [Gluon CV Toolkit](https://github.com/dmlc/gluon-cv) \u003cimg src=\"https://img.shields.io/github/stars/dmlc/gluon-cv?style=social\"/\u003e : GluonCV provides implementations of the state-of-the-art (SOTA) deep learning models in computer vision.\r\n\r\n    - [zhreshold/mxnet-yolo](https://github.com/zhreshold/mxnet-yolo) \u003cimg src=\"https://img.shields.io/github/stars/zhreshold/mxnet-yolo?style=social\"/\u003e : YOLO: You only look once real-time object detector.\r\n\r\n\r\n  - ### Web Implementation\r\n\r\n    - [ModelDepot/tfjs-yolo-tiny](https://github.com/ModelDepot/tfjs-yolo-tiny) \u003cimg src=\"https://img.shields.io/github/stars/ModelDepot/tfjs-yolo-tiny?style=social\"/\u003e : In-Browser Object Detection using Tiny YOLO on Tensorflow.js.\r\n\r\n    - [justadudewhohacks/tfjs-tiny-yolov2](https://github.com/justadudewhohacks/tfjs-tiny-yolov2) \u003cimg src=\"https://img.shields.io/github/stars/justadudewhohacks/tfjs-tiny-yolov2?style=social\"/\u003e : Tiny YOLO v2 object detection with tensorflow.js.\r\n\r\n    - [reu2018DL/YOLO-LITE](https://github.com/reu2018DL/YOLO-LITE) \u003cimg src=\"https://img.shields.io/github/stars/reu2018DL/YOLO-LITE?style=social\"/\u003e : YOLO-LITE is a web implementation of YOLOv2-tiny.\r\n\r\n    - [mobimeo/node-yolo](https://github.com/mobimeo/node-yolo) \u003cimg src=\"https://img.shields.io/github/stars/mobimeo/node-yolo?style=social\"/\u003e : Node bindings for YOLO/Darknet image recognition library.\r\n\r\n    - [Sharpiless/Yolov5-Flask-VUE](https://github.com/Sharpiless/Yolov5-Flask-VUE) \u003cimg src=\"https://img.shields.io/github/stars/Sharpiless/Yolov5-Flask-VUE?style=social\"/\u003e : 基于Flask开发后端、VUE开发前端框架，在WEB端部署YOLOv5目标检测模型。\r\n\r\n    - [shaqian/tfjs-yolo](https://github.com/shaqian/tfjs-yolo) \u003cimg src=\"https://img.shields.io/github/stars/shaqian/tfjs-yolo?style=social\"/\u003e : YOLO v3 and Tiny YOLO v1, v2, v3 with Tensorflow.js.\r\n\r\n    - [zqingr/tfjs-yolov3](https://github.com/zqingr/tfjs-yolov3) \u003cimg src=\"https://img.shields.io/github/stars/zqingr/tfjs-yolov3?style=social\"/\u003e : A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny.\r\n\r\n    - [bennetthardwick/darknet.js](https://github.com/bennetthardwick/darknet.js) \u003cimg src=\"https://img.shields.io/github/stars/bennetthardwick/darknet.js?style=social\"/\u003e : A NodeJS wrapper of pjreddie's darknet / yolo.\r\n\r\n    - [nihui/ncnn-webassembly-yolov5](https://github.com/nihui/ncnn-webassembly-yolov5) \u003cimg src=\"https://img.shields.io/github/stars/nihui/ncnn-webassembly-yolov5?style=social\"/\u003e : Deploy YOLOv5 in your web browser with ncnn and webassembly.\r\n\r\n    - [muhk01/Yolov5-on-Flask](https://github.com/muhk01/Yolov5-on-Flask) \u003cimg src=\"https://img.shields.io/github/stars/muhk01/Yolov5-on-Flask?style=social\"/\u003e : Running YOLOv5 through web browser using Flask microframework.\r\n\r\n    - [tcyfree/yolov5](https://github.com/tcyfree/yolov5) \u003cimg src=\"https://img.shields.io/github/stars/tcyfree/yolov5?style=social\"/\u003e : 基于Flask开发后端、VUE开发前端框架，在WEB端部署YOLOv5目标检测模型。\r\n\r\n    - [siffyy/YOLOv5-Web-App-for-Vehicle-Detection](https://github.com/siffyy/YOLOv5-Web-App-for-Vehicle-Detection) \u003cimg src=\"https://img.shields.io/github/stars/siffyy/YOLOv5-Web-App-for-Vehicle-Detection?style=social\"/\u003e : Repo for Web Application for Vehicle detection from Satellite Imagery using YOLOv5 model.\r\n\r\n    - [Devmawi/BlazorObjectDetection-Sample](https://github.com/Devmawi/BlazorObjectDetection-Sample) \u003cimg src=\"https://img.shields.io/github/stars/Devmawi/BlazorObjectDetection-Sample?style=social\"/\u003e : A sample for demonstrating online execution of an onnx model by a Blazor app.\r\n\r\n    - [Hyuto/yolov5-onnxruntime-web](https://github.com/Hyuto/yolov5-onnxruntime-web) \u003cimg src=\"https://img.shields.io/github/stars/Hyuto/yolov5-onnxruntime-web?style=social\"/\u003e : YOLOv5 right in your browser with onnxruntime-web.\r\n\r\n\r\n  - ### Others\r\n\r\n    - [jinfagang/yolov7_d2](https://github.com/jinfagang/yolov7_d2) \u003cimg src=\"https://img.shields.io/github/stars/jinfagang/yolov7_d2?style=social\"/\u003e : 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥\r\n\r\n    - [yang-0201/YOLOv6_pro](https://github.com/yang-0201/YOLOv6_pro) \u003cimg src=\"https://img.shields.io/github/stars/yang-0201/YOLOv6_pro?style=social\"/\u003e : Make it easier for yolov6 to change the network structure.\r\n\r\n    - [j-marple-dev/AYolov2](https://github.com/j-marple-dev/AYolov2) \u003cimg src=\"https://img.shields.io/github/stars/j-marple-dev/AYolov2?style=social\"/\u003e : The main goal of this repository is to rewrite the object detection pipeline with a better code structure for better portability and adaptability to apply new experimental methods. The object detection pipeline is based on [Ultralytics YOLOv5](https://github.com/ultralytics/yolov5).\r\n\r\n    - [fcakyon/yolov5-pip](https://github.com/fcakyon/yolov5-pip) \u003cimg src=\"https://img.shields.io/github/stars/fcakyon/yolov5-pip?style=social\"/\u003e : Packaged version of ultralytics/yolov5.\r\n\r\n    - [kadirnar/yolov6-pip](https://github.com/kadirnar/yolov6-pip) \u003cimg src=\"https://img.shields.io/github/stars/kadirnar/yolov6-pip?style=social\"/\u003e : Packaged version of yolov6 model.\r\n\r\n    - [kadirnar/yolov7-pip](https://github.com/kadirnar/yolov7-pip) \u003cimg src=\"https://img.shields.io/github/stars/kadirnar/yolov7-pip?style=social\"/\u003e : Packaged version of yolov7 model.\r\n\r\n    - [kadirnar/torchyolo](https://github.com/kadirnar/torchyolo) \u003cimg src=\"https://img.shields.io/github/stars/kadirnar/torchyolo?style=social\"/\u003e : PyTorch implementation of YOLOv5, YOLOv6, YOLOv7, YOLOX.\r\n\r\n    - [CvPytorch](https://github.com/shanglianlm0525/CvPytorch) \u003cimg src=\"https://img.shields.io/github/stars/shanglianlm0525/CvPytorch?style=social\"/\u003e : CvPytorch is an open source COMPUTER VISION toolbox based on PyTorch.\r\n\r\n    - [Holocron](https://github.com/frgfm/Holocron) \u003cimg src=\"https://img.shields.io/github/stars/frgfm/Holocron?style=social\"/\u003e : PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss).\r\n\r\n    - [DL-Practise/YoloAll](https://github.com/DL-Practise/YoloAll) \u003cimg src=\"https://img.shields.io/github/stars/DL-Practise/YoloAll?style=social\"/\u003e : YoloAll is a collection of yolo all versions. you you use YoloAll to test yolov3/yolov5/yolox/yolo_fastest.\r\n\r\n    - [msnh2012/Msnhnet](https://github.com/msnh2012/Msnhnet) \u003cimg src=\"https://img.shields.io/github/stars/msnh2012/Msnhnet?style=social\"/\u003e : (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.\r\n\r\n    - [xinghanliuying/yolov5-trick](https://github.com/xinghanliuying/yolov5-trick) \u003cimg src=\"https://img.shields.io/github/stars/xinghanliuying/yolov5-trick?style=social\"/\u003e : 基于yolov5的改进库。\r\n\r\n    - [BMW-InnovationLab/BMW-YOLOv4-Training-Automation](https://github.com/BMW-InnovationLab/BMW-YOLOv4-Training-Automation) \u003cimg src=\"https://img.shields.io/github/stars/BMW-InnovationLab/BMW-YOLOv4-Training-Automation?style=social\"/\u003e : YOLOv4-v3 Training Automation API for Linux.\r\n\r\n    - [AntonMu/TrainYourOwnYOLO](https://github.com/AntonMu/TrainYourOwnYOLO) \u003cimg src=\"https://img.shields.io/github/stars/AntonMu/TrainYourOwnYOLO?style=social\"/\u003e : Train a state-of-the-art yolov3 object detector from scratch!\r\n\r\n    - [madhawav/YOLO3-4-Py](https://github.com/madhawav/YOLO3-4-Py) \u003cimg src=\"https://img.shields.io/github/stars/madhawav/YOLO3-4-Py?style=social\"/\u003e : A Python wrapper on Darknet. Compatible with YOLO V3.\r\n\r\n    - [theAIGuysCode/yolov4-custom-functions](https://github.com/theAIGuysCode/yolov4-custom-functions) \u003cimg src=\"https://img.shields.io/github/stars/theAIGuysCode/yolov4-custom-functions?style=social\"/\u003e : A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.\r\n\r\n    - [tiquasar/FLAITER](https://github.com/tiquasar/FLAITER) \u003cimg src=\"https://img.shields.io/github/stars/tiquasar/FLAITER?style=social\"/\u003e : Machine Learning and AI Mobile Application.\r\n\r\n    - [kadirnar/Minimal-Yolov6](https://github.com/kadirnar/Minimal-Yolov6) \u003cimg src=\"https://img.shields.io/github/stars/kadirnar/Minimal-Yolov6?style=social\"/\u003e : Minimal-Yolov6.\r\n\r\n    - [DataXujing/YOLOv6](https://github.com/DataXujing/YOLOv6) \u003cimg src=\"https://img.shields.io/github/stars/DataXujing/YOLOv6?style=social\"/\u003e : 🌀 🌀 手摸手 美团 YOLOv6模型训练和TensorRT端到端部署方案教程。\r\n\r\n    - [DataXujing/YOLOv7](https://github.com/DataXujing/YOLOv7) \u003cimg src=\"https://img.shields.io/github/stars/DataXujing/YOLOv7?style=social\"/\u003e : 🔥🔥🔥 Official YOLOv7训练自己的数据集并实现端到端的TensorRT模型加速推断。\r\n\r\n    - [DataXujing/YOLOv8](https://github.com/DataXujing/YOLOv8) \u003cimg src=\"https://img.shields.io/github/stars/DataXujing/YOLOv8?style=social\"/\u003e : 🔥 Official YOLOv8模型训练和部署。Official YOLOv8 训练自己的数据集并基于NVIDIA TensorRT和华为昇腾端到端模型加速以及安卓手机端部署。\r\n\r\n    - [DataXujing/YOLOv9](https://github.com/DataXujing/YOLOv9) \u003cimg src=\"https://img.shields.io/github/stars/DataXujing/YOLOv9?style=social\"/\u003e : 🔥 YOLOv9 paper解析，训练自己的数据集，TensorRT端到端部署， NCNN安卓手机部署。\r\n\r\n    - [Code-keys/yolov5-darknet](https://github.com/Code-keys/yolov5-darknet) \u003cimg src=\"https://img.shields.io/github/stars/Code-keys/yolov5-darknet?style=social\"/\u003e : yolov5-darknet support yaml \u0026\u0026 cfg.\r\n\r\n    - [Code-keys/yolo-darknet](https://github.com/Code-keys/yolo-darknet) \u003cimg src=\"https://img.shields.io/github/stars/Code-keys/yolo-darknet?style=social\"/\u003e : YOLO-family complemented by darknet. yolov5 yolov7 et al ...\r\n\r\n    - [pooya-mohammadi/deep_utils](https://github.com/pooya-mohammadi/deep_utils) \u003cimg src=\"https://img.shields.io/github/stars/pooya-mohammadi/deep_utils?style=social\"/\u003e : A toolkit full of handy functions including most used models and utilities for deep-learning practitioners!\r\n\r\n    - [yl-jiang/YOLOSeries](https://github.com/yl-jiang/YOLOSeries) \u003cimg src=\"https://img.shields.io/github/stars/yl-jiang/YOLOSeries?style=social\"/\u003e : YOLO Series.\r\n\r\n    - [yjh0410/FreeYOLO](https://github.com/yjh0410/FreeYOLO) \u003cimg src=\"https://img.shields.io/github/stars/yjh0410/FreeYOLO?style=social\"/\u003e : FreeYOLO is inspired by many other excellent works, such as YOLOv7 and YOLOX.\r\n\r\n    - [open-yolo/yolov7](https://github.com/open-yolo/yolov7) \u003cimg src=\"https://img.shields.io/github/stars/open-yolo/yolov7?style=social\"/\u003e : Improved and packaged version of WongKinYiu/yolov7.\r\n\r\n    - [iloveai8086/YOLOC](https://github.com/iloveai8086/YOLOC) \u003cimg src=\"https://img.shields.io/github/stars/iloveai8086/YOLOC?style=social\"/\u003e : 🚀YOLOC is Combining different modules to build an different Object detection model.\r\n\r\n    - [miemie2013/miemiedetection](https://github.com/miemie2013/miemiedetection) \u003cimg src=\"https://img.shields.io/github/stars/miemie2013/miemiedetection?style=social\"/\u003e : Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、SOLOv2 an so on.\r\n\r\n    - [RyanCCC/YOLOSeries](https://github.com/RyanCCC/YOLOSeries) \u003cimg src=\"https://img.shields.io/github/stars/RyanCCC/YOLOSeries?style=social\"/\u003e : YOLO算法的实现。\r\n\r\n    - [HuKai97/YOLOX-Annotations](https://github.com/HuKai97/YOLOX-Annotations) \u003cimg src=\"https://img.shields.io/github/stars/HuKai97/YOLOX-Annotations?style=social\"/\u003e : 一个YOLOX的中文注释版本，供大家参考学习！\r\n\r\n    - [isLinXu/YOLOv8_Efficient](https://github.com/isLinXu/YOLOv8_Efficient) \u003cimg src=\"https://img.shields.io/github/stars/isLinXu/YOLOv8_Efficient?style=social\"/\u003e : 🚀Simple and efficient use for Ultralytics yolov8🚀\r\n\r\n    - [z1069614715/objectdetection_script](https://github.com/z1069614715/objectdetection_script) \u003cimg src=\"https://img.shields.io/github/stars/z1069614715/objectdetection_script?style=social\"/\u003e : 一些关于目标检测的脚本的改进思路代码。\r\n\r\n\r\n\r\n\r\n## Lighter and Deployment Frameworks\r\n\r\n\r\n  - ### High-performance Inference Engine\r\n    #### 高性能推理引擎\r\n\r\n    - ##### ONNX\r\n\r\n        - [ONNX Runtime](https://github.com/microsoft/onnxruntime) \u003cimg src=\"https://img.shields.io/github/stars/microsoft/onnxruntime?style=social\"/\u003e : ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/coderonion%2Fawesome-yolo-object-detection/projects"}