YOLOv8改进有效系列目录 | 包含卷积、主干、检测头、注意力机制、Neck

入门必会知识点

标题链接
写给初学者的YOLO目标检测 概述https://blog.csdn.net/shangyanaf/article/details/130399439
YOLOv8 来了,快速上手实操https://blog.csdn.net/shangyanaf/article/details/130539468
目标检测算法以及常用库概述https://blog.csdn.net/shangyanaf/article/details/132988174
万字详解YOLOv8网络结构Backbone/neck/head以及Conv、Bottleneck、C2f、SPPF、Detect等模块https://blog.csdn.net/shangyanaf/article/details/139223155
新手小白快速看懂yolov8模型训练结果图表,通过mAP、Precision、Recall等评价性能https://blog.csdn.net/shangyanaf/article/details/139131447
图解YOLOV8基础概念详解https://blog.csdn.net/shangyanaf/article/details/137654837
YOLOv8.yaml文件详解https://blog.csdn.net/shangyanaf/article/details/137656355
YOLOv8 超参数调优和数据增强指南
YOLOv9教程:如何在自定义数据上进行YOLOv9的分割训练https://blog.csdn.net/shangyanaf/article/details/138284645
YOLO-World:缩小开放词汇下的目标检测检测速度和准确性之间的差距https://blog.csdn.net/shangyanaf/article/details/136206642
手把手教你搭建YOLOV8+CUDA环境,训练自定义数据集,训练推理验证导出。小白也能看得懂的!https://blog.csdn.net/shangyanaf/article/details/139029717
万字长文精解目标检测中的TP、FP、FN、TN、Precision、Recall 、 F1 Score、AP、mAP与AR 。附代码实现。https://blog.csdn.net/shangyanaf/article/details/138966767
混淆矩阵与多分类混淆矩阵概念详解及其应用求 Precision F1-Score Recallhttps://blog.csdn.net/shangyanaf/article/details/139104085

实战小项目

标题链接
使用 YOLOv8 和 Python、OpenCV 实现行人检测
如何使用 YOLOv9 进行对象检测https://blog.csdn.net/shangyanaf/article/details/136757338
YOLOv9教程:如何在自定义数据上进行YOLOv9的分割训练https://blog.csdn.net/shangyanaf/article/details/138284645
使用Yolov8和OpenCV计算视频中手扶梯上的人数https://blog.csdn.net/shangyanaf/article/details/134430259
使用YOLOV5实现视频中的车辆计数https://blog.csdn.net/shangyanaf/article/details/134877969
YOLO结合PySimpleGUI 构建实时目标检测软件!SoEasy!https://blog.csdn.net/shangyanaf/article/details/135285799

YOLO创新改进

标题链接
【YOLOv8改进 】 AKConv(可改变核卷积):任意数量的参数和任意采样形状的即插即用的卷积 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135661842CONV
【YOLOv8改进】动态蛇形卷积(Dynamic Snake Convolution)用于管状结构分割任务 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135668961CONV
【YOLOv8改进】SCConv :即插即用的空间和通道重建卷积 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135742727CONV
【YOLOv8改进】RFAConv:感受野注意力卷积,创新空间注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135815075CONV
【YOLOv8改进】骨干网络: SwinTransformer (基于位移窗口的层次化视觉变换器)(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135867187
【YOLOv8改进】Inner-IoU: 基于辅助边框的IoU损失(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135904930损失函数
【YOLOv8改进】Shape-IoU:考虑边框形状与尺度的指标(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135927712损失函数
【YOLOv8改进】MPDIoU:有效和准确的边界框损失回归函数 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/135948703损失函数
【YOLOv8改进】BiFPN:加权双向特征金字塔网络 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136021981特征融合
【YOLOv8改进】 AFPN :渐进特征金字塔网络 (论文笔记+引入代码).mdhttps://blog.csdn.net/shangyanaf/article/details/136025499特征融合
【YOLOv8改进】 SPD-Conv空间深度转换卷积,处理低分辨率图像和小对象问题 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136051327CONV
【YOLOv8改进】MSCA: 多尺度卷积注意力 (论文笔记+引入代码).mdhttps://blog.csdn.net/shangyanaf/article/details/136057088注意力
【YOLOv8改进】 YOLOv8 更换骨干网络之 GhostNet :通过低成本操作获得更多特征 (论文笔记+引入代码).mdhttps://blog.csdn.net/shangyanaf/article/details/136151800
【YOLOv8改进】 YOLOv8 更换骨干网络之GhostNetV2 长距离注意力机制增强廉价操作,构建更强端侧轻量型骨干 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136170972
【YOLOv8改进】MCA:用于图像识别的深度卷积神经网络中的多维协作注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136205065注意力
【YOLOv8改进】 MSDA:多尺度空洞注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136215149注意力
【YOLOv8改进】iRMB: 倒置残差移动块 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136658166
【YOLOv8改进】CoordAttention: 用于移动端的高效坐标注意力机制 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136824282注意力机制
【YOLOv8改进】MobileNetV3替换Backbone (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136891204主干
【YOLOv8改进】MobileViT 更换主干网络: 轻量级、通用且适合移动设备的视觉变压器 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/136962297主干
【YOLOv8改进】MSBlock : 分层特征融合策略 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/137029177CONV
【YOLOv8改进】Polarized Self-Attention: 极化自注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/137295765注意力机制
【YOLOv8改进】LSKNet(Large Selective Kernel Network ):空间选择注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/137614259注意力机制
【YOLOv8改进】Explicit Visual Center: 中心化特征金字塔模块(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/137645622特征融合篇
【YOLOv8改进】Non-Local:基于非局部均值去噪滤波的自注意力模型 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139105131注意力机制
【YOLOv8改进】STA(Super Token Attention) 超级令牌注意力机制 (论文笔记+引入代码))https://blog.csdn.net/shangyanaf/article/details/139113660注意力机制
【YOLOv8改进】HAT(Hybrid Attention Transformer,)混合注意力机制 (论文笔记+引入代码))https://blog.csdn.net/shangyanaf/article/details/139142532注意力机制
【YOLOv8改进】ACmix(Mixed Self-Attention and Convolution) (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139167656混合卷积注意力机制
【YOLOv8改进】EMA(Efficient Multi-Scale Attention):基于跨空间学习的高效多尺度注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139160226注意力机制
【YOLOv8改进】CPCA(Channel prior convolutional attention)中的通道注意力,增强特征表征能力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139186904注意力机制
【YOLOv8改进】DAT(Deformable Attention):可变性注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139193465注意力机制
【YOLOv8改进】D-LKA Attention:可变形大核注意力 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139212227注意力机制
【YOLOv8改进】LSKA(Large Separable Kernel Attention):大核分离卷积注意力模块 (论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139249202注意力机制
【YOLOv8改进】CoTAttention:上下文转换器注意力(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139261641注意力机制
【YOLOv8改进】MLCA(Mixed local channel attention):混合局部通道注意力(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139279527注意力机制
【YOLOv8改进】CAFM(Convolution and Attention Fusion Module):卷积和注意力融合模块https://blog.csdn.net/shangyanaf/article/details/139305822混合卷积注意力机制
【YOLOv8改进】MSFN(Multi-Scale Feed-Forward Network):多尺度前馈网络https://blog.csdn.net/shangyanaf/article/details/139306250其他
【YOLOv8改进】BRA(bi-level routing attention ):双层路由注意力(论文笔记+引入代码)https://blog.csdn.net/shangyanaf/article/details/139307690注意力机制
【YOLOv8改进】 ODConv(Omni-Dimensional Dynamic Convolution):全维度动态卷积https://blog.csdn.net/shangyanaf/article/details/139389091CONV
【YOLOv8改进】 SAConv(Switchable Atrous Convolution):可切换的空洞卷积https://blog.csdn.net/shangyanaf/article/details/139393928CONV
【YOLOv8改进】 ParameterNet:DynamicConv(Dynamic Convolution):2024最新动态卷积https://blog.csdn.net/shangyanaf/article/details/139395420CONV
【YOLOv8改进】 RFB (Receptive Field Block):多分支卷积块https://blog.csdn.net/shangyanaf/article/details/139431807CONV
【YOLOv8改进】 OREPA(Online Convolutional Re-parameterization):在线卷积重参数化https://blog.csdn.net/shangyanaf/article/details/139465775CONV
【YOLOv8改进】DualConv( Dual Convolutional):用于轻量级深度神经网络的双卷积核https://blog.csdn.net/shangyanaf/article/details/139477420CONV
【YOLOv8改进】SlideLoss损失函数,解决样本不平衡问题https://blog.csdn.net/shangyanaf/article/details/139483941损失函数
【YOLOv8改进】 YOLOv8自带损失函数CIoU / DIoU / GIoU 详解,以及如何切换损失函数https://blog.csdn.net/shangyanaf/article/details/139509783损失函数
【YOLOv8改进】YOLOv8 更换损失函数之 SIoU EIoU WIoU _ Focal_*IoU CIoU DIoU ShapeIoU MPDIouhttps://blog.csdn.net/shangyanaf/article/details/139512620损失函数
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值