Awesome-YOLO-Object-Detection

🚀🚀🚀 YOLO is a great real-time one-stage object detection framework. This repository lists some awesome public YOLO object detection projects and datasets.

Contents

• Awesome-YOLO-Object-Detection
  • Summary
    • Famous YOLO
    • Extensional Frameworks
    • Awesome List
    • Paper and Code Overview
      • Paper Review
      • Code Review
    • Learning Resources
  • Other Versions of YOLO
    • PyTorch Implementation
    • C Implementation
    • CPP Implementation
    • ROS Implementation
    • Mojo Implementation
    • Rust Implementation
    • Go Implementation
    • CSharp Implementation
    • Tensorflow and Keras Implementation
    • PaddlePaddle Implementation
    • Caffe Implementation
    • MXNet Implementation
    • Web Implementation
    • Others
  • Lighter and Deployment Frameworks
    • High-performance Inference Engine
      • ONNX
      • TensorRT
      • DeepStream
      • OpenVINO
      • NCNN
      • MNN
      • Other Engine
    • NPU and FPGA Hardware Deployment
      • RK3588
      • FPGA
      • Other Hardware
    • Pruning Knoweldge-Distillation Quantization
      • Pruning
      • Quantization
      • Knoweldge-Distillation
    • Lightweight Backbones and FPN
  • Object Detection Applications
    • Open World Object Detection
    • Few-shot Object Detection
    • Small Object Detection
    • Multimodal Image Detection
    • Video Object Detection
    • Object Tracking
      • Multi-Object Tracking
      • Dynamic Object Tracking
    • Deep Reinforcement Learning
    • Motion Control Field
    • Super-Resolution Field
    • Spiking Neural Network
    • Attention and Transformer
    • Oriented Object Detection
    • Face Detection and Recognition
      • Face Detection
      • Face Recognition
    • Face Mask Detection
    • Social Distance Detection
    • Autonomous Driving Field Detection
      • Vehicle Detection
      • License Plate Detection and Recognition
      • Lane Detection
      • Driving Behavior Detection
      • Parking Slot Detection
      • Traffic Light Detection
      • Traffic Sign Detection
      • Crosswalk Detection
      • Traffic Accidents Detection
      • Road Damage Detection
    • Animal Detection
    • Helmet Detection
    • Hand Detection
    • Gesture Recognition
    • Action Detection
    • Emotion Recognition
    • Human Pose Estimation
    • Distance Measurement
    • Instance and Semantic Segmentation
    • 3D Object Detection
    • SLAM Field Detection
    • Industrial Defect Detection
    • SAR Image Detection
    • Safety Monitoring Field Detection
    • Anti-UAV Field Detection
    • Medical Field Detection
    • Chemistry Field Detection
    • Agricultural Field Detection
    • Sports Field Detection
    • Aerial Imagery Detection
    • Adverse Weather Conditions
    • Adversarial Attack and Defense
    • Camouflaged Detection
    • Game Field Detection
    • Automatic Annotation Tools
    • Feature Map Visualization
    • Object Detection Evaluation Metrics
    • GUI
      • Swift-Related
      • Flutter-Related
      • Streamlit-Related
      • Gradio-Related
      • QT-Related
      • PySide-Related
    • Other Applications
  • Object Detection Datasets
    • Datasets Share Platform
    • Datasets Tools
      • Data Annotation
      • Data Augmentation
      • Data Management
    • General Detection and Recognition Datasets
      • General Object Detection Datasets
      • General Object Recognition Datasets
    • Autonomous Driving Datasets
      • Diverse Autonomous Driving Datasets
      • Traffic Sign Detection Datasets
      • License Plate Detection and Recognition Datasets
    • Adverse Weather Datasets
    • Person Detection Datasets
    • Anti-UAV Datasets
    • Optical Aerial Imagery Datasets
    • Low-light Image Datasets
    • Infrared Image Datasets
    • SAR Image Datasets
    • Sonar Image Datasets
    • Multimodal Image Datasets
    • 3D Object Detection Datasets
    • Vehicle-to-Everything Field Datasets
    • Super-Resolution Field Datasets
    • Face Detection and Recognition Datasets
      • Face Detection Datasets
      • Face Recognition Datasets
  • Blogs
  • Videos

Summary

• Famous YOLO

  • YOLOv1 (Darknet ) : "You Only Look Once: Unified, Real-Time Object Detection". (CVPR 2016)

  • YOLOv2 (Darknet ) : "YOLO9000: Better, Faster, Stronger". (CVPR 2017)

  • YOLOv3 (Darknet ) : "YOLOv3: An Incremental Improvement". (arXiv 2018)

  • YOLOv4 (WongKinYiu/PyTorch_YOLOv4 ) : "YOLOv4: Optimal Speed and Accuracy of Object Detection". (arXiv 2020)

  • Scaled-YOLOv4 (WongKinYiu/ScaledYOLOv4 ) : "Scaled-YOLOv4: Scaling Cross Stage Partial Network". (CVPR 2021)

  • YOLOv5 : YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite. docs.ultralytics.com. YOLOv5 🚀 is the world's most loved vision AI, representing Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.

  • YOLOv6 : "YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications". (arXiv 2022).

  • YOLOv7 : "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors". (CVPR 2023).

  • YOLOv8 : NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite. docs.ultralytics.com

  • YOLOv9 : "YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information". (arXiv 2024)

  • MultimediaTechLab/YOLO : 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.

  • YOLOv10 : "YOLOv10: Real-Time End-to-End Object Detection". (arXiv 2024)

  • YOLOv11 : NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite. Ultralytics YOLOv11 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

  • YOLOv12 : "YOLOv12: Attention-Centric Real-Time Object Detectors". (arXiv 2025)

  • YOLO-World | YOLO-World-v2 : "YOLO-World: Real-Time Open-Vocabulary Object Detection". (CVPR 2024). www.yoloworld.cc

  • YOLOE : "YOLOE: Real-Time Seeing Anything". (arXiv 2025).

• Extensional Frameworks

  • Qwen2.5-VL : Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud. "Qwen2.5-VL Technical Report". (arXiv 2025). 2025-01-26，Qwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL!. "Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution". (arXiv 2024). "Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond". (arXiv 2023).

  • Kimi-VL : Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities. "Kimi-VL Technical Report". (arXiv 2025).

  • Visual-RFT : 🌈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).

  • VLM-R1 : 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.

  • Florence-2 : "Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks". (CVPR 2024).

  • maestro : 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, PaliGemma 2, and Qwen2.5-VL. maestro.roboflow.com

  • Autodistill : 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

  • EdgeYOLO : 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). "EdgeYOLO: An Edge-Real-Time Object Detector". (arXiv 2023)

  • YOLOX : "YOLOX: Exceeding YOLO Series in 2021". (arXiv 2021)

  • YOLOR : "You Only Learn One Representation: Unified Network for Multiple Tasks". (arXiv 2021)

  • YOLOF : "You Only Look One-level Feature". (CVPR 2021).

  • YOLOS : "You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection". (NeurIPS 2021)

  • DAMO-YOLO : 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)

  • YOLO-NAS : Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS. 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.

  • LeYOLO : "LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection". (arXiv 2024)

  • DynamicDet : "DynamicDet: A Unified Dynamic Architecture for Object Detection". (CVPR 2023)

  • DINO : "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection". (ICLR 2023).

  • GroundingDINO : "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection". (ECCV 2024).

  • RT-DETR | RT-DETRv2 : "DETRs Beat YOLOs on Real-time Object Detection". (CVPR 2024). "RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer". (arXiv 2024).

  • EasyCV : An all-in-one toolkit for computer vision. "YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6". (arXiv 2022).

  • YOLACT & YOLACT++ : You Only Look At CoefficienTs. (ICCV 2019, IEEE TPAMI 2020)

  • Alpha-IoU : "Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression". (NeurIPS 2021)

  • CIoU : Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT). (AAAI 2020, IEEE TCYB 2021)

  • Albumentations : 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)

  • doubleZ0108/Data-Augmentation : General Data Augmentation Algorithms for Object Detection(esp. Yolo).

• Awesome List

  • awesome-yolo-object-detection : 🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.

  • srebroa/awesome-yolo : 🚀 ⭐ The list of the most popular YOLO algorithms - awesome YOLO.

  • Bubble-water/YOLO-Summary : YOLO-Summary.

  • WZMIAOMIAO/deep-learning-for-image-processing : deep learning for image processing including classification and object-detection etc.

  • hoya012/deep_learning_object_detection : A paper list of object detection using deep learning.

  • amusi/awesome-object-detection : Awesome Object Detection.

  • wenhwu/awesome-remote-sensing-change-detection : List of datasets, codes, and contests related to remote sensing change detection.

  • ZHOUYI1023/awesome-radar-perception : A curated list of radar datasets, detection, tracking and fusion.

  • lartpang/awesome-segmentation-saliency-dataset : A collection of some datasets for segmentation / saliency detection. Welcome to PR...😄

  • TianhaoFu/Awesome-3D-Object-Detection : Papers, code and datasets about deep learning for 3D Object Detection.

  • xahidbuffon/Awesome_Underwater_Datasets : Pointers to large-scale underwater datasets and relevant resources.

  • M-3LAB/awesome-industrial-anomaly-detection : Paper list and datasets for industrial image anomaly detection.

  • ZhangXiwuu/Awesome_visual_place_recognition_datasets : A curated list of Visual Place Recognition (VPR)/ loop closure detection (LCD) datasets.

  • ari-dasci/OD-WeaponDetection : Datasets for weapon detection based on image classification and object detection tasks.

  • DLLXW/objectDetectionDatasets : 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。

  • kuanhungchen/awesome-tiny-object-detection : 🕶 A curated list of Tiny Object Detection papers and related resources.

• Paper and Code Overview

  • Paper Review

    • 52CV/CV-Surveys : 计算机视觉相关综述。包括目标检测、跟踪........

    • GreenTeaHua/YOLO-Review : "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 & Information Technology 2022)

    • "A Review of Yolo Algorithm Developments". (Procedia Computer Science 2022)

  • Code Review

    • iscyy/ultralyticsPro : 🔥🔥🔥 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🚀

    • MMDetection : OpenMMLab Detection Toolbox and Benchmark. mmdetection.readthedocs.io. (arXiv 2019)

    • MMYOLO : OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOX, PPYOLOE, etc. mmyolo.readthedocs.io/zh_CN/dev/

    • iscyy/yoloair : 🔥🔥🔥 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。

    • iscyy/yoloair2 : ☁️💡🎈专注于改进YOLOv7，Support to improve Backbone, Neck, Head, Loss, IoU, NMS and other modules.

    • jizhishutong/YOLOU : 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！》"

    • WangQvQ/Yolov5_Magic : YOLO Magic🪄 is an extension based on Ultralytics' YOLOv5, designed to provide more powerful functionality and simpler operations for visual tasks.

    • positive666/yolo_research : 🚀 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.

    • augmentedstartups/AS-One : Easy & Modular Computer Vision Detectors and Trackers - Run YOLO-NAS,v8,v7,v6,v5,R,X in under 20 lines of code. www.augmentedstartups.com

    • Oneflow-Inc/one-yolov5 : 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》"

    • PaddlePaddle/PaddleYOLO : 🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOX, YOLOv5u, YOLOv7u, RTMDet and so on. 🚀🚀🚀

    • WangRongsheng/BestYOLO : 🌟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!

    • KangChou/Cver4s : Cver4s：Computer vision algorithm code base.

    • chaizwj/yolov8-tricks : 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。

• Learning Resources

  • zjhellofss/KuiperLLama : 《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。

  • zjhellofss/KuiperInfer : 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。

  • zjhellofss/kuiperdatawhale : 从零自制深度学习推理框架。

  • roboflow/notebooks : 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

  • yjh0410/PyTorch_YOLO_Tutorial : YOLO Tutorial.

  • HuKai97/yolov5-5.x-annotations : 一个基于yolov5-5.0的中文注释版本！

  • crkk-feng/yolov5-annotations : A Chinese annotated version of yolov5-5.0.

  • XiaoJiNu/yolov5-v6-chinese-comment : yolov5-v6版本注释。

  • 1131624548/About-YOLOv5-7-0 : YOLOv5代码注释。

  • zyds/yolov5-code : 手把手带你实战 YOLOv5。

Other Versions of YOLO

• PyTorch Implementation

  • ultralytics/yolov3 : YOLOv3 in PyTorch > ONNX > CoreML > TFLite.

  • eriklindernoren/PyTorch-YOLOv3 : Minimal PyTorch implementation of YOLOv3.

  • Tianxiaomo/pytorch-YOLOv4 : PyTorch ,ONNX and TensorRT implementation of YOLOv4.

  • ayooshkathuria/pytorch-yolo-v3 : A PyTorch implementation of the YOLO v3 object detection algorithm.

  • WongKinYiu/PyTorch_YOLOv4 : PyTorch implementation of YOLOv4.

  • argusswift/YOLOv4-pytorch : This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO.

  • longcw/yolo2-pytorch : YOLOv2 in PyTorch.

  • bubbliiiing/yolov5-v6.1-pytorch : 这是一个yolov5-v6.1-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolov5-pytorch : 这是一个YoloV5-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolov4-pytorch : 这是一个YoloV4-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolov4-tiny-pytorch : 这是一个YoloV4-tiny-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolov3-pytorch : 这是一个yolo3-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolox-pytorch : 这是一个yolox-pytorch的源码，可以用于训练自己的模型。

  • bubbliiiing/yolov7-pytorch : 这是一个yolov7的库，可以用于训练自己的数据集。

  • bubbliiiing/yolov8-pytorch : 这是一个yolov8-pytorch的仓库，可以用于训练自己的数据集。

  • BobLiu20/YOLOv3_PyTorch : Full implementation of YOLOv3 in PyTorch.

  • ruiminshen/yolo2-pytorch : PyTorch implementation of the YOLO (You Only Look Once) v2.

  • DeNA/PyTorch_YOLOv3 : Implementation of YOLOv3 in PyTorch.

  • abeardear/pytorch-YOLO-v1 : an experiment for yolo-v1, including training and testing.

  • wuzhihao7788/yolodet-pytorch : reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5，YOLOv3, etc.

  • uvipen/Yolo-v2-pytorch : YOLO for object detection tasks.

  • Peterisfar/YOLOV3 : yolov3 by pytorch.

  • misads/easy_detection : 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。

  • miemiedetection : Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、SOLOv2 an so on.

  • pjh5672/YOLOv1 : YOLOv1 implementation using PyTorch.

  • pjh5672/YOLOv2 : YOLOv2 implementation using PyTorch.

  • pjh5672/YOLOv3 : YOLOv3 implementation using PyTorch.

  • Iywie/pl_YOLO : YOLOv7, YOLOX and YOLOv5 are working right now.

  • DavidLandup0/deepvision : 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.

  • theos-ai/easy-yolov7 : This a clean and easy-to-use implementation of YOLOv7 in PyTorch, made with ❤️ by Theos AI.

• C Implementation

  • ggml : Tensor library for machine learning. Written in C.

  • rockcarry/ffcnn : ffcnn is a cnn neural network inference framework, written in 600 lines C language.

  • ar7775/Object-Detection-System-Yolo : Object Detection System.

  • lstuma/YOLO_utils : A few utilities for the YOLO project implemented in C for extra speed.

  • RajneeshKumar12/yolo-detection-app : Yolo app for object detection.

  • Deyht/CIANNA : CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists.

• CPP Implementation

  • walktree/libtorch-yolov3 : A Libtorch implementation of the YOLO v3 object detection algorithm, written with pure C++.

  • yasenh/libtorch-yolov5 : A LibTorch inference implementation of the yolov5.

  • Nebula4869/YOLOv5-LibTorch : Real time object detection with deployment of YOLOv5 through LibTorch C++ API.

  • ncdhz/YoloV5-LibTorch : 一个 C++ 版本的 YoloV5 封装库.

  • Rane2021/yolov5_train_cpp_inference : yolov5训练和c++推理代码，效果出色。

  • stephanecharette/DarkHelp : The DarkHelp C++ API is a wrapper to make it easier to use the Darknet neural network framework within a C++ application.

  • UNeedCryDear/yolov5-opencv-dnn-cpp : 使用opencv模块部署yolov5-6.0版本。

  • UNeedCryDear/yolov5-seg-opencv-onnxruntime-cpp : yolov5 segmentation with onnxruntime and opencv.

  • hpc203/yolov5-dnn-cpp-python : 用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序。

  • hpc203/yolox-opencv-dnn : 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。

  • hpc203/yolov7-opencv-onnxrun-cpp-py : 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。

  • doleron/yolov5-opencv-cpp-python : Example of using ultralytics YOLO V5 with OpenCV 4.5.4, C++ and Python.

  • UNeedCryDear/yolov8-opencv-onnxruntime-cpp : detection and instance segmentation of yolov8,use onnxruntime and opencv.

• ROS Implementation

  • mgonzs13/yolov8_ros : Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11 for ROS 2.

  • leggedrobotics/darknet_ros : Real-Time Object Detection for ROS.

  • engcang/ros-yolo-sort : YOLO and SORT, and ROS versions of them.

  • chrisgundling/YoloLight : Tiny-YOLO-v2 ROS Node for Traffic Light Detection.

  • Ar-Ray-code/YOLOX-ROS : YOLOX + ROS2 object detection package.

  • Ar-Ray-code/YOLOv5-ROS : YOLOv5 + ROS2 object detection package.

  • Tossy0423/yolov4-for-darknet_ros : This is the environment in which YOLO V4 is ported to darknet_ros.

  • qianmin/yolov5_ROS : run YOLOv5 in ROS，ROS使用YOLOv5。

  • ailllist/yolov5_ROS : yolov5 for ros, not webcam.

  • Shua-Kang/ros_pytorch_yolov5 : A ROS wrapper for yolov5. (master branch is v5.0 of yolov5; for v6.1, see branch v6.1).

  • ziyan0302/Yolov5_DeepSort_Pytorch_ros : Connect Yolov5 detection module and DeepSort tracking module via ROS.

  • U07157135/ROS2-with-YOLOv5 : 在無人機上以ROS2技術實現YOLOv5物件偵測。

  • lukazso/yolov6-ros : ROS package for YOLOv6.

  • qq44642754a/Yolov5_ros : Real-time object detection with ROS, based on YOLOv5 and PyTorch (基于 YOLOv5的ROS实时对象检测).

  • lukazso/yolov7-ros : ROS package for official YOLOv7.

  • phuoc101/yolov7_ros : ROS package for official YOLOv7.

  • ConfusionTechnologies/ros-yolov5-node : For ROS2, uses ONNX GPU Runtime to inference YOLOv5.

  • Ar-Ray-code/darknet_ros_fp16 : darknet + ROS2 Humble + OpenCV4 + CUDA 11（cuDNN, Jetson Orin）.

  • wk123467/yolov5s_trt_ros : 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。

  • PardisTaghavi/yolov7_strongsort_ros : Integration of "Yolov7 StrongSort" with ROS for real time object tracking.

  • af-doom/yolov8_ros_tensorrt- : This is a YOLOv8 project based on ROS implementation, where YOLOv8 uses Tensorrt acceleration.

  • KoKoMier/ros_darknet_yolov4 : 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。

  • YellowAndGreen/Yolov5-OpenCV-Cpp-Python-ROS : Inference with YOLOv5, OpenCV 4.5.4 DNN, C++, ROS and Python.

  • mgonzs13/yolov8_ros : ROS 2 wrap for Ultralytics YOLOv8 to perform object detection.

  • fishros/yolov5_ros2 : 基于YoloV5的ROS2功能包，可以快速完成物体识别与位姿发布。

  • fateshelled/EdgeYOLO-ROS : EdgeYOLO + ROS2 object detection package.

  • vivaldini/yolov6-uav : This repository contains a ROS noetic package for YOLOv6 to recognize objects from UAV and provide their positions.

  • Alpaca-zip/ultralytics_ros : ROS/ROS2 package for Ultralytics YOLOv8 real-time object detection.

• Mojo Implementation

  • taalhaataahir0102/Mojo-Yolo : Mojo-Yolo.

• Rust Implementation

  • Candle : Minimalist ML framework for Rust.

  • Tokenizers : 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production. huggingface.co/docs/tokenizers

  • Safetensors : Simple, safe way to store and distribute tensors. huggingface.co/docs/safetensors

  • Burn : Burn - A Flexible and Comprehensive Deep Learning Framework in Rust. burn-rs.github.io/

  • TensorFlow Rust : Rust language bindings for TensorFlow.

  • tch-rs : Rust bindings for the C++ api of PyTorch.

  • dfdx : Deep learning in Rust, with shape checked tensors and neural networks.

  • tract : Sonos' Neural Network inference engine. Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

  • ort : A Rust wrapper for ONNX Runtime. docs.rs/ort

  • usls : A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.

  • ptaxom/pnn : pnn is 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.

  • bencevans/rust-opencv-yolov5 : YOLOv5 Inference with ONNX & OpenCV in Rust.

  • masc-it/yolov5-api-rust : Rust API to run predictions with YoloV5 models.

  • AndreyGermanov/yolov8_onnx_rust : YOLOv8 inference using Rust.

  • igor-yusupov/rusty-yolo : rusty-yolo.

  • gsuyemoto/yolo-rust : Run YOLO computer vision model using Rust and OpenCV and/or Torch.

  • alianse777/darknet-rust : A Rust wrapper for Darknet, an open source neural network framework written in C and CUDA. pjreddie.com/darknet/

  • 12101111/yolo-rs : Yolov3 & Yolov4 with TVM and rust.

  • TKGgunter/yolov4_tiny_rs : A rust implementation of yolov4_tiny algorithm.

  • flixstn/You-Only-Look-Once : A Rust implementation of Yolo for object detection and tracking.

  • lenna-project/yolo-plugin : Yolo Object Detection Plugin for Lenna.

  • laclouis5/globox-rs : Object detection toolbox for parsing, converting and evaluating bounding box annotations.

  • metobom/tchrs-opencv-webcam-inference : This example shows steps for running a Python trained model on webcam feed with opencv and tch-rs. Model will run on GPU.

  • Go Implementation

    • LdDl/go-darknet : go-darknet: Go bindings for Darknet (Yolo V4, Yolo V7-tiny, Yolo V3).

    • adalkiran/distributed-inference : 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.

    • wimspaargaren/yolov3 : Go implementation of the yolo v3 object detection system.

    • wimspaargaren/yolov5 : Go implementation of the yolo v5 object detection system.

    • genert/real_time_object_detection_go : Real Time Object Detection with OpenCV, Go, and Yolo v4.

  • CSharp Implementation

    • ML.NET : ML.NET is an open source and cross-platform machine learning framework for .NET.

    • TorchSharp : A .NET library that provides access to the library that powers PyTorch.

    • TensorFlow.NET : .NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.

    • DlibDotNet : Dlib .NET wrapper written in C++ and C# for Windows, MacOS, Linux and iOS.

    • DiffSharp : DiffSharp: Differentiable Functional Programming.

    • dme-compunet/YOLOv8 : Use YOLOv8 in real-time, for object detection, instance segmentation, pose estimation and image classification, via ONNX Runtime. www.nuget.org/packages/YoloV8

    • techwingslab/yolov5-net : YOLOv5 object detection with C#, ML.NET, ONNX.

    • sstainba/Yolov8.Net : A .net 6 implementation to use Yolov5 and Yolov8 models via the ONNX Runtime.

    • Alturos.Yolo : C# Yolo Darknet Wrapper (real-time object detection).

    • ivilson/Yolov7net : Yolov7 Detector for .Net 6.

    • sangyuxiaowu/ml_yolov7 : ML.NET Yolov7. "微信公众号「桑榆肖物」《YOLOv7 在 ML.NET 中使用 ONNX 检测对象》"

    • keijiro/TinyYOLOv2Barracuda : Tiny YOLOv2 on Unity Barracuda.

    • derenlei/Unity_Detection2AR : Localize 2D image object detection in 3D Scene with Yolo in Unity Barracuda and ARFoundation.

    • died/YOLO3-With-OpenCvSharp4 : Demo of implement YOLO v3 with OpenCvSharp v4 on C#.

    • mbaske/yolo-unity : YOLO In-Game Object Detection for Unity (Windows).

    • BobLd/YOLOv4MLNet : Use the YOLO v4 and v5 (ONNX) models for object detection in C# using ML.Net.

    • keijiro/YoloV4TinyBarracuda : YoloV4TinyBarracuda is an implementation of the YOLOv4-tiny object detection model on the Unity Barracuda neural network inference library.

    • zhang8043/YoloWrapper : C#封装YOLOv4算法进行目标检测。

    • maalik0786/FastYolo : Fast Yolo for fast initializing, object detection and tracking.

    • Uehwan/CSharp-Yolo-Video : C# Yolo for Video.

    • HTTP123-A/HumanDetection_Yolov5NET : YOLOv5 object detection with ML.NET, ONNX.

    • Celine-Hsieh/Hand_Gesture_Training--yolov4 : Recognize the gestures' features using the YOLOv4 algorithm.

    • lin-tea/YOLOv5DetectionWithCSharp : YOLOv5s inference In C# and Training In Python.

    • MirCore/Unity-Object-Detection-and-Localization-with-VR : Detect and localize objects from the front-facing camera image of a VR Headset in a 3D Scene in Unity using Yolo and Barracuda.

    • CarlAreDHopen-eaton/YoloObjectDetection : Yolo Object Detection Application for RTSP streams.

    • TimothyMeadows/Yolo6.NetCore : You Only Look Once (v6) for .NET Core LTS.

    • mwetzko/EasyYoloDarknet : EasyYoloDarknet.

    • mwetzko/EasyYoloDarknet : Windows optimized Yolo / Darknet Compile, Train and Detect.

    • cj-mills/Unity-OpenVINO-YOLOX : This tutorial series covers how to perform object detection in the Unity game engine with the OpenVINO™ Toolkit.

    • natml-hub/YOLOX : High performance object detector based on YOLO series.

    • thisistherealdiana/YOLO_project : YOLO project made by Diana Kereselidze.

    • oujunke/Yolo5Net : Yolo5实现于TensorFlow.Net.

    • wojciechp6/YOLO-UnityBarracuda : Object detection app build on Unity Barracuda and YOLOv2 Tiny.

    • RaminAbbaszadi/YoloWrapper-WPF : WPF (C#) Yolo Darknet Wrapper.

    • fengyhack/YoloWpf : GUI demo for Object Detection with YOLO and OpenCVSharp.

    • hanzhuang111/Yolov5Wpf : 使用ML.NET部署YOLOV5 的ONNX模型。

    • MaikoKingma/yolo-winforms-test : 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.

    • SeanAnd/WebcamObjectDetection : YOLO object detection using webcam in winforms.

    • Devmawi/BlazorObjectDetection-Sample : Simple project for demonstrating how to embed a continuously object detection with Yolo on a video in a hybrid Blazor app (WebView2).

    • Soju06/yolov5-annotation-viewer : yolov5 annotation viewer.

    • developer-ken/YoloPredictorMLDotNet : YoloPredictorMLDotNet.

    • LionelC-Kyo/CSharp_YoloV5_Torch : Run Yolo V5 in C# By Torch.

    • wanglvhang/OnnxYoloDemo : 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.

    • BobLd/YOLOv3MLNet : Use the YOLO v3 (ONNX) model for object detection in C# using ML.Net.

    • zgabi/Yolo.Net : zgabi/Yolo.Net

    • aliardan/RoadMarkingDetection : Road markings detection using yolov5 model based on ONNX.

    • TimothyMeadows/Yolo5.NetCore : You Only Look Once (v5) for .NET Core LTS.

    • AD-HO/YOLOv5-ML.NET : Inferencing Yolov5 ONNX model using ML.NET and ONNX Runtime.

    • ToxicSkill/YOLOV7-Webcam-inference : Simple WPF program for webcam inference with yoloV7 models.

    • aliardan/RoadMarkingDetection : Road markings detection using yolov5 model based on ONNX.

    • rabbitsun2/csharp_and_microsoft_ml_and_yolo_v5_sample : C#, Microsoft ML, Yolo v5, Microsoft ML.DNN, OpenCVSharp4 연계 프로젝트.

    • hsysfan/YOLOv5-Seg-OnnxRuntime : YOLOv5 Segmenation Implementation in C# and OnnxRuntime.

    • dme-compunet/YOLOv8 : Use YOLOv8 in real-time, for object detection, instance segmentation, pose estimation and image classification, via ONNX Runtime.

  • Tensorflow and Keras Implementation

    • YunYang1994/tensorflow-yolov3 : 🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement".

    • zzh8829/yolov3-tf2 : YoloV3 Implemented in Tensorflow 2.0.

    • hunglc007/tensorflow-yolov4-tflite : YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite.

    • gliese581gg/YOLO_tensorflow : tensorflow implementation of 'YOLO : Real-Time Object Detection'.

    • llSourcell/YOLO_Object_Detection : This is the code for "YOLO Object Detection" by Siraj Raval on Youtube.

    • wizyoung/YOLOv3_TensorFlow : Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.

    • theAIGuysCode/yolov4-deepsort : Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

    • mystic123/tensorflow-yolo-v3 : Implementation of YOLO v3 object detector in Tensorflow (TF-Slim).

    • hizhangp/yolo_tensorflow : Tensorflow implementation of YOLO, including training and test phase.

    • nilboy/tensorflow-yolo : tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test).

    • qqwweee/keras-yolo3 : A Keras implementation of YOLOv3 (Tensorflow backend).

    • allanzelener/YAD2K : YAD2K: Yet Another Darknet 2 Keras.

    • experiencor/keras-yolo2 : YOLOv2 in Keras and Applications.

    • experiencor/keras-yolo3 : Training and Detecting Objects with YOLO3.

    • SpikeKing/keras-yolo3-detection : YOLO v3 物体检测算法。

    • xiaochus/YOLOv3 : Keras implementation of yolo v3 object detection.

    • bubbliiiing/yolo3-keras : 这是一个yolo3-keras的源码，可以用于训练自己的模型。

    • bubbliiiing/yolov4-keras : 这是一个YoloV4-keras的源码，可以用于训练自己的模型。

    • bubbliiiing/yolov4-tf2 : 这是一个yolo4-tf2（tensorflow2）的源码，可以用于训练自己的模型。

    • bubbliiiing/yolov4-tiny-tf2 : 这是一个YoloV4-tiny-tf2的源码，可以用于训练自己的模型。

    • pythonlessons/TensorFlow-2.x-YOLOv3 : YOLOv3 implementation in TensorFlow 2.3.1.

    • miemie2013/Keras-YOLOv4 : PPYOLO AND YOLOv4.

    • Ma-Dan/keras-yolo4 : A Keras implementation of YOLOv4 (Tensorflow backend).

    • miranthajayatilake/YOLOw-Keras : YOLOv2 Object Detection w/ Keras (in just 20 lines of code).

    • maiminh1996/YOLOv3-tensorflow : Re-implement YOLOv3 with TensorFlow.

    • Stick-To/Object-Detection-Tensorflow : Object Detection API Tensorflow.

    • avBuffer/Yolov5_tf : Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow.

    • ruiminshen/yolo-tf : TensorFlow implementation of the YOLO (You Only Look Once).

    • xiao9616/yolo4_tensorflow2 : yolo 4th edition implemented by tensorflow2.0.

    • sicara/tf2-yolov4 : A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection.

    • LongxingTan/Yolov5 : Efficient implementation of YOLOV5 in TensorFlow2.

    • geekjr/quickai : QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

    • CV_Lab/yolov5_rt_tfjs : 🚀 基于TensorFlow.js的YOLOv5实时目标检测项目。

    • Burf/TFDetection : A Detection Toolbox for Tensorflow2.

    • taipingeric/yolo-v4-tf.keras : A simple tf.keras implementation of YOLO v4.

    • david8862/keras-YOLOv3-model-set : end-to-end YOLOv4/v3/v2 object detection pipeline, implemented on tf.keras with different technologies.

  • PaddlePaddle Implementation

    • PaddlePaddle/PaddleDetection : Object Detection toolkit based on PaddlePaddle. "PP-YOLO: An Effective and Efficient Implementation of Object Detector". (arXiv 2020)

    • nemonameless/PaddleDetection_YOLOv5 : YOLOv5 of PaddleDetection, Paddle implementation of YOLOv5.

    • nemonameless/PaddleDetection_YOLOX : Paddle YOLOX, 51.8% on COCO val by YOLOX-x, 44.6% on YOLOX-ConvNeXt-s.

    • nemonameless/PaddleDetection_YOLOset : Paddle YOLO set: YOLOv3, PPYOLO, PPYOLOE, YOLOX, YOLOv5, YOLOv7 and so on.

    • miemie2013/Paddle-YOLOv4 : Paddle-YOLOv4.

    • Sharpiless/PaddleDetection-Yolov5 : 基于Paddlepaddle复现yolov5，支持PaddleDetection接口。

    • Nioolek/PPYOLOE_pytorch : An unofficial implementation of Pytorch version PP-YOLOE,based on Megvii YOLOX training code.

  • Caffe Implementation

    • ChenYingpeng/caffe-yolov3 : A real-time object detection framework of Yolov3/v4 based on caffe.

    • ChenYingpeng/darknet2caffe : Convert darknet weights to caffemodel.

    • eric612/Caffe-YOLOv3-Windows : A windows caffe implementation of YOLO detection network.

    • Harick1/caffe-yolo : Caffe for YOLO.

    • choasup/caffe-yolo9000 : Caffe for YOLOv2 & YOLO9000.

    • gklz1982/caffe-yolov2 : caffe-yolov2.

  • MXNet Implementation

    • Gluon CV Toolkit : GluonCV provides implementations of the state-of-the-art (SOTA) deep learning models in computer vision.

    • zhreshold/mxnet-yolo : YOLO: You only look once real-time object detector.

  • Web Implementation

    • ModelDepot/tfjs-yolo-tiny : In-Browser Object Detection using Tiny YOLO on Tensorflow.js.

    • justadudewhohacks/tfjs-tiny-yolov2 : Tiny YOLO v2 object detection with tensorflow.js.

    • reu2018DL/YOLO-LITE : YOLO-LITE is a web implementation of YOLOv2-tiny.

    • mobimeo/node-yolo : Node bindings for YOLO/Darknet image recognition library.

    • Sharpiless/Yolov5-Flask-VUE : 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。

    • shaqian/tfjs-yolo : YOLO v3 and Tiny YOLO v1, v2, v3 with Tensorflow.js.

    • zqingr/tfjs-yolov3 : A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny.

    • bennetthardwick/darknet.js : A NodeJS wrapper of pjreddie's darknet / yolo.

    • nihui/ncnn-webassembly-yolov5 : Deploy YOLOv5 in your web browser with ncnn and webassembly.

    • muhk01/Yolov5-on-Flask : Running YOLOv5 through web browser using Flask microframework.

    • tcyfree/yolov5 : 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。

    • siffyy/YOLOv5-Web-App-for-Vehicle-Detection : Repo for Web Application for Vehicle detection from Satellite Imagery using YOLOv5 model.

    • Devmawi/BlazorObjectDetection-Sample : A sample for demonstrating online execution of an onnx model by a Blazor app.

    • Hyuto/yolov5-onnxruntime-web : YOLOv5 right in your browser with onnxruntime-web.

  • Others

    • jinfagang/yolov7_d2 : 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

    • yang-0201/YOLOv6_pro : Make it easier for yolov6 to change the network structure.

    • j-marple-dev/AYolov2 : 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.

    • fcakyon/yolov5-pip : Packaged version of ultralytics/yolov5.

    • kadirnar/yolov6-pip : Packaged version of yolov6 model.

    • kadirnar/yolov7-pip : Packaged version of yolov7 model.

    • kadirnar/torchyolo : PyTorch implementation of YOLOv5, YOLOv6, YOLOv7, YOLOX.

    • CvPytorch : CvPytorch is an open source COMPUTER VISION toolbox based on PyTorch.

    • Holocron : PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss).

    • DL-Practise/YoloAll : YoloAll is a collection of yolo all versions. you you use YoloAll to test yolov3/yolov5/yolox/yolo_fastest.

    • msnh2012/Msnhnet : (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

    • xinghanliuying/yolov5-trick : 基于yolov5的改进库。

    • BMW-InnovationLab/BMW-YOLOv4-Training-Automation : YOLOv4-v3 Training Automation API for Linux.

    • AntonMu/TrainYourOwnYOLO : Train a state-of-the-art yolov3 object detector from scratch!

    • madhawav/YOLO3-4-Py : A Python wrapper on Darknet. Compatible with YOLO V3.

    • theAIGuysCode/yolov4-custom-functions : A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.

    • tiquasar/FLAITER : Machine Learning and AI Mobile Application.

    • kadirnar/Minimal-Yolov6 : Minimal-Yolov6.

    • DataXujing/YOLOv6 : 🌀 🌀 手摸手 美团 YOLOv6模型训练和TensorRT端到端部署方案教程。

    • DataXujing/YOLOv7 : 🔥🔥🔥 Official YOLOv7训练自己的数据集并实现端到端的TensorRT模型加速推断。

    • DataXujing/YOLOv8 : 🔥 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。

    • DataXujing/YOLOv9 : 🔥 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。

    • Code-keys/yolov5-darknet : yolov5-darknet support yaml && cfg.

    • Code-keys/yolo-darknet : YOLO-family complemented by darknet. yolov5 yolov7 et al ...

    • pooya-mohammadi/deep_utils : A toolkit full of handy functions including most used models and utilities for deep-learning practitioners!

    • yl-jiang/YOLOSeries : YOLO Series.

    • yjh0410/FreeYOLO : FreeYOLO is inspired by many other excellent works, such as YOLOv7 and YOLOX.

    • open-yolo/yolov7 : Improved and packaged version of WongKinYiu/yolov7.

    • iloveai8086/YOLOC : 🚀YOLOC is Combining different modules to build an different Object detection model.

    • miemie2013/miemiedetection : Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、SOLOv2 an so on.

    • RyanCCC/YOLOSeries : YOLO算法的实现。

    • HuKai97/YOLOX-Annotations : 一个YOLOX的中文注释版本，供大家参考学习！

    • isLinXu/YOLOv8_Efficient : 🚀Simple and efficient use for Ultralytics yolov8🚀

    • z1069614715/objectdetection_script : 一些关于目标检测的脚本的改进思路代码。

Lighter and Deployment Frameworks

• High-performance Inference Engine

  高性能推理引擎

  • ONNX

    • ONNX Runtime : ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator. onnxruntime.ai

    • ONNX : Open Neural Network Exchange. Open standard for machine learning interoperability. onnx.ai

    • ONNXMLTools : ONNXMLTools enables you to convert models from different machine learning toolkits into ONNX. onnx.ai

    • xboot/libonnx : A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

    • kraiskil/onnx2c : Open Neural Network Exchange to C compiler. Onnx2c is a ONNX to C compiler. It will read an ONNX file, and generate C code to be included in your project. Onnx2c's target is "Tiny ML", meaning running the inference on microcontrollers.

    • tract : Sonos' Neural Network inference engine. Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

    • ort : A Rust wrapper for ONNX Runtime. docs.rs/ort

    • onnxruntime-rs : This is an attempt at a Rust wrapper for Microsoft's ONNX Runtime (version 1.8).

    • Wonnx : Wonnx is a GPU-accelerated ONNX inference run-time written 100% in Rust, ready for the web.

    • altius : Small ONNX inference runtime written in Rust.

    • Hyuto/yolo-nas-onnx : Inference YOLO-NAS ONNX model. hyuto.github.io/yolo-nas-onnx/

    • DanielSarmiento04/yolov10cpp : Implementation of yolo v10 in c++ std 17 over opencv and onnxruntime.

  • TensorRT

    • TensorRT : NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT. developer.nvidia.com/tensorrt

    • TensorRT-LLM : TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines. nvidia.github.io/TensorRT-LLM

    • NVIDIA/TensorRT-Model-Optimizer : TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs. nvidia.github.io/TensorRT-Model-Optimizer

    • kalfazed/tensorrt_starter : This repository give a guidline to learn CUDA and TensorRT from the beginning.

    • wang-xinyu/tensorrtx : TensorRTx aims to implement popular deep learning networks with tensorrt network definition APIs.

    • laugh12321/TensorRT-YOLO : 🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️. 🚀 TensorRT-YOLO is an easy-to-use, extremely efficient inference deployment tool for the YOLO series designed specifically for NVIDIA devices. The project not only integrates TensorRT plugins to enhance post-processing but also utilizes CUDA kernels and CUDA graphs to accelerate inference. 🚀 TensorRT-YOLO 是一款专为 NVIDIA 设备设计的易用灵活、极致高效的YOLO系列推理部署工具。项目不仅集成了 TensorRT 插件以增强后处理效果，还使用了 CUDA 核函数以及 CUDA 图来加速推理。

    • olibartfast/object-detection-inference : C++ object detection inference from video or image input source. Inference for object detection from a video or image input source, with support for multiple switchable frameworks to manage the inference process, and optional GStreamer integration for video capture.

    • shouxieai/tensorRT_Pro : C++ library based on tensorrt integration.

    • shouxieai/infer : A new tensorrt integrate. Easy to integrate many tasks.

    • Melody-Zhou/tensorRT_Pro-YOLOv8 : This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8. 前已支持 YOLOv8、YOLOv8-Cls、YOLOv8-Seg、YOLOv8-OBB、YOLOv8-Pose、RT-DETR、ByteTrack、YOLOv9、YOLOv10、RTMO、PP-OCRv4、LaneATT 高性能推理！！！🚀🚀🚀

    • FeiYull/TensorRT-Alpha : 🔥🔥🔥TensorRT for YOLOv8、YOLOv8-Pose、YOLOv8-Seg、YOLOv8-Cls、YOLOv7、YOLOv6、YOLOv5、YOLONAS......🚀🚀🚀CUDA IS ALL YOU NEED.🍎🍎🍎

    • zhiqwang/yolort : yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn. zhiqwang.com/yolort

    • 1461521844lijin/trt_yolo_video_pipeline : TensorRT+YOLO系列的 多路 多卡 多实例 并行视频分析处理案例。

    • l-sf/Linfer : 基于TensorRT的C++高性能推理库，Yolov10, YoloPv2，Yolov5/7/X/8，RT-DETR，单目标跟踪OSTrack、LightTrack。

    • taifyang/yolo-inference : C++ and Python implementations of YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOv11 inference.

    • triple-Mu/YOLOv8-TensorRT : YOLOv8 using TensorRT accelerate !

    • emptysoal/TensorRT-YOLOv8-ByteTrack : An object tracking project with YOLOv8 and ByteTrack, speed up by C++ and TensorRT.

    • Linaom1214/TensorRT-For-YOLO-Series : tensorrt for yolo series (YOLOv10,YOLOv9,YOLOv8,YOLOv7,YOLOv6,YOLOX,YOLOv5), nms plugin support.

    • spacewalk01/yolov11-tensorrt : C++ implementation of YOLOv11 using TensorRT API.

    • cyrusbehr/YOLOv8-TensorRT-CPP : YOLOv8 TensorRT C++ Implementation. A C++ Implementation of YoloV8 using TensorRT Supports object detection, semantic segmentation, and body pose estimation.

    • emptysoal/TensorRT-YOLOv8 : Based on tensorrt v8.0+, deploy detect, pose, segment, tracking of YOLOv8 with C++ and python api.

    • hamdiboukamcha/yolov10-tensorrt : YOLOv10 C++ TensorRT : Real-Time End-to-End Object Detection.

    • VIDIA-AI-IOT/torch2trt : An easy to use PyTorch to TensorRT converter.

    • DefTruth/lite.ai.toolkit : 🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv5. MNN, NCNN, TNN, ONNXRuntime. “🛠Lite.Ai.ToolKit: 一个轻量级的C++ AI模型工具箱，用户友好（还行吧），开箱即用。已经包括 100+ 流行的开源模型。这是一个根据个人兴趣整理的C++工具箱，, 涵盖目标检测、人脸检测、人脸识别、语义分割、抠图等领域。”

    • PaddlePaddle/FastDeploy : ⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

    • enazoe/yolo-tensorrt : TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

    • guojianyang/cv-detect-robot : 🔥🔥🔥🔥🔥🔥Docker NVIDIA Docker2 YOLOV5 YOLOX YOLO Deepsort TensorRT ROS Deepstream Jetson Nano TX2 NX for High-performance deployment(高性能部署)。

    • BlueMirrors/Yolov5-TensorRT : Yolov5 TensorRT Implementations.

    • lewes6369/TensorRT-Yolov3 : TensorRT for Yolov3.

    • CaoWGG/TensorRT-YOLOv4 :tensorrt5, yolov4, yolov3,yolov3-tniy,yolov3-tniy-prn.

    • isarsoft/yolov4-triton-tensorrt : YOLOv4 on Triton Inference Server with TensorRT.

    • TrojanXu/yolov5-tensorrt : A tensorrt implementation of yolov5.

    • tjuskyzhang/Scaled-YOLOv4-TensorRT : Implement yolov4-tiny-tensorrt, yolov4-csp-tensorrt, yolov4-large-tensorrt(p5, p6, p7) layer by layer using TensorRT API.

    • Syencil/tensorRT : TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据。

    • SeanAvery/yolov5-tensorrt : YOLOv5 in TensorRT.

    • Monday-Leo/YOLOv7_Tensorrt : A simple implementation of Tensorrt YOLOv7.

    • ibaiGorordo/ONNX-YOLOv6-Object-Detection : Python scripts performing object detection using the YOLOv6 model in ONNX.

    • ibaiGorordo/ONNX-YOLOv7-Object-Detection : Python scripts performing object detection using the YOLOv7 model in ONNX.

    • triple-Mu/yolov7 : End2end TensorRT YOLOv7.

    • hewen0901/yolov7_trt : yolov7目标检测算法的c++ tensorrt部署代码。

    • tsutof/tiny_yolov2_onnx_cam : Tiny YOLO v2 Inference Application with NVIDIA TensorRT.

    • Monday-Leo/Yolov5_Tensorrt_Win10 : A simple implementation of tensorrt yolov5 python/c++🔥

    • Wulingtian/yolov5_tensorrt_int8 : TensorRT int8 量化部署 yolov5s 模型，实测3.3ms一帧！

    • Wulingtian/yolov5_tensorrt_int8_tools : tensorrt int8 量化yolov5 onnx模型。

    • MadaoFY/yolov5_TensorRT_inference : 记录yolov5的TensorRT量化及推理代码，经实测可运行于Jetson平台。

    • ibaiGorordo/ONNX-YOLOv8-Object-Detection : Python scripts performing object detection using the YOLOv8 model in ONNX.

    • we0091234/yolov8-tensorrt : yolov8 tensorrt 加速.

    • FeiYull/yolov8-tensorrt : YOLOv8的TensorRT+CUDA加速部署，代码可在Win、Linux下运行。

    • cvdong/YOLO_TRT_SIM : 🐇 一套代码同时支持YOLO X, V5, V6, V7, V8 TRT推理 ™️ 🔝 ,前后处理均由CUDA核函数实现 CPP/CUDA🚀

    • cvdong/YOLO_TRT_PY : 🐰 一套代码同时支持YOLOV5, V6, V7, V8 TRT推理 ™️ PYTHON ✈️

    • Psynosaur/Jetson-SecVision : Person detection for Hikvision DVR with AlarmIO ports, uses TensorRT and yolov4.

    • tatsuya-fukuoka/yolov7-onnx-infer : Inference with yolov7's onnx model.

    • MadaoFY/yolov5_TensorRT_inference : 记录yolov5的TensorRT量化及推理代码，经实测可运行于Jetson平台。

    • ervgan/yolov5_tensorrt_inference : TensorRT cpp inference for Yolov5 model. Supports yolov5 v1.0, v2.0, v3.0, v3.1, v4.0, v5.0, v6.0, v6.2, v7.0.

    • AlbinZhu/easy-trt : TensorRT for YOLOv10 with CUDA.

    • PrinceP/tensorrt-cpp-for-onnx : Tensorrt codebase to inference in c++ for all major neural arch using onnx.

    • hamdiboukamcha/Yolo-V10-cpp-TensorRT : The YOLOv10 C++ TensorRT Project in C++ and optimized using NVIDIA TensorRT.

    • DataXujing/YOLOv12-TensorRT : YOLOv12 TensorRT 端到端模型加速推理和INT8量化实现。

  • DeepStream

    • NVIDIA-AI-IOT/deepstream_reference_apps : Reference Apps using DeepStream 6.1.

    • NVIDIA-AI-IOT/deepstream_python_apps : DeepStream SDK Python bindings and sample applications.

    • NVIDIA-AI-IOT/deepstream_python_apps : This repository provides YOLOV5 GPU optimization sample.

    • marcoslucianops/DeepStream-Yolo : NVIDIA DeepStream SDK 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO models.

    • DanaHan/Yolov5-in-Deepstream-5.0 : Describe how to use yolov5 in Deepstream 5.0.

    • ozinc/Deepstream6_YoloV5_Kafka : This repository gives a detailed explanation on making custom trained deepstream-Yolo models predict and send message over kafka.

    • kn1ghtf1re/yolov8-deepstream-6-1 : YOLOv8 by Ultralytics in DeepStream 6.1.

    • bharath5673/Deepstream : yolov2 ,yolov5 ,yolov6 ,yolov7 ,yolov7,yolovR ,yolovX on deepstream.

    • Savant : Python Computer Vision & Video Analytics Framework With Batteries Included. savant-ai.io

    • Savant : Plug-and-Play Custom Parsers for AI Models in NVIDIA DeepStream SDK. Supported YOLOv11 model.

  • OpenVINO

    • OpenVINO : This open source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics.

    • PINTO0309/OpenVINO-YoloV3 : YoloV3/tiny-YoloV3 + RaspberryPi3/Ubuntu LaptopPC + NCS/NCS2 + USB Camera + Python + OpenVINO.

    • TNTWEN/OpenVINO-YOLOV4 : This is implementation of YOLOv4,YOLOv4-relu,YOLOv4-tiny,YOLOv4-tiny-3l,Scaled-YOLOv4 and INT8 Quantization in OpenVINO2021.3.

    • fb029ed/yolov5_cpp_openvino : 用c++实现了yolov5使用openvino的部署。

    • dlod-openvino/yolov5_infer : Do the YOLOv5 model inference by OpenCV/OpenVINO based on onnx model format.

    • snail0614/yolov5.6_openvino_cpp : yolov5.6.1 OpenVINO的C++实现。

    • shungfu/openvino_yolov5v7 : YOLOv5 YOLOv7 INT8 quantization using OpenVINO.

    • dacquaviva/yolov5-openvino-cpp-python : Example of using ultralytics YOLOv5 with Openvino in C++ and Python.

    • rlggyp/YOLOv10-OpenVINO-CPP-Inference : YOLOv10 C++ implementation using OpenVINO for efficient and accurate real-time object detection.

  • NCNN

    • NCNN : ncnn is a high-performance neural network inference framework optimized for the mobile platform.

    • Baiyuetribe/ncnn-models : awesome AI models with NCNN, and how they were converted ✨✨✨

    • Qengineering/YoloV10-ncnn-Raspberry-Pi-4 : YoloV10 for a bare Raspberry Pi 4 or 5.

    • cmdbug/YOLOv5_NCNN : 🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。

    • natanielruiz/android-yolo : Real-time object detection on Android using the YOLO network with TensorFlow.

    • nihui/ncnn-android-yolov5 : The YOLOv5 object detection android example.

    • szaza/android-yolo-v2 : Android YOLO real time object detection sample application with Tensorflow mobile.

    • FeiGeChuanShu/ncnn-android-yolox : Real time yolox Android demo by ncnn.

    • xiangweizeng/darknet2ncnn : Darknet2ncnn converts the darknet model to the ncnn model.

    • sunnyden/YOLOV5_NCNN_Android : YOLOv5 C++ Implementation on Android using NCNN framework.

    • duangenquan/YoloV2NCS : This project shows how to run tiny yolo v2 with movidius stick.

    • lp6m/yolov5s_android : Run yolov5s on Android device!

    • KoheiKanagu/ncnn_yolox_flutter : This is a plugin to run YOLOX on ncnn.

    • cyrillkuettel/ncnn-android-yolov5 : This is a sample ncnn android project, it depends on ncnn library and opencv.

    • DataXujing/ncnn_android_yolov6 : 手摸手实现基于QT和NCNN的安卓手机YOLOv6模型的部署！

    • Qengineering/YoloV3-ncnn-Raspberry-Pi-4 : YoloV3 Raspberry Pi 4.

    • Qengineering/YoloV4-ncnn-Raspberry-Pi-4 : YoloV4 on a bare Raspberry Pi 4 with ncnn framework.

    • Qengineering/YoloV5-ncnn-Raspberry-Pi-4 : YoloV5 for a bare Raspberry Pi 4.

    • Qengineering/YoloV6-ncnn-Raspberry-Pi-4 : YoloV6 for a bare Raspberry Pi using ncnn.

    • Qengineering/YoloV7-ncnn-Raspberry-Pi-4 : YoloV7 for a bare Raspberry Pi using ncnn.

    • Qengineering/YoloV8-ncnn-Raspberry-Pi-4 : YoloV8 for a bare Raspberry Pi 4.

    • FeiGeChuanShu/ncnn-android-yolov8 : Real time yolov8 Android demo by ncnn.

    • FLamefiREz/yolov10-android-ncnn : yolov10-android-ncnn.

  • MNN

    • MNN : MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. (MLSys 2020)

    • apxlwl/MNN-yolov3 : MNN demo of Strongeryolo, including channel pruning, android support...

  • Other Engine

    • TVM : Open deep learning compiler stack for cpu, gpu and specialized accelerators.

    • ceccocats/tkDNN : Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms. "A Systematic Assessment of Embedded Neural Networks for Object Detection". (IEEE ETFA 2020)

    • Tengine : Tengine is a lite, high performance, modular inference engine for embedded device.

    • Paddle Lite : Multi-platform high performance deep learning inference engine (飞桨多端多平台高性能深度学习推理引擎）。

    • DeployAI/nndeploy : nndeploy is a cross-platform, high-performing, and straightforward AI model deployment framework. We strive to deliver a consistent and user-friendly experience across various inference framework in complex deployment environments and focus on performance. nndeploy一款跨平台、高性能、简单易用的模型端到端部署框架。我们致力于屏蔽不同推理框架的差异，提供一致且用户友好的编程体验，同时专注于部署全流程的性能。

    • yhwang-hub/dl_model_infer : his is a c++ version of the AI reasoning library. Currently, it only supports the reasoning of the tensorrt model. The follow-up plan supports the c++ reasoning of frameworks such as Openvino, NCNN, and MNN. There are two versions for pre- and post-processing, c++ version and cuda version. It is recommended to use the cuda version., This repository provides accelerated deployment cases of deep learning CV popular models, and cuda c supports dynamic-batch image process, infer, decode, NMS.

    • hollance/YOLO-CoreML-MPSNNGraph : Tiny YOLO for iOS implemented using CoreML but also using the new MPS graph API.

    • r4ghu/iOS-CoreML-Yolo : This is the implementation of Object Detection using Tiny YOLO v1 model on Apple's CoreML Framework.

    • airockchip/rknn_model_zoo : Rockchip Neural Network(RKNN)是瑞芯微为了加速模型推理而基于自身NPU硬件架构定义的一套模型格式.使用该格式定义的模型在Rockchip NPU上可以获得远高于CPU/GPU的性能。

    • LynxiTechnology/Lynxi-model-zoo : Lynxi-model-zoo.

• NPU and FPGA Hardware Deployment

  NPU 和 FPGA 硬件部署

  • RK3588

    • Qengineering/YoloV8-NPU : YoloV8 for RK3566/68/88 NPU (Rock 5, Orange Pi 5, Radxa Zero 3).

    • aemior/yolov8n_rk3588 : This repository contains a demonstration of Yolv8n running on an RK3588 device.

    • cqu20160901/yolov8n_rknn_Cplusplus_dfl : yolov8 瑞芯微 rknn 板端 C++部署，使用平台 rk3588，全网最简单、运行最快的部署方式。

    • cqu20160901/yolov8seg_rknn_Cplusplus : yolov8seg 瑞芯微 rknn 板端 C++部署，使用平台 rk3588。

    • Ley-WL/ultralytics-rknn : 基于ultralytics-yolov8, 将其检测/分类/分割/姿态等任务移植到rk3588上。

    • 455670288/rknn-yolov8s-multi-thread-inference : yolov8s在rk3588的推理部署，并使用多线程池并行npu推理加速。

    • leafqycc/rknn-cpp-Multithreading : A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames). / 一个使用c++在rk3588/3588s上运行的yolov5s简单demo(142帧/s)。

    • leafqycc/rknn-multi-threaded : A simple demo of yolov5s running on rk3588/3588s using Python (about 72 frames). / 一个使用Python在rk3588/3588s上运行的yolov5s简单demo(大约72帧/s)。

    • wzxzhuxi/rknn-3588-npu-yolo-accelerate : rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.

    • kaylorchen/rk3588-yolo-demo : The project is a multi-threaded inference demo of Yolo running on the RK3588 platform, which has been adapted for reading video files and camera feeds. The demo uses the Yolov8n model for file inference, with a maximum inference frame rate of up to 100 frames per second.

    • MontaukLaw/yolov5_3588_multi_thread : 启动多线程, relu激活, 3588的yolo部署, 帧率150以上.

    • crab2rab/RKNN-YOLOV5-BatchInference-MultiThreading : RKNN-YOLOV5-BatchInference-MultiThreadingYOLOV5多张图片多线程C++推理。

    • Qengineering/YoloV10-NPU : YoloV10 NPU for the RK3566/68/88.

    • cqu20160901/yolov10_rknn_Cplusplus : yolov10 瑞芯微 rknn 板端 C++部署，使用平台 rk3588。

    • Zhou-sx/yolov5_Deepsort_rknn : Track vehicles and persons on rk3588 / rk3399pro.

    • Applied-Deep-Learning-Lab/Yolov5_RK3588 : Yolov5_RK3588.

    • cqu20160901/yolov10_onnx_rknn_horizon_tensorRT : yolov10 目标检测部署版本，便于移植不同平台（onnx、tensorRT、rknn、Horizon），全网部署最简单、运行速度最快的部署方式（全网首发）。

    • icetd/RkYoloRtspServer : simple yolov5 rtspserver for rk3588.

  • FPGA

    • Xilinx/Vitis-AI : Vitis AI offers a unified set of high-level C++/Python programming APIs to run AI applications across edge-to-cloud platforms, including DPU for Alveo, and DPU for Zynq Ultrascale+ MPSoC and Zynq-7000. It brings the benefits to easily port AI applications from cloud to edge and vice versa. 10 samples in VART Samples are available to help you get familiar with the unfied programming APIs. Vitis-AI-Library provides an easy-to-use and unified interface by encapsulating many efficient and high-quality neural networks.

    • tensil-ai/tensil : Open source machine learning accelerators. www.tensil.ai

    • 19801201/SpinalHDL_CNN_Accelerator : CNN accelerator implemented with Spinal HDL.

    • dhm2013724/yolov2_xilinx_fpga : YOLOv2 Accelerator in Xilinx's Zynq-7000 Soc(PYNQ-z2, Zedboard and ZCU102). (硕士论文 2019, 电子技术应用 2019, 计算机科学与探索 2019)

    • Yu-Zhewen/Tiny_YOLO_v3_ZYNQ : Implement Tiny YOLO v3 on ZYNQ. "A Parameterisable FPGA-Tailored Architecture for YOLOv3-Tiny". (ARC 2020)

    • HSqure/ultralytics-pt-yolov3-vitis-ai-edge : This demo is only used for inference testing of Vitis AI v1.4 and quantitative compilation of DPU. It is compatible with the training results of ultralytics/yolov3 v9.5.0 (it needs to use the model saving method of Pytorch V1.4).

    • mcedrdiego/Kria_yolov3_ppe : Kria KV260 Real-Time Personal Protective Equipment Detection. "Deep Learning for Site Safety: Real-Time Detection of Personal Protective Equipment". (Automation in Construction 2020)

    • xlsjdjdk/Ship-Detection-based-on-YOLOv3-and-KV260 : This is the entry project of the Xilinx Adaptive Computing Challenge 2021. It uses YOLOv3 for ship target detection in optical remote sensing images, and deploys DPU on the KV260 platform to achieve hardware acceleration.

    • Pomiculture/YOLOv4-Vitis-AI : Custom YOLOv4 for apple recognition (clean/damaged) on Alveo U280 accelerator card using Vitis AI framework.

    • mkshuvo2/ZCU104_YOLOv3_Post_Processing : Tensor outputs form Vitis AI Runner Class for YOLOv3.

    • puffdrum/v4tiny_pt_quant : quantization for yolo with xilinx/vitis-ai-pytorch.

    • chanshann/LITE_YOLOV3_TINY_VITISAI : LITE_YOLOV3_TINY_VITISAI.

    • LukiBa/zybo_yolo : YOLO example implementation using Intuitus CNN accelerator on ZYBO ZYNQ-7000 FPGA board.

    • matsuda-slab/YOLO_ZYNQ_MASTER : Implementation of YOLOv3-tiny on FPGA.

    • FerberZhang/Yolov2-FPGA-CNN- : A demo for accelerating YOLOv2 in xilinx's fpga PYNQ.

    • ChainZeeLi/FPGA_DPU : This project is to implement YOLO v3 on Xilinx FPGA with DPU.

    • xbdxwyh/yolov3_fpga_project : yolov3_fpga_project.

    • ZLkanyo009/Yolo-compression-and-deployment-in-FPGA : 基于FPGA量化的人脸口罩检测。

    • xiying-boy/yolov3-AX7350 : 基于HLS_YOLOV3的驱动文件。

    • himewel/yolowell : A set of hardware architectures to build a co-design of convolutional neural networks inference at FPGA devices.

    • embedeep/Free-TPU : Free TPU for FPGA with Lenet, MobileNet, Squeezenet, Resnet, Inception V3, YOLO V3, and ICNet. Deep learning acceleration using Xilinx zynq (Zedboard or ZC702 ) or kintex-7 to solve image classification, detection, and segmentation problem.

    • yarakigit/design_contest_yolo_change_ps_to_pl : Converts pytorch yolo format weights to C header files for bare-metal (FPGA implementation).

    • MasLiang/CNN-On-FPGA : This is the code of the CNN on FPGA.But this can only be used for reference at present for some files are write coarsly using ISE.

    • adamgallas/fpga_accelerator_yolov3tiny : fpga_accelerator_yolov3tiny.

    • ylk678910/tiny-yolov3-fpga : Use an all-programmable SoC board to implement locating and tracking tasks. The hardware algorithm, a row-stationary-like strategy, can parallel calculate and reduce the storage buffer area on FPGA.

    • zhen8838/K210_Yolo_framework : Yolo v3 framework base on tensorflow, support multiple models, multiple datasets, any number of output layers, any number of anchors, model prune, and portable model to K210 !

    • SEASKY-Master/SEASKY_K210 : K210 PCB YOLO.

    • SEASKY-Master/Yolo-for-k210 : Yolo-for-k210.

    • TonyZ1Min/yolo-for-k210 : keras-yolo-for-k210.

    • vseasky/yolo-for-k210 : Yolo-for-k210.

    • InnoIPA/dpu-sc : dpu-sc presented how to create quick demos to run AI inference(YOLOv4-Tiny, LPRNet) on DPU with MPSoC.

    • InnoIPA/vaiGO : vaiGO means Vitis-ai GO. We provide utility and tutorial that make it easy to convert a trained AI model into a bitstream that can be deployed on an FPGA Edge AI Box.

    • InnoIPA/EXMU-X261-usermanual : We have built more defect detection solutions with YOLOv4-tiny on EXMU-X261.

  • Other Hardware

    • guichristmann/edge-tpu-tiny-yolo : Run Tiny YOLO-v3 on Google's Edge TPU USB Accelerator.

    • Charlie839242/-Trash-Classification-Car : 这是一个基于yolo-fastest模型的小车，主控是art-pi开发板，使用了rt thread操作系统。

    • Charlie839242/Deploy-yolo-fastest-tflite-on-raspberry : This project deploys a yolo fastest model in the form of tflite on raspberry 3b+.

    • mahxn0/Hisi3559A_Yolov5 : 基于hisi3559a的yolov5训练部署全流程。

    • ZhenxinYUAN/YOLO_hi3516Deploy : Deploy Yolo series algorithms on Hisilicon platform hi3516, including yolov3, yolov5, yolox, etc.

    • jveitchmichaelis/edgetpu-yolo : Minimal-dependency Yolov5 export and inference demonstration for the Google Coral EdgeTPU.

    • xiaqing10/Hisi_YoLoV5 : 海思nnie跑yolov5。

    • BaronLeeLZP/hi3516dv300_nnie-yolov3-demo : 在海思Hisilicon的Hi3516dv300芯片上，利用nnie和opencv库，简洁了官方yolov3用例中各种复杂的嵌套调用/复杂编译，提供了交叉编译后可成功上板部署运行的demo。

    • OpenVINO-dev-contest/YOLOv7_OpenVINO : This repository will demostrate how to deploy a offical YOLOv7 pre-trained model with OpenVINO runtime api.

    • littledeep/YOLOv5-RK3399Pro : PyTorch-->ONNX-->RKNN.

    • jnulzl/YOLOV5_RK1126 : yolov5 rk1126 cpp code.

    • Qengineering/YoloCam : AI camera with live feed, email notification, Gdrive storage and event-triggered GPIO. Raspberry Pi stand-alone AI-powered camera with live feed, email notification and event-triggered cloud storage.

    • LSH9832/edgeyolo : an edge-real-time anchor-free object detector with decent performance.

    • liuyuan000/Rv1126_YOLOv5-Lite : YOLOv5-Lite在Rv1126部署。

• Pruning Knoweldge-Distillation Quantization

  • Pruning

    剪枝

    • Torch-Pruning : Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs. "Towards Any Structural Pruning". (CVPR 2023)

    • SparseML : Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models. "Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks". (PMLR 2020). "Woodfisher: Efficient second-order approximation for neural network compression". (NeurIPS 2020)

    • SparseZoo : Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes.

    • Gumpest/YOLOv5-Multibackbone-Compression : YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming) and Quantization (MQBench) Compression Tool Box.

    • SlimYOLOv3 : "SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications". (arXiv 2019)

    • uyzhang/yolov5_prune : Yolov5 pruning on COCO Dataset.

    • midasklr/yolov5prune : yolov5模型剪枝。

    • ZJU-lishuang/yolov5_prune : yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5.

    • sbbug/yolov5-prune-multi : yolov5-prune-multi 无人机视角、多模态、模型剪枝、国产AI芯片部署。

    • Syencil/mobile-yolov5-pruning-distillation : mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

    • Lam1360/YOLOv3-model-pruning : 在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）。

    • tanluren/yolov3-channel-and-layer-pruning : yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏。

    • coldlarry/YOLOv3-complete-pruning : 提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。

    • SpursLipu/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone : YOLO ModelCompression MultidatasetTraining.

    • talebolano/yolov3-network-slimming : yolov3 network slimming剪枝的一种实现。

    • Bigtuo/YOLOX-Lite : 将YOLOv5-Lite代码中的head更换为YOLOX head。

    • YINYIPENG-EN/Pruning_for_YOLOV5_pytorch : Pruning_for_YOLOV5_pytorch.

    • chumingqian/Model_Compression_For_YOLOV3-V4 : In this repository using the dynamic sparse training( variable sparse rate s which can speed up the sparse training process), channel pruning and knowledge distilling for YOLOV3 and YOLOV4.

    • xhwNobody/yolov5_prune_sfp : 基于SFP和FPGM的yolov5的软剪枝实现。

  • Quantization

    量化

    • dog-qiuqiu/FastestDet : ⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler. "知乎「马雪浩」《FastestDet: 比yolo-fastest更快！更强！更简单！全新设计的超实时Anchor-free目标检测算法》"。 "微信公众号「计算机视觉研究院」《FastestDet：比yolov5更快！更强！全新设计的超实时Anchor-free目标检测算法（附源代码下载）》"。

    • dog-qiuqiu/Yolo-Fastest : Yolo-Fastest：超超超快的开源ARM实时目标检测算法。 Zenodo 2021. "知乎「马雪浩」《Yolo-Fastest：超超超快的开源ARM实时目标检测算法》"。

    • dog-qiuqiu/Yolo-FastestV2 : Yolo-FastestV2:更快，更轻，移动端可达300FPS，参数量仅250k。 "知乎「马雪浩」《Yolo-FastestV2:更快，更轻，移动端可达300FPS，参数量仅250k》"。

    • YOLObile : "YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design". (AAAI 2021)

    • PaddleSlim : PaddleSlim is an open-source library for deep model compression and architecture search. PaddleSlim是一个专注于深度学习模型压缩的工具库，提供低比特量化、知识蒸馏、稀疏化和模型结构搜索等模型压缩策略，帮助用户快速实现模型的小型化。

    • PPL量化工具 : PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool. PPL QuantTool 是一个高效的工业级神经网络量化工具。

    • PINTO_model_zoo : A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

    • ppogg/YOLOv5-Lite : 🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

    • AlexeyAB/yolo2_light : Light version of convolutional neural network Yolo v3 & v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference).

  • Knoweldge-Distillation

    知识蒸馏

    • torchdistill : torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation. A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

    • wonbeomjang/yolov5-knowledge-distillation : implementation of Distilling Object Detectors with Fine-grained Feature Imitation on yolov5. "Distilling Object Detectors with Fine-grained Feature Imitation". (CVPR 2019)

    • Sharpiless/Yolov5-distillation-train-inference : Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据。

    • Sharpiless/yolov5-distillation-5.0 : yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s。

    • Sharpiless/yolov5-knowledge-distillation : yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）。

    • chengpanghu/Knowledge-Distillation-yolov5 : Knowledge-Distillation-yolov5 基于yolov5的知识蒸馏。

    • magicshuang/yolov5_distillation : yolov5 知识蒸馏，yolov5-l模型压缩至yolov5-s 压缩算法是 Distilling Object Detectors with Fine-grained Feature Imitation。

    • Sharpiless/Yolov3-MobileNet-Distillation : 在Yolov3-MobileNet上进行模型蒸馏训练。

    • SsisyphusTao/Object-Detection-Knowledge-Distillation : An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.

• Lightweight Backbones and FPN

  轻量级骨干网络和特征金字塔网络

  • murufeng/awesome_lightweight_networks : The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

  • Bobo-y/flexible-yolov5 : More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam，dcn and so on), and tensorrt.

  • XingZeng307/YOLOv5_with_BiFPN : This repo is mainly for replacing PANet with BiFPN in YOLOv5.

  • dog-qiuqiu/MobileNet-Yolo : MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥.

  • eric612/MobileNet-YOLO : A caffe implementation of MobileNet-YOLO detection network.

  • eric612/Mobilenet-YOLO-Pytorch : Include mobilenet series (v1,v2,v3...) and yolo series (yolov3,yolov4,...) .

  • Adamdad/keras-YOLOv3-mobilenet : A Keras implementation of YOLOv3 (Tensorflow backend) inspired by allanzelener/YAD2K.

  • fsx950223/mobilenetv2-yolov3 : yolov3 with mobilenetv2 and efficientnet.

  • liux0614/yolo_nano : Unofficial implementation of yolo nano.

  • lingtengqiu/Yolo_Nano : Pytorch implementation of yolo_Nano for pedestrian detection.

  • bubbliiiing/mobilenet-yolov4-pytorch : 这是一个mobilenet-yolov4的库，把yolov4主干网络修改成了mobilenet，修改了Panet的卷积组成，使参数量大幅度缩小。

  • bubbliiiing/efficientnet-yolo3-pytorch : 这是一个efficientnet-yolo3-pytorch的源码，将yolov3的主干特征提取网络修改成了efficientnet。

  • HuKai97/YOLOv5-ShuffleNetv2 : YOLOv5的轻量化改进(蜂巢检测项目)。

  • YOLO-ReT : "YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs". (WACV 2022)

Object Detection Applications

• Open World Object Detection

  开放世界目标检测

  • YOLO-World : "YOLO-World: Real-Time Open-Vocabulary Object Detection". (CVPR 2024). www.yoloworld.cc

  • Florence-2 : "Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks". (CVPR 2024).

  • maestro : 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, PaliGemma 2, and Qwen2.5-VL. maestro.roboflow.com

  • Autodistill : 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

  • DOSOD : "A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space". (arXiv 2024).

  • DINO : "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection". (ICLR 2023).

  • GroundingDINO : "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection". (ECCV 2024).

  • UniDetector : "Detecting Everything in the Open World: Towards Universal Object Detection". (CVPR 2023).

  • buxihuo/OW-YOLO : Detect known and unknown objects in the open world（具有区分已知与未知能力的全新检测器））.

• Few-shot Object Detection

  少样本目标检测

  • Autodistill : 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

  • bingykang/Fewshot_Detection : "Few-shot Object Detection via Feature Reweighting". (ICCV 2019).

  • SSDA-YOLO : Codes for my paper "SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection". (Computer Vision and Image Understanding, 2023).

  • OneTeacher : "Towards End-to-end Semi-supervised Learning for One-stage Object Detection". (arXiv 2023).

  • Efficient Teacher : "Efficient Teacher: Semi-Supervised Object Detection for YOLOv5". (arXiv 2023).

• Small Object Detection

  小目标检测

  • YOLO-Patch-Based-Inference : Python library for YOLO small object detection and instance segmentation. This Python library simplifies SAHI-like inference for instance segmentation tasks, enabling the detection of small objects in images. It caters to both object detection and instance segmentation tasks, supporting a wide range of Ultralytics models.

  • SAHI : "Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection". (arXiv 2022, Zenodo 2021).

  • Slim-neck by GSConv : "Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles". (arXiv 2022)

  • hustvl/TinyDet : "TinyDet: accurately detecting small objects within 1 GFLOPs". (Science China Information Sciences, 2023)

  • QueryDet : "QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection". (CVPR 2022)

  • RFLA : "RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection". (ECCV 2022). "微信公众号「CV技术指南」《ECCV 2022 | RFLA：基于高斯感受野的微小目标检测标签分配》"

  • YOLT : "You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery". (arXiv 2018). "微信公众号「江大白」《基于大尺寸图像的小目标检测竞赛经验总结》"

  • SIMRDWN : "Satellite Imagery Multiscale Rapid Detection with Windowed Networks". (arXiv 2018, WACV 2019)

  • YOLTv5 : YOLTv5 builds upon YOLT and SIMRDWN, and updates these frameworks to use the ultralytics/yolov5 version of the YOLO object detection family.

  • TPH-YOLOv5 : "TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios". (ICCV 2021)

  • mwaseema/Drone-Detection : "Dogfight: Detecting Drones from Drones Videos". (CVPR 2021)

  • CEASA : "Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images". (arXiv 2023). "微信公众号「集智书童」《即插即用 | CEASA模块给你所有，小目标精度提升的同时速度也变快了》"

  • KevinMuyaoGuo/yolov5s_for_satellite_imagery : 基于YOLOv5的卫星图像目标检测demo | A demo for satellite imagery object detection based on YOLOv5。

  • Hongyu-Yue/yoloV5_modify_smalltarget : YOLOV5 小目标检测修改版。

  • muyuuuu/Self-Supervise-Object-Detection : Self-Supervised Object Detection. 水面漂浮垃圾目标检测，分析源码改善 yolox 检测小目标的缺陷，提出自监督算法预训练无标签数据，提升检测性能。

  • swricci/small-boat-detector : Trained yolo v3 model weights and configuration file to detect small boats in satellite imagery.

  • Resham-Sundar/sahi-yolox : YoloX with SAHI Implementation.

  • YOLO-Z : "YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles". (arXiv 2021). "微信公众号「计算机视觉研究院」《Yolo-Z：改进的YOLOv5用于小目标检测（附原论文下载）》".

  • M2S : "A novel Multi to Single Module for small object detection". (arXiv 2023). "微信公众号「集智书童」《基于YOLOv5改进再设计 | M2S全面提升小目标精度》".

  • ultralytics/xview-yolov3 : xView 2018 Object Detection Challenge: YOLOv3 Training and Inference.

  • inderpreet1390/yolov5-small-target : Repository for improved yolov5 for small target detection.

  • AllenSquirrel/YOLOv3_ReSAM : YOLOv3_ReSAM:A Small Target Detection Method With Spatial Attention Module.

  • kadirnar/yolov5-sahi : Yolov5 Modelini Kullanarak Özel Nesne Eğitimi ve SAHI Kullanımı.

  • kadirnar/Yolov6-SAHI : Yolov6-SAHI.

  • zRzRzRzRzRzRzR/Mult-YOLO-alogorithm-of-RoboMaster-Radar-Detection-2023 : 2023年西交利物浦大学动云科技GMaster战队雷达yolo小目标检测。

  • quantumxiaol/yolov8-small-target-detection : 基于yolov8实现小目标检测，在NWPU VHR-10和DOTA上测试。

  • shaunyuan22/SODA : Official code library for SODA: A Large-scale Benchmark for Small Object Detection. "Towards Large-Scale Small Object Detection: Survey and Benchmarks". (arXiv 2022)

  • qunshansj/Small-Object-Detection-Head-Improved-YOLOv5-Infrared-Sensing-System : 基于小目标检测头的改进YOLOv5红外遥感图像小目标检测系统。

• Multimodal Image Detection

  多模态图像检测

  • NVIDIA-AI-IOT/Lidar_AI_Solution : This is a highly optimized solution for self-driving 3D-lidar repository. It does a great job of speeding up sparse convolution/CenterPoint/BEVFusion/OSD/Conversion. A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).

  • remaro-network/KD-YOLOX-ViT : This repository holds the code for the Python implementation of YOLOX-ViT. Furthermore, it has the implementation of the Knowledge Distillation (KD) method, evaluation metrics of the object detector and the side-scan sonar image dataset for underwater wall detection. "Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection". (arXiv 2024). The Sonar Wall Detection Dataset (SWDD) is publicly accessible at https://zenodo.org/records/10528135.

  • wandahangFY/YOLO-MIF : YOLO-MIF(YOLOv8-RGBT) is an improved version of YOLOv8 for object detection in gray-scale images, incorporating multi-information fusion to enhance detection accuracy. The detection of RGBT mode is also added. YOLO-MIF是在灰度图像中进行目标检测的改进型YOLOv8模型，引入了多信息融合策略，提高了检测准确性。 并添加了RGBT模式的检测,分割以及关节点任务。 "YOLO-MIF: Improved YOLOv8 with Multi-Information fusion for object detection in Gray-Scale images". (Advanced Engineering Informatics, 2024).

  • wandahangFY/YOLOv11-RGBT : YOLOv11-RGBT: Towards a Comprehensive Multispectral Object Detection Framework（Supports RGBT detection for all YOLO series from YOLOv3 to YOLOv12, as well as RTDETR.））

  • mcw1217/Triple_YOLOv8 : This project uses three types of images as inputs RGB, Depth, and thermal images to perform object detection with YOLOv8.

  • ljcuestc/YoloMultispectralFusion-Coarse-to-fine-Registration : "A Novel Multispectral Fusion Defect Detection Framework With Coarse-to-Fine Multispectral Registration". (IEEE Transactions on Instrumentation and Measurement, 2023)

  • SuperYOLO : "SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery". (arXiv 2022)

  • QuincyQAQ/YOLOv8-Multi-Modal-Fusion-Network-RGB-IR : YOLOv8-Multi-Modal-Fusion-Network-RGB-IR.

  • mangoggul/YOLO-MultiModal : Multi-Modal-YOLO detection.

  • DocF/multispectral-object-detection : Multispectral Object Detection with Yolov5 and Transformer.

  • Ye-zixiao/Double-YOLO-Kaist : 一种基于YOLOv3/4的双流混合模态道路行人检测方法🌊💧💦。

  • lzhihan/yolov5_Visible_Infrared_Vehicle_Detection : 基于可见光和红外图像的深度学习车辆目标检测。

  • jere357/yolov5-RGBD : "fork" from yolov5 with the possibility of running inferences on RGBD(C) images, work in progress. This repo is not a fork of the original repo bcs i already have 1 fork with a PR pending, this is still messy code and a work in progress.

  • huashu996/dual_result_fusion_yolov5 : result set fusion for visible-light and infrared images. 此双模态检测是通过对可见光和红外图像分别训练，得到两个weight，在运行时会对两种图像分别检测，最后对检测结果求极大似然，并且能够对目标进行测距。

  • MAli-Farooq/Thermal-YOLO : This study is related to object detection in thermal infrared spectrum using YOLO-V5 framework for ADAS application.

  • OrangeSodahub/CRLFnet : Camera-Radar-Lidar Fusion detection net based on ROS, YOLOv3, OpenPCDet integration.

  • mjoshi07/Visual-Sensor-Fusion : LiDAR Fusion with Vision.

  • Arrowes/CEAM-YOLOv7 : CEAM-YOLOv7: Improved YOLOv7 Based on Channel Expansion and Attention Mechanism for Driver Distraction Behavior Detection.

• Video Object Detection

  视频目标检测

  • YOLOV : "YOLOV: Making Still Image Object Detectors Great at Video Object Detection". (arXiv 2022)

  • StreamYOLO : "Real-time Object Detection for Streaming Perception". (CVPR 2022)

  • REPP : "Robust and efficient post-processing for video object detection". (IROS 2020)

  • NoScope : "Noscope: optimizing neural network queries over video at scale". (arXiv 2017)

• Object Tracking

  目标跟踪

  • Multi-Object Tracking

    多目标跟踪

    • nmhaddad/fast-track : Object tracking pipelines complete with RF-DETR, YOLOv9, YOLO-NAS, YOLOv8, and YOLOv7 detection and BYTETracker tracking.

    • sujanshresstha/YOLOv10_DeepSORT : This repository contains code for object detection and tracking in videos using the YOLOv10 object detection model and the DeepSORT algorithm.

    • BoxMOT : BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models.

    • mikel-brostrom/Yolov7_StrongSORT_OSNet : Real-time multi-camera multi-object tracker using YOLOv7 and StrongSORT with OSNet.

    • RizwanMunawar/yolov8-object-tracking : YOLOv8 Object Tracking Using PyTorch, OpenCV and Ultralytics.

    • xuarehere/yolo_series_deepsort_pytorch : Deepsort with yolo series. This project support the existing yolo detection model algorithm (YOLOv3, YOLOV4, YOLOV4Scaled, YOLOV5, YOLOV6, YOLOV7, YOLOV8, YOLOX, YOLOR, PPYOLOE ).

    • JackWoo0831/Yolov7-tracker : Yolo v7 and several Multi-Object Tracker(SORT, DeepSORT, ByteTrack, BoT-SORT, etc.) in VisDrone2019 Dataset. It uses a unified style and integrated tracker for easy embedding in your own projects. YOLOv7 + 各种tracker实现多目标跟踪。

    • BoT-SORT : "BoT-SORT: Robust Associations Multi-Pedestrian Tracking". (arXiv 2022)

    • StrongSORT : "StrongSORT: Make DeepSORT Great Again". (arXiv 2022)

    • UAVMOT : "Multi-Object Tracking Meets Moving UAV". (CVPR 2022)

    • HKPolyU-UAV/AUTO : "Dynamic Object Tracking on Autonomous UAV System for Surveillance Applications". (Sensors 2021)

    • bharath5673/StrongSORT-YOLO : Real-time multi-camera multi-object tracker using (YOLOv5, YOLOv7) and StrongSORT with OSNet.

    • mikel-brostrom/Yolov7_StrongSORT_OSNet : Real-time multi-camera multi-object tracker using YOLOv7 and StrongSORT with OSNet.

    • kadirnar/yolov5-strongsort : Minimal PyTorch implementation of YOLOv5 and StrongSORT.

    • ZQPei/deep_sort_pytorch : MOT using deepsort and yolov3 with pytorch.

    • Qidian213/deep_sort_yolov3 : Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow.

    • CSTrack : "Rethinking the competition between detection and ReID in Multi-Object Tracking". (arXiv 2020)

    • ROLO : ROLO is short for Recurrent YOLO, aimed at simultaneous object detection and tracking.

    • FastMOT : "FastMOT: High-Performance Multiple Object Tracking Based on Deep SORT and KLT". (Zenodo 2020)

    • Sharpiless/Yolov5-deepsort-inference : 使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中。

    • Sharpiless/Yolov5-Deepsort : 最新版本yolov5+deepsort目标检测和追踪，能够显示目标类别，支持5.0版本可训练自己数据集。

    • LeonLok/Multi-Camera-Live-Object-Tracking : Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.

    • LeonLok/Deep-SORT-YOLOv4 : People detection and optional tracking with Tensorflow backend.

    • obendidi/Tracking-with-darkflow : Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow.

    • DrewNF/Tensorflow_Object_Tracking_Video : Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition.

    • dyh/unbox_yolov5_deepsort_counting : yolov5 deepsort 行人 车辆 跟踪 检测 计数。

    • theAIGuysCode/yolov3_deepsort : Object tracking implemented with YOLOv3, Deep Sort and Tensorflow.

    • weixu000/libtorch-yolov3-deepsort : libtorch-yolov3-deepsort.

    • pmj110119/YOLOX_deepsort_tracker : using yolox+deepsort for object-tracking.

    • abhyantrika/nanonets_object_tracking : nanonets_object_tracking.

    • mattzheng/keras-yolov3-KF-objectTracking : 以kears-yolov3做detector，以Kalman-Filter算法做tracker，进行多人物目标追踪。

    • rohanchandra30/TrackNPred : A Software Framework for End-to-End Trajectory Prediction.

    • RichardoMrMu/yolov5-deepsort-tensorrt : A c++ implementation of yolov5 and deepsort.

    • bamwani/car-counting-and-speed-estimation-yolo-sort-python : This project imlements the following tasks in the project: 1. Vehicle counting, 2. Lane detection. 3.Lane change detection and 4.speed estimation.

    • ArtLabss/tennis-tracking : Open-source Monocular Python HawkEye for Tennis.

    • CaptainEven/YOLOV4_MCMOT : Using YOLOV4 as detector for MCMOT.

    • opendatacam/node-moving-things-tracker : javascript implementation of "tracker by detections" for realtime multiple object tracking (MOT).

    • lanmengyiyu/yolov5-deepmar : 行人轨迹和属性分析。

    • zengwb-lx/Yolov5-Deepsort-Fastreid : YoloV5 + deepsort + Fast-ReID 完整行人重识别系统。

    • tensorturtle/classy-sort-yolov5 <img src="https://img.shields.io/github/stars/tensor