开始讲解之前推荐一下我的专栏本专栏的内容支持(分类、检测、分割、追踪、关键点检测),专栏目前为限时折扣欢迎大家订阅本专栏本专栏每周更新5-7篇最新机制更有包含我所有改进的文件和交流群提供给大家本人定期在群内分享发表论文方法和经验。一、本文介绍本文给大家带来的改进机制是Haar 小波的下采样HWD替换传统下采样改变YOLO传统的Conv下采样在小波变换中Haar小波作为一种基本的小波函数用于将图像数据分解为多个层次的近似和细节信息这是一种多分辨率的分析方法。我将其用在YOLOv26上其明显降低参数和轻量化效果十分明显这种不同架构下的模块和YOLO结合属于多模态的融合利用这种结构去发表论文是十分容易接收的.欢迎大家订阅我的专栏一起学习YOLO专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、原理介绍三、核心代码四、手把手教你添加HWD机制4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五五、正式训练5.1 yaml文件5.1.1 yaml文件15.1.2 yaml文件25.2 训练代码5.3 训练过程截图五、本文总结二、原理介绍官方论文地址官方论文地址点击此处即可跳转论文需要花钱此论文官方代码地址官方代码地址点击此处即可跳转论文介绍了一种基于Haar小波变换的图像压缩方法及其压缩图像质量的评估方法。下面是对论文内容的详细分析主要内容和方法1. Haar小波变换的介绍Haar小波是最简单的小波形式之一具有易于计算和实现的优点。文章中应用了二维离散小波变换2D DWT将图像信息矩阵分解为细节矩阵和信息矩阵。重构图像使用这些矩阵和小波变换的信息完成。2. 图像压缩技术压缩技术通过使用Haar小波作为基函数减少图像文件大小同时尽可能保持图像质量。压缩过程包括将图像信息转换为更易于编码的格式这通常涉及转换、量化和熵编码。结论论文证明了Haar小波变换是一种有效的图像压缩工具尤其适合需要高压缩比而又不希望图像质量下降太多的应用场景。此外通过对比传统的DCT和最新的小波变换方法作者指出Haar小波在处理图像边缘和细节方面具有一定的优势尤其是在压缩高分辨率图像时。三、核心代码本节的代码使用方式看章节四import torch import torch.nn as nn try: from pytorch_wavelets import DWTForward # 按照这个第三方库需要安装pip install pytorch_wavelets1.3.0 # 如果提示缺少pywt库则安装 pip install PyWavelets except: pass class Down_wt(nn.Module): def __init__(self, in_ch, out_ch): super(Down_wt, self).__init__() self.wt DWTForward(J1, modezero, wavehaar) self.conv_bn_relu nn.Sequential( nn.Conv2d(in_ch*4, out_ch, kernel_size1, stride1), nn.BatchNorm2d(out_ch), nn.ReLU(inplaceTrue), ) def forward(self, x): yL, yH self.wt(x) y_HL yH[0][:,:,0,::] y_LH yH[0][:,:,1,::] y_HH yH[0][:,:,2,::] x torch.cat([yL, y_HL, y_LH, y_HH], dim1) x self.conv_bn_relu(x) return x if __name__ __main__: # Generating Sample image image_size (1, 64, 224, 224) image torch.rand(*image_size) # Model model Down_wt(64, 32) out model(image) print(out.size())四、手把手教你添加HWD机制下面的步骤如果你不会或者不想麻烦操作可以联系作者获得本专栏添加所有项目文件的源代码可直接训练.4.1 修改一第一还是建立文件我们找到如下ultralytics/nn文件夹下建立一个目录名字呢就是Addmodules文件夹4.2 修改二然后在Addmodules文件夹内建立一个新的py文件将本文章节三中的“核心代码复制粘贴进去。4.3 修改三第二步我们在该目录下创建一个新的py文件名字为__init__.py然后在其内部导入我们的文件如下图所示。4.4 修改四第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(此处只需要添加一次即可如果你用我其它的改进机制这里的步骤只需要添加一次)4.5 修改五在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1500行左右按照图示位置添加即可此处需要自己有一定的判别能力如果不会可联系作者获得视频教程。到此就修改完成了大家可以复制下面的yaml文件运行更多使用方式可以联系作者获得使用视频本文仅列出常见的使用方式。。五、正式训练5.1 yaml文件5.1.1 yaml文件1训练信息YOLO26-Haar-1 summary: 272 layers, 2,201,752 parameters, 2,201,752 gradients, 5.2 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Haar, [128]] # 1-P2/4 - [-1, 2, C3k2, [256, False, 0.25]] - [-1, 1, Haar, [256]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] - [-1, 1, Haar, [512]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] - [-1, 1, Haar, [1024]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) # - [-1, 1, Conv, [256, 3, 2]] - [-1, 1, Haar, [256]] # 和上面一层二选一. - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) # - [-1, 1, Conv, [512, 3, 2]] - [-1, 1, Haar, [512]] # 和上面一层二选一. - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)5.1.2 yaml文件2训练信息YOLO26-Haar-2 summary: 268 layers, 2,303,960 parameters, 2,303,960 gradients, 5.3 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Haar, [128]] # 1-P2/4 - [-1, 2, C3k2, [256, False, 0.25]] - [-1, 1, Haar, [256]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] - [-1, 1, Haar, [512]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] - [-1, 1, Haar, [1024]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] # - [-1, 1, Haar, [256]] # 和上面一层二选一. - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] # - [-1, 1, Haar, [512]] # 和上面一层二选一. - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - [-1, 2, C3k2_ADown, [256, False, 0.25]] - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 2, C3k2_ADown, [512, False, 0.25]] - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 2, C3k2_ADown, [512, True]] - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 2, C3k2_ADown, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2_ADown, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2_ADown, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2_ADown, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2_ADown, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)5.2 训练代码大家可以创建一个py文件将我给的代码复制粘贴进去配置好自己的文件路径即可运行。import warnings warnings.filterwarnings(ignore) from ultralytics import YOLO if __name__ __main__: model YOLO(模型配置文件地址,也就是5.1你保存到本地文件的地址) # 如何切换模型版本, 上面的ymal文件可以改为 yolo26s.yaml就是使用的26s, # 类似某个改进的yaml文件名称为yolo26-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolo26l-XXX.yaml即可改的是上面YOLO中间的名字不是配置文件的 # model.load(yolo26n.pt) # 是否加载预训练权重,科研不建议大家加载否则很难提升精度 model.train( datar数据集文件地址, # 如果大家任务是其它的ultralytics/cfg/default.yaml找到这里修改task可以改成detect, segment, classify, pose cacheFalse, imgsz640, epochs20, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerMuSGD, # using SGD/MuSGD # resume, # 这里是填写last.pt地址 ampFalse, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )5.3 训练过程截图五、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
yolov26改进 | Conv/卷积篇 | 利用Haar 小波的下采样HWD替换传统下采样（附网络结构图）
发布时间：2026/7/18 12:38:04
开始讲解之前推荐一下我的专栏本专栏的内容支持(分类、检测、分割、追踪、关键点检测),专栏目前为限时折扣欢迎大家订阅本专栏本专栏每周更新5-7篇最新机制更有包含我所有改进的文件和交流群提供给大家本人定期在群内分享发表论文方法和经验。一、本文介绍本文给大家带来的改进机制是Haar 小波的下采样HWD替换传统下采样改变YOLO传统的Conv下采样在小波变换中Haar小波作为一种基本的小波函数用于将图像数据分解为多个层次的近似和细节信息这是一种多分辨率的分析方法。我将其用在YOLOv26上其明显降低参数和轻量化效果十分明显这种不同架构下的模块和YOLO结合属于多模态的融合利用这种结构去发表论文是十分容易接收的.欢迎大家订阅我的专栏一起学习YOLO专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、原理介绍三、核心代码四、手把手教你添加HWD机制4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五五、正式训练5.1 yaml文件5.1.1 yaml文件15.1.2 yaml文件25.2 训练代码5.3 训练过程截图五、本文总结二、原理介绍官方论文地址官方论文地址点击此处即可跳转论文需要花钱此论文官方代码地址官方代码地址点击此处即可跳转论文介绍了一种基于Haar小波变换的图像压缩方法及其压缩图像质量的评估方法。下面是对论文内容的详细分析主要内容和方法1. Haar小波变换的介绍Haar小波是最简单的小波形式之一具有易于计算和实现的优点。文章中应用了二维离散小波变换2D DWT将图像信息矩阵分解为细节矩阵和信息矩阵。重构图像使用这些矩阵和小波变换的信息完成。2. 图像压缩技术压缩技术通过使用Haar小波作为基函数减少图像文件大小同时尽可能保持图像质量。压缩过程包括将图像信息转换为更易于编码的格式这通常涉及转换、量化和熵编码。结论论文证明了Haar小波变换是一种有效的图像压缩工具尤其适合需要高压缩比而又不希望图像质量下降太多的应用场景。此外通过对比传统的DCT和最新的小波变换方法作者指出Haar小波在处理图像边缘和细节方面具有一定的优势尤其是在压缩高分辨率图像时。三、核心代码本节的代码使用方式看章节四import torch import torch.nn as nn try: from pytorch_wavelets import DWTForward # 按照这个第三方库需要安装pip install pytorch_wavelets1.3.0 # 如果提示缺少pywt库则安装 pip install PyWavelets except: pass class Down_wt(nn.Module): def __init__(self, in_ch, out_ch): super(Down_wt, self).__init__() self.wt DWTForward(J1, modezero, wavehaar) self.conv_bn_relu nn.Sequential( nn.Conv2d(in_ch*4, out_ch, kernel_size1, stride1), nn.BatchNorm2d(out_ch), nn.ReLU(inplaceTrue), ) def forward(self, x): yL, yH self.wt(x) y_HL yH[0][:,:,0,::] y_LH yH[0][:,:,1,::] y_HH yH[0][:,:,2,::] x torch.cat([yL, y_HL, y_LH, y_HH], dim1) x self.conv_bn_relu(x) return x if __name__ __main__: # Generating Sample image image_size (1, 64, 224, 224) image torch.rand(*image_size) # Model model Down_wt(64, 32) out model(image) print(out.size())四、手把手教你添加HWD机制下面的步骤如果你不会或者不想麻烦操作可以联系作者获得本专栏添加所有项目文件的源代码可直接训练.4.1 修改一第一还是建立文件我们找到如下ultralytics/nn文件夹下建立一个目录名字呢就是Addmodules文件夹4.2 修改二然后在Addmodules文件夹内建立一个新的py文件将本文章节三中的“核心代码复制粘贴进去。4.3 修改三第二步我们在该目录下创建一个新的py文件名字为__init__.py然后在其内部导入我们的文件如下图所示。4.4 修改四第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(此处只需要添加一次即可如果你用我其它的改进机制这里的步骤只需要添加一次)4.5 修改五在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1500行左右按照图示位置添加即可此处需要自己有一定的判别能力如果不会可联系作者获得视频教程。到此就修改完成了大家可以复制下面的yaml文件运行更多使用方式可以联系作者获得使用视频本文仅列出常见的使用方式。。五、正式训练5.1 yaml文件5.1.1 yaml文件1训练信息YOLO26-Haar-1 summary: 272 layers, 2,201,752 parameters, 2,201,752 gradients, 5.2 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Haar, [128]] # 1-P2/4 - [-1, 2, C3k2, [256, False, 0.25]] - [-1, 1, Haar, [256]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] - [-1, 1, Haar, [512]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] - [-1, 1, Haar, [1024]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) # - [-1, 1, Conv, [256, 3, 2]] - [-1, 1, Haar, [256]] # 和上面一层二选一. - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) # - [-1, 1, Conv, [512, 3, 2]] - [-1, 1, Haar, [512]] # 和上面一层二选一. - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)5.1.2 yaml文件2训练信息YOLO26-Haar-2 summary: 268 layers, 2,303,960 parameters, 2,303,960 gradients, 5.3 GFLOPs# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Haar, [128]] # 1-P2/4 - [-1, 2, C3k2, [256, False, 0.25]] - [-1, 1, Haar, [256]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] - [-1, 1, Haar, [512]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] - [-1, 1, Haar, [1024]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] # - [-1, 1, Haar, [256]] # 和上面一层二选一. - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] # - [-1, 1, Haar, [512]] # 和上面一层二选一. - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)# Ultralytics AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. modelyolo26n.yaml will call yolo26.yaml with scale n # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - [-1, 2, C3k2_ADown, [256, False, 0.25]] - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 2, C3k2_ADown, [512, False, 0.25]] - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 2, C3k2_ADown, [512, True]] - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 2, C3k2_ADown, [1024, True]] - [-1, 1, SPPF, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2_ADown, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, nearest]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2_ADown, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2_ADown, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2_ADown, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)5.2 训练代码大家可以创建一个py文件将我给的代码复制粘贴进去配置好自己的文件路径即可运行。import warnings warnings.filterwarnings(ignore) from ultralytics import YOLO if __name__ __main__: model YOLO(模型配置文件地址,也就是5.1你保存到本地文件的地址) # 如何切换模型版本, 上面的ymal文件可以改为 yolo26s.yaml就是使用的26s, # 类似某个改进的yaml文件名称为yolo26-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolo26l-XXX.yaml即可改的是上面YOLO中间的名字不是配置文件的 # model.load(yolo26n.pt) # 是否加载预训练权重,科研不建议大家加载否则很难提升精度 model.train( datar数据集文件地址, # 如果大家任务是其它的ultralytics/cfg/default.yaml找到这里修改task可以改成detect, segment, classify, pose cacheFalse, imgsz640, epochs20, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerMuSGD, # using SGD/MuSGD # resume, # 这里是填写last.pt地址 ampFalse, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )5.3 训练过程截图五、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
