yolov26改进 | Conv/卷积篇 | 全维度动态卷积ODConv卷积二次创新C3k2助力YOLOv26有效涨点（附网络结构图）

Snu77

394人浏览 · 2026-05-08 17:15:24

Snu77 · 2026-05-08 17:15:24 发布

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3-5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。

一、本文介绍

这篇文章给大家带来的是ODConv(Omni-Dimensional Dynamic Convolution)中文名字全维度动态卷积，该卷积可以即插即用，可以直接替换网络结构中的任何一个卷积模块，在本文的末尾提供可以直接替换卷积模块的ODConv，二次创新的C3k2_ODConv(配合教程将代码复制粘贴到你自己的代码中即可运行)给大家，该卷积模块主要具有更小的计算量和更高的精度下面的图片是精度的对比本文提供了两种代码一种是二次创新C3k2，另外一种是利用ODConv替换传统的Conv进行下采样（本文提供了二次创新的C3k2网络结构图帮助大家理解，同时可以插入到大家撰写的论文中）。

适用场景：轻量化、所有检测目标时均可使用进行有效涨点

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

2.2论文总结

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

4.6 修改六

5.1 yaml文件

二、基本原理介绍

论文地址：论文地址点击即可跳转阅读

代码地址：代码地址点击即可跳转阅读

大家估计只是冲着代码来看，估计很少想要看其原理的，所以我们这里只做略微的介绍和简单的讲解，最起码知道其基本的原理。

2.1ODConv基本原理介绍

ODConv的创新之处在于它采用了一种多维注意力机制。这种机制通过并行策略来学习卷积核在核空间所有四个维度（即空间大小、输入通道数和每个卷积层的输出通道数）上的互补注意力。这种方法适用于任何卷积层，增强了网络的灵活性和适应性(这个四个维度的卷积可以在代码中清晰的体现出来)

ODConv卷积主要的改进机制就是在上面的地方体现出来的，这个变量名aggregate_weight就是文中提到的四个维度，其中的通道数[16，16，3，3]的含义为其具有16个维度，每个卷积核有16个通道，卷积核的大小是3x3，所以这处就是体现其具体改动的地方，这处的代码可以在我文末提供的代码中可以找到如果想要了解可以自己debug看一下。

那么大家可能想问了，它是如何减少计算量的呢？因为他具有16个通道数所以他计算是通过并行的方式，因为这一机制导致它的计算量也变小了(是不是感觉一举两得)。

总结：其实ODConv就是提出了这么一种具有多维度的卷积核所以其减少了计算量同时提高了检测精度。

上面的总结是我个人的理解，下面的是文章中的总结->

2.2论文总结

Omni-Dimensional Dynamic Convolution（ODConv）的基本原理是对传统的卷积神经网络（CNN）中卷积层的设计进行创新。在传统的CNN中，每个卷积层通常使用固定的、静态的卷积核来提取特征。相比之下，ODConv引入了一种动态的、多维的注意力机制，对卷积核的设计进行了全面的改进。下面详细介绍其原理：

多维动态注意力机制：ODConv的核心创新是其多维动态注意力机制。传统的动态卷积通常只在卷积核数量这一个维度上实现动态性，即通过对多个卷积核进行加权组合以适应不同的输入特征。ODConv则进一步扩展了这一概念，它不仅在卷积核数量上动态调整，还涉及到卷积核的其他三个维度：空间大小、输入通道数、输出通道数。这意味着ODConv能够更精细地适应输入数据的特征，从而提高特征提取的效果。

并行策略：ODConv采用并行策略来同时学习不同维度上的注意力。这种策略允许网络在处理每个维度的特征时更加高效，同时确保各维度之间的互补性和协同作用。

下面的图片左边的是传统的动态卷积右边是文章中提出的ODConv。

ODConv的独特之处：与DyConv和CondConv不同，ODConv采用了一种新颖的多维注意力机制。这种机制不是仅针对每个卷积核计算一个单一的注意力标量，而是沿着卷积核空间的所有四个维度计算四种类型的注意力：αsi, αci, αfi, 和αwi。这样的设计允许ODConv在空间大小、输入通道数、过滤器数量（输出通道数）和卷积核数量这四个维度上进行细粒度的动态调整。这一处在代码中也有清晰的体现如下图->

并行计算：ODConv能够以并行的方式计算这四种类型的注意力，这提高了其效率，并允许它更全面地捕捉和利用输入数据的多维特征。

上面提到了每个通道分别计算其注意力机制，那么其是如何生效的呢？并且提高模型精度的呢？

下面图片中分别具有a，b，c，d代表四个不同通道的注意力机制生效方式。

如何在其四种不同类型的注意力机制中逐步应用到卷积核上的过程的呢，下面是对这一过程的解释：

位置维度的逐点乘法（Location-wise Multiplication）：如上图(a)所示，这一步涉及到沿着卷积核的空间维度（即卷积核的高度和宽度）进行的乘法操作。在这里，ODConv计算的位置维度注意力（αsi）被应用于卷积核的每个空间位置上，这允许网络动态调整卷积核在处理不同空间位置的信息时的重要性。
通道维度的逐通道乘法（Channel-wise Multiplication）：如上图(b)所示，这一步是沿着输入通道维度进行的乘法操作。在这个阶段，通道维度的注意力（αci）被应用于卷积核的每个输入通道上，使得网络能够针对不同的输入特征通道动态调整其处理方式。
输出通道维度的逐滤波器乘法（Filter-wise Multiplication）：如上图(c)所示，这一步是沿着输出通道维度进行的乘法操作。在这里，输出通道维度的注意力（αfi）影响卷积核的每个输出滤波器，从而使网络能够根据不同输出特征的重要性进行调整。
卷积核维度的逐核乘法（Kernel-wise Multiplication）：如上图(d)所示，这一步是沿着卷积核维度进行的乘法操作。卷积核维度的注意力（αwi）在这一阶段被应用，它允许网络动态调整不同卷积核的重要性。

通过这种分步骤的乘法操作，ODConv能够在卷积过程中综合考虑空间位置、输入通道、输出通道和卷积核数量等多个维度的信息，从而实现对卷积核的全方位动态调整。这种细致的调整方式使得ODConv能够更精准地提取特征，增强网络的学习和表达能力。论文的方法部分对这些操作的具体数学表达和实现细节(大家有兴趣可以看看论文，论文在开头我提供了地址)。

三、ODConv代码

核心代码使用方式看章节四！

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.autograd


__all__ = ['C3k2_ODConv', 'ODConv2d']


def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p


class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))


class Attention(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size=3, groups=1, reduction=0.0625, kernel_num=4, min_channel=16):
        super(Attention, self).__init__()
        attention_channel = max(int(in_planes * reduction), min_channel)
        self.kernel_size = kernel_size
        self.kernel_num = kernel_num
        self.temperature = 1.0

        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
        self.bn = nn.BatchNorm2d(attention_channel)
        self.relu = nn.ReLU(inplace=True)

        self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
        self.func_channel = self.get_channel_attention

        if in_planes == groups and in_planes == out_planes:  # depth-wise convolution
            self.func_filter = self.skip
        else:
            self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
            self.func_filter = self.get_filter_attention

        if kernel_size == 1:  # point-wise convolution
            self.func_spatial = self.skip
        else:
            self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
            self.func_spatial = self.get_spatial_attention

        if kernel_num == 1:
            self.func_kernel = self.skip
        else:
            self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
            self.func_kernel = self.get_kernel_attention

        self._initialize_weights()

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            if isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def update_temperature(self, temperature):
        self.temperature = temperature

    @staticmethod
    def skip(_):
        return 1.0

    def get_channel_attention(self, x):
        channel_attention = torch.sigmoid(self.channel_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return channel_attention

    def get_filter_attention(self, x):
        filter_attention = torch.sigmoid(self.filter_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return filter_attention

    def get_spatial_attention(self, x):
        spatial_attention = self.spatial_fc(x).view(x.size(0), 1, 1, 1, self.kernel_size, self.kernel_size)
        spatial_attention = torch.sigmoid(spatial_attention / self.temperature)
        return spatial_attention

    def get_kernel_attention(self, x):
        kernel_attention = self.kernel_fc(x).view(x.size(0), -1, 1, 1, 1, 1)
        kernel_attention = F.softmax(kernel_attention / self.temperature, dim=1)
        return kernel_attention

    def forward(self, x):
        x = self.avgpool(x)
        x = self.fc(x)
        # x = self.bn(x) # 在外面我提供了一个bn这里会报错
        x = self.relu(x)
        return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)


class ODConv2d(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=1, dilation=1, groups=1,
                 reduction=0.0625, kernel_num=4):
        super(ODConv2d, self).__init__()
        in_planes = in_planes
        self.in_planes = in_planes
        self.out_planes = out_planes
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.groups = groups
        self.kernel_num = kernel_num
        self.attention = Attention(in_planes, out_planes, kernel_size, groups=groups,
                                   reduction=reduction, kernel_num=kernel_num)
        self.weight = nn.Parameter(torch.randn(kernel_num, out_planes, in_planes // groups, kernel_size, kernel_size),
                                   requires_grad=True)
        self._initialize_weights()

        if self.kernel_size == 1 and self.kernel_num == 1:
            self._forward_impl = self._forward_impl_pw1x
        else:
            self._forward_impl = self._forward_impl_common

    def _initialize_weights(self):
        for i in range(self.kernel_num):
            nn.init.kaiming_normal_(self.weight[i], mode='fan_out', nonlinearity='relu')

    def update_temperature(self, temperature):
        self.attention.update_temperature(temperature)

    def _forward_impl_common(self, x):
        # Multiplying channel attention (or filter attention) to weights and feature maps are equivalent,
        # while we observe that when using the latter method the models will run faster with less gpu memory cost.
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        batch_size, in_planes, height, width = x.size()
        x = x * channel_attention
        x = x.reshape(1, -1, height, width)
        aggregate_weight = spatial_attention * kernel_attention * self.weight.unsqueeze(dim=0)
        aggregate_weight = torch.sum(aggregate_weight, dim=1).view(
            [-1, self.in_planes // self.groups, self.kernel_size, self.kernel_size])
        output = F.conv2d(x, weight=aggregate_weight, bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups * batch_size)
        output = output.view(batch_size, self.out_planes, output.size(-2), output.size(-1))
        output = output * filter_attention
        return output

    def _forward_impl_pw1x(self, x):
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        x = x * channel_attention
        output = F.conv2d(x, weight=self.weight.squeeze(dim=0), bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups)
        output = output * filter_attention
        return output

    def forward(self, x):
        return self._forward_impl(x)

class Bottleneck_ODConv(nn.Module):
    """Standard bottleneck."""

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
        expansion.
        """
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = ODConv2d(c1, c_, 3, 1)
        self.cv2 = Conv(c_, c2, 3, 1)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        """'forward()' applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck_ODConv(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck_ODConv(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))

    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))

class Attention_YOLOv26(nn.Module):
    """Attention module that performs self-attention on the input tensor.

    Args:
        dim (int): The input tensor dimension.
        num_heads (int): The number of attention heads.
        attn_ratio (float): The ratio of the attention key dimension to the head dimension.

    Attributes:
        num_heads (int): The number of attention heads.
        head_dim (int): The dimension of each attention head.
        key_dim (int): The dimension of the attention key.
        scale (float): The scaling factor for the attention scores.
        qkv (Conv): Convolutional layer for computing the query, key, and value.
        proj (Conv): Convolutional layer for projecting the attended values.
        pe (Conv): Convolutional layer for positional encoding.
    """

    def __init__(self, dim: int, num_heads: int = 8, attn_ratio: float = 0.5):
        """Initialize multi-head attention module.

        Args:
            dim (int): Input dimension.
            num_heads (int): Number of attention heads.
            attn_ratio (float): Attention ratio for key dimension.
        """
        super().__init__()
        self.num_heads = num_heads
        self.head_dim = dim // num_heads
        self.key_dim = int(self.head_dim * attn_ratio)
        self.scale = self.key_dim**-0.5
        nh_kd = self.key_dim * num_heads
        h = dim + nh_kd * 2
        self.qkv = Conv(dim, h, 1, act=False)
        self.proj = Conv(dim, dim, 1, act=False)
        self.pe = Conv(dim, dim, 3, 1, g=dim, act=False)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Forward pass of the Attention module.

        Args:
            x (torch.Tensor): The input tensor.

        Returns:
            (torch.Tensor): The output tensor after self-attention.
        """
        B, C, H, W = x.shape
        N = H * W
        qkv = self.qkv(x)
        q, k, v = qkv.view(B, self.num_heads, self.key_dim * 2 + self.head_dim, N).split(
            [self.key_dim, self.key_dim, self.head_dim], dim=2
        )

        attn = (q.transpose(-2, -1) @ k) * self.scale
        attn = attn.softmax(dim=-1)
        x = (v @ attn.transpose(-2, -1)).view(B, C, H, W) + self.pe(v.reshape(B, C, H, W))
        x = self.proj(x)
        return x


class PSABlock(nn.Module):
    """PSABlock class implementing a Position-Sensitive Attention block for neural networks.

    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.

    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.

    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.

    """

    def __init__(self, c: int, attn_ratio: float = 0.5, num_heads: int = 4, shortcut: bool = True) -> None:
        """Initialize the PSABlock.

        Args:
            c (int): Input and output channels.
            attn_ratio (float): Attention ratio for key dimension.
            num_heads (int): Number of attention heads.
            shortcut (bool): Whether to use shortcut connections.
        """
        super().__init__()

        self.attn = Attention_YOLOv26(c, attn_ratio=attn_ratio, num_heads=num_heads)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Execute a forward pass through PSABlock.

        Args:
            x (torch.Tensor): Input tensor.

        Returns:
            (torch.Tensor): Output tensor after attention and feed-forward processing.
        """
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x

class C3k_ODConv(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck_ODConv(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))


class C3k2_ODConv(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(
        self,
        c1: int,
        c2: int,
        n: int = 1,
        c3k: bool = False,
        e: float = 0.5,
        attn: bool = False,
        g: int = 1,
        shortcut: bool = True,
    ):
        """Initialize C3k2 modu
        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            n (int): Number of blocks.
            c3k (bool): Whether to use C3k blocks.
            e (float): Expansion ratio.
            attn (bool): Whether to use attention blocks.
            g (int): Groups for convolutions.
            shortcut (bool): Whether to use shortcut connections.
        """
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            nn.Sequential(
                Bottleneck_ODConv(self.c, self.c, shortcut, g),
                PSABlock(self.c, attn_ratio=0.5, num_heads=max(self.c // 64, 1)),
            )
            if attn
            else C3k_ODConv(self.c, self.c, 2, shortcut, g)
            if c3k
            else Bottleneck_ODConv(self.c, self.c, shortcut, g)
            for _ in range(n)
        )

if __name__ == "__main__":
    # Generating Sample image
    image_size = (1, 64, 240, 240)
    image = torch.rand(*image_size)

    # Model
    mobilenet_v1 = C3k2_ODConv(64, 64)

    out = mobilenet_v1(image)
    print(out.size())

四、在模型中调用ODConv模块

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）。

4.6 修改六

在'ultralytics/nn/tasks.py'文件内的parse_model方法函数内（位置大概在1600+行左右），按照图示位置进行代码的替换即可（此处不改如果你yaml文件中的所有C3k2都被改名了，则检测头会使用老版本的v8检测头参数量会大幅度增加，但不影响运行很多人都忽略了这一步）。

            if "C3k2" in getattr(m, "__name__", str(m)):
                legacy = False
                if scale in "mlx":
                    args[3] = True

到此就修改完成了，大家可以复制下面的yaml文件运行。

五、正式训练

5.1 yaml文件

5.1.1 yaml文件1

训练信息：YOLO26-C3K2-ODConv-3 summary: 303 layers, 2,932,515 parameters, 2,932,515 gradients, 5.9 GFLOP

其中C3k2_ODConv可以自由搭配使用或者不使用，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。

# 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. 'model=yolo26n.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, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 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_ODConv, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_ODConv, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_ODConv, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2_ODConv, [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-C3K2-ODConv-2 summary: 297 layers, 2,878,718 parameters, 2,878,718 gradients, 5.9 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. 'model=yolo26n.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_ODConv, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_ODConv, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_ODConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_ODConv, [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, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-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)

5.1.3 yaml文件3

训练信息：YOLO26-C3K2-ODConv-3 summary: 315 layers, 4,104,457 parameters, 4,104,457 gradients, 9.1 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. 'model=yolo26n.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_ODConv, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_ODConv, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_ODConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_ODConv, [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_ODConv, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_ODConv, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_ODConv, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2_ODConv, [1024, True, 0.5, True]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

5.1.4 yaml文件4

训练信息：YOLO26-ODConv summary: 296 layers, 4,605,782 parameters, 4,605,782 gradients, 4.5 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. 'model=yolo26n.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, ODConv2d, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, ODConv2d, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, ODConv2d, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, ODConv2d, [1024, 3, 2]] # 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, ODConv2d, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, ODConv2d, [512, 3, 2]]
  - [[-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)

5.2 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。

## 注意此处优化器需要使用SGD，使用MuSGD会报错.

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(
        data=r"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
                cache=False,
                imgsz=640,
                epochs=20,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=0,
                workers=0,
                device='0',
                optimizer='SGD', # using SGD/MuSGD
                # resume=, # 这里是填写last.pt地址
                amp=True,  # 如果出现训练损失为Nan可以关闭amp
                project='runs/train',
                name='exp',
                )

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

AtomGit开源社区

AtomGit 是由开放原子开源基金会联合 CSDN 等生态伙伴共同推出的新一代开源与人工智能协作平台。平台坚持“开放、中立、公益”的理念，把代码托管、模型共享、数据集托管、智能体开发体验和算力服务整合在一起，为开发者提供从开发、训练到部署的一站式体验。

更多推荐

Linux 音频子系统完整梳理：ALSA、ASoC、DAPM、Codec、Machine、es8389 与 rk‑multicodecs 全解析

本文深入解析了Linux音频子系统的核心架构，包括ALSA、ASoC、DAPM等关键组件。主要内容分为：整体架构：从用户空间接口ALSA到内核ASoC框架，再到DAPM电源管理，形成完整的音频处理链路。组件分工： ALSA提供用户接口（PCM播放/录音、Mixer控制） ASoC负责SoC音频系统集成（CPU DAI、Codec DAI、Machine驱动） DAPM实现动态电源管理核心实现