yolo项目汇总-CSDN博客

Perform a series of ablation experiments on yolov5 to make it lighter (smaller Flops, lower memory, and fewer parameters) and faster (add shuffle channel, yolov5 head for channel reduce. It can infer at least 10+ FPS On the Raspberry Pi 4B when input the frame with 320×320) and is easier to deploy (removing the Focus layer and four slice operations, reducing the model quantization accuracy to an acceptable range).

在 yolov5 上进行一系列消融实验，使其更轻（更小的 Flops、更低的内存和更少的参数）和更快（添加 shuffle channel，yolov5 head for channel reduce。它可以在 Raspberry Pi 4B 上推断至少 10+ FPS 时输入320×320的帧）更容易部署（去掉Focus层和四片操作，将模型量化精度降低到可以接受的范围内）。

4. YOLOXGitHub - Megvii-BaseDetection/YOLOX: YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/ - GitHub - Megvii-BaseDetection/YOLOX: YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/https://github.com/Megvii-BaseDetection/YOLOX5.YOLOR

属实没看懂YOLOR，如何评价YOLOR：性能超过Scaled-YOLOv4和PP-YOLOv2? - 知乎在尝试努力看懂这篇文章后，我选择了放弃。不知道是我理解能力有问题还是作者的表达方式的问题，我并不能…https://www.zhihu.com/question/460412369/answer/1896485698

GitHub - WongKinYiu/yolor: implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206) - GitHub - WongKinYiu/yolor: implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)https://github.com/WongKinYiu/yolor6. 做跟踪的

GitHub - Sharpiless/Yolov5-deepsort-inference: 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https://github.com/Sharpiless/Yolov5-deepsort-inference

https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorchhttps://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch7.人脸检测

GitHub - miladsoltany/Face-Detection: Face detection using yolov5Face detection using yolov5. Contribute to miladsoltany/Face-Detection development by creating an account on GitHub.https://github.com/miladsoltany/Face-Detection

https://github.com/deepcam-cn/yolov5-facehttps://github.com/deepcam-cn/yolov5-face8.旋转目标检测

https://github.com/BossZard/rotation-yolov5https://github.com/BossZard/rotation-yolov5

https://github.com/hukaixuan19970627/yolov5_obbhttps://github.com/hukaixuan19970627/yolov5_obb9. 剪枝蒸馏

https://github.com/xhwNobody/yolov5_prune_sfphttps://github.com/xhwNobody/yolov5_prune_sfp https://github.com/mvpzhangqiu/yolov5prunehttps://github.com/mvpzhangqiu/yolov5prune

https://github.com/ZJU-lishuang/yolov5_prunehttps://github.com/ZJU-lishuang/yolov5_prune GitHub - midasklr/yolov5pruneContribute to midasklr/yolov5prune development by creating an account on GitHub.https://github.com/midasklr/yolov5prune GitHub - jiachengjiacheng/Pruned-YOLO: Using model pruning method to obtain compact models Pruned-YOLOv5 based on YOLOv5.Using model pruning method to obtain compact models Pruned-YOLOv5 based on YOLOv5. - GitHub - jiachengjiacheng/Pruned-YOLO: Using model pruning method to obtain compact models Pruned-YOLOv5 based on YOLOv5.https://github.com/jiachengjiacheng/Pruned-YOLO

https://github.com/Syencil/mobile-yolov5-pruning-distillationhttps://github.com/Syencil/mobile-yolov5-pruning-distillation yolov5 (V6) 剪枝的干净代码版本：

GitHub - uyzhang/yolov5_prune

10. The original Yolo V5 was an amazing project. When I want to make some changes to the network, it's not so easy, such as adding branches and trying other backbones. Maybe there are people like me, so I split the yolov5 model to {backbone, neck, head} to facilitate the operation of various modules and support more backbones.Basically, I only changed the model, and I didn't change the architecture, training and testing of yolov5. Therefore, if the original code is updated, it is also very convenient to update this code. if this repo can help you, please give me a star.

最初的 Yolo V5 是一个了不起的项目。当我想对网络进行一些更改时，并不是那么容易，例如添加分支和尝试其他主干。可能有我这样的人，所以我把yolov5模型拆分成{backbone,neck,head}，方便各个模块的操作，支持更多的主干。基本上我只改了模型，没改架构， yolov5的训练和测试。因此，如果更新原始代码，更新这段代码也很方便。如果这个repo可以帮助你，请给我一个star。

GitHub - yl305237731/flexible-yolov5: More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam，dcn and so on), and tensorrtMore readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam，dcn and so on), and tensorrt - GitHub - yl305237731/flexible-yolov5: More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam，dcn and so on), and tensorrthttps://github.com/yl305237731/flexible-yolov511. TPH-yolov5

GitHub - cv516Buaa/tph-yolov5https://github.com/cv516Buaa/tph-yolov512. yolov5注释版

GitHub - SCAU-HuKai/yolov5-5.x-annotations: 一个基于yolov5-5.0的中文注释版本！https://github.com/SCAU-HuKai/yolov5-5.x-annotations
https://github.com/Laughing-q/yolov5_annotationshttps://github.com/Laughing-q/yolov5_annotations13. 车牌检测

GitHub - xialuxi/yolov5-car-plate: 基于yolov5的车牌检测，包含车牌角点检测基于yolov5的车牌检测，包含车牌角点检测. Contribute to xialuxi/yolov5-car-plate development by creating an account on GitHub.https://github.com/xialuxi/yolov5-car-plate

https://github.com/zeusees/License-Plate-Detectorhttps://github.com/zeusees/License-Plate-Detector14. YOLODet-PyTorch是端到端基于pytorch框架复现yolo最新算法的目标检测开发套件，旨在帮助开发者更快更好地完成检测模型的训练、精度速度优化到部署全流程。YOLODet-PyTorch以模块化的设计实现了多种主流YOLO目标检测算法，并且提供了丰富的数据增强、网络组件、损失函数等模块。

https://github.com/wuzhihao7788/yolodet-pytorchhttps://github.com/wuzhihao7788/yolodet-pytorch15. 蒸馏

GitHub - Sharpiless/yolov5-distillation-5.0: yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5syolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s - GitHub - Sharpiless/yolov5-distillation-5.0: yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5shttps://github.com/Sharpiless/yolov5-distillation-5.0 GitHub - Sharpiless/yolov5-knowledge-distillation: yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）https://github.com/Sharpiless/yolov5-knowledge-distillation GitHub - SsisyphusTao/Object-Detection-Knowledge-Distillation: An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5. - GitHub - SsisyphusTao/Object-Detection-Knowledge-Distillation: An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.https://github.com/SsisyphusTao/Object-Detection-Knowledge-Distillation

GitHub - Sharpiless/Yolov5-distillation-train-inference: Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据https://github.com/Sharpiless/Yolov5-distillation-train-inference16. yolov5 with bi-fpn

GitHub - XingZeng307/YOLOv5_with_BiFPNContribute to XingZeng307/YOLOv5_with_BiFPN development by creating an account on GitHub.https://github.com/XingZeng307/YOLOv5_with_BiFPN17. 小目标检测

GitHub - Hongyu-Yue/yoloV5_modify_smalltarget: YOLOV5 小目标检测修改版YOLOV5 小目标检测修改版. Contribute to Hongyu-Yue/yoloV5_modify_smalltarget development by creating an account on GitHub.https://github.com/Hongyu-Yue/yoloV5_modify_smalltarget18.人行横道检测

GitHub - zhangzhengde0225/CDNet: The Crosswalk Detection (Zebra Crossing Detection) Network based on YOLOv5The Crosswalk Detection (Zebra Crossing Detection) Network based on YOLOv5 - GitHub - zhangzhengde0225/CDNet: The Crosswalk Detection (Zebra Crossing Detection) Network based on YOLOv5https://github.com/zhangzhengde0225/CDNet19. yolov5-shufflenetv2

GitHub - shaoshengsong/YOLOv5-ShuffleNetV2Contribute to shaoshengsong/YOLOv5-ShuffleNetV2 development by creating an account on GitHub.https://github.com/shaoshengsong/YOLOv5-ShuffleNetV220.yolov5项目汇总

GitHub - ashishpatel26/Yolov5-King-of-object-Detection: Yolov5 : You Look Only Once v5 Learning Resources and Collectionhttps://github.com/ashishpatel26/Yolov5-King-of-object-Detection#yolov5-collection-21.

accomplished

2021.12.15
- change backbone to Ghostnet
- Finish EagleEye pruning YOLOv5 series
2021.12.27
- change backbone to shufflenetv2
- change backbone to efficientnetv2

https://github.com/Ranking666/Yolov5-Processinghttps://github.com/Ranking666/Yolov5-Processing22. transformer-yolov5

https://github.com/pat-langevin/yolov5_transformerhttps://github.com/pat-langevin/yolov5_transformer23.可以训练yolov5(v6.0)、yolox、小型网络，添加注意力机制

https://github.com/xialuxi/yolov5_allhttps://github.com/xialuxi/yolov5_all24.

GitHub - OutBreak-hui/YoloV5-Flexible-and-Inference: 基于YoloV5的一些魔改及相关部署方案基于YoloV5的一些魔改及相关部署方案. Contribute to OutBreak-hui/YoloV5-Flexible-and-Inference development by creating an account on GitHub.https://github.com/OutBreak-hui/YoloV5-Flexible-and-Inference

25. 小麦检测，添加mix-up数据增强

https://github.com/tanmaypandey7/wheat-detection#Modificationshttps://github.com/tanmaypandey7/wheat-detection#Modifications 小麦检测，添加SE

GitHub - Chuxwa/Global-Wheat-Detection-using-Yolov5: An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021). - GitHub - Chuxwa/Global-Wheat-Detection-using-Yolov5: An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).https://github.com/Chuxwa/Global-Wheat-Detection-using-Yolov5

26. 替换YOLOv5 tag=4.0 主干：MobileNetV2@1.0 和 MobileNetV2@0.25

https://github.com/RedHandLM/MobileNet-YOLOv5https://github.com/RedHandLM/MobileNet-YOLOv527.

在yolox正添加训练yolov5的数据格式，以及测试代码。
目前是在单gpu模式下修改调试的代码，多gpu下还需要。
具体修改：
- 在yolox/data/datasets/下添加yolo.py和yolo_classes.py
- 在yolox/data/datasets/ init .py中添加
  - 从 .yolo 导入 YOLODataset
  - 从 .yolo_classes 导入 YOLO_CLASSES
- 在yolox/evaluators/下添加yolo_evaluator.py
- 在yolox/evaluators/ init .py中添加：
  - 从 .yolo_evaluator 导入 YOLOEvaluator
- 训练的配置文件参考yolox_yolo_s.py
修改代码，多gpu下分别计算各自卡上的map，未做多gpu同步计算。
增加多gpu计算map的代码

GitHub - xialuxi/yolox-yolov5https://github.com/xialuxi/yolox-yolov528.mobilenetv3,shufflenetv2

This repo code uses Softmax and CrossEntropyLoss instead of BCEWithLogitsLoss.The improved source code is fully compatible with the original version of YOLOv5:v5. At the same time, backbone supports mobilenetv3,shufflenetv2, the original backbone supports all, and so on.

GitHub - shaoshengsong/YOLOv5-ShuffleNetV2-CrossEntropyLossContribute to shaoshengsong/YOLOv5-ShuffleNetV2-CrossEntropyLoss development by creating an account on GitHub.https://github.com/shaoshengsong/YOLOv5-ShuffleNetV2-CrossEntropyLoss29.PP-LCNET

GitHub - OutBreak-hui/Yolov5-PP-LCNetContribute to OutBreak-hui/Yolov5-PP-LCNet development by creating an account on GitHub.https://github.com/OutBreak-hui/Yolov5-PP-LCNet30.

2020.12.1：