yolov26改进 | Conv/卷积篇 | ScConv空间和通道重构卷积二次创新C3k2（包独家含网络结构图）

Snu77

365人浏览 · 2026-05-10 00:39:30

Snu77 · 2026-05-10 00:39:30 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内容是SCConv，即空间和通道重构卷积，是一种发布于2023.9月份的一个新的改进机制。它的核心创新在于能够同时处理图像的空间（形状、结构）和通道（色彩、深度）信息，这样的处理方式使得SCConv在分析图像时更加精细和高效。这种技术不仅适用于复杂场景的图像处理，还能在普通的对象检测任务中提供更高的精确度(亲测在小目标检测和正常的物体检测中都有效提点)。SCConv的这种能力，特别是在处理大量数据和复杂图像时的优势。本文通过先介绍SCConv的基本网络结构和原理当大家对该卷积有一个大概的了解，然后教大家如何将该卷积添加到自己的网络结构中（本文包独家含网络结构图）。

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

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、网络结构讲解

论文地址：官方论文地址

代码地址：官方代码地址

2.1 SCConv的主要思想

SCConv（空间和通道重构卷积）的高效卷积模块，以减少卷积神经网络（CNN）中的空间和通道冗余。SCConv旨在通过优化特征提取过程，减少计算资源消耗并提高网络性能。该模块包括两个单元：

1.空间重构单元（SRU）：SRU通过分离和重构方法来减少空间冗余。

2.通道重构单元（CRU）：CRU采用分割-变换-融合策略来减少通道冗余。

下面是SCConv的结构示意图->

下面我将分别解释这两个单元->

2.2 空间重构单元（SRU）

空间重构单元（SRU）是SCConv模块的一部分，负责减少特征在空间维度上的冗余。SRU接收输入特征，并通过以下步骤处理：

1. 组归一化（Group Normalization）：首先对输入特征进行归一化，以减少不同特征图之间的尺度差异。
2. 权重生成：通过应用归一化和激活函数，如Sigmoid，从归一化的特征图中生成权重。
3. 特征分离：根据生成的权重，对输入特征进行分离，形成多个子特征集。
4. 特征重构：最后，这些分离出来的特征集经过变换和重组，产生空间精炼的特征输出，以便进一步处理。

上图展示了空间重构单元（SRU）的架构。SRU的工作流程如下：

1. 输入特征X：首先进行组归一化（GN）处理。
2. 分离：通过一系列的权重 $eq?W_%7B1%7D$ , $eq?W_%7B2%7D$ , ..., $eq?W_%7BC%7D$ 对特征进行加权，这些权重是通过输入特征的通道 $eq?%5Cgamma_1%2C%20%5Cgamma_2%2C%20...%2C%20%5Cgamma_c$ 经过归一化和非线性激活函数（如Sigmoid）计算得到的。
3. 重构：加权后的特征被分割成两个部分 $eq?X_%7BW%7D%5E%7B1%7D$ 和 $eq?X_%7BW%7D%5E%7B2%7D$ ，然后这两部分各自经过变换，最终通过加法和拼接操作重构，得到空间精炼特征 $eq?X_%7BW%7D$ 。

总结：这个单元的设计目的是为了减少输入特征的空间冗余，从而提高卷积神经网络处理特征的效率。

2.3 通道重构单元（CRU）

通道重构单元（CRU）是SCConv模块的一部分，旨在减少卷积神经网络特征的通道冗余。CRU对经过空间重构单元（SRU）处理后的特征进一步操作，通过以下步骤减少通道冗余：

上图详细展示了通道重构单元（CRU）的架构，该单元从空间精炼特征 $ X^W $ 开始进行处理。CRU的工作流程包括以下几个步骤：

1. 分割（Split）：特征 $eq?X%5E%7BW%7D$ 被分割成两部分，通过不同比例的 $eq?%5Calpha$ 和 $eq?%281-%5Calpha%29$ 路径进行不同的1x1卷积处理。
2. 变换（Transform）：通过全局卷积（GWC）和点卷积（PWC）进一步变换这两部分特征。
3. 融合（Fuse）：两个变换后的特征 $eq?Y_%7B1%7D$ 和 $eq?Y_%7B2%7D$ 经过池化和SoftMax加权融合，形成最终的通道精炼特征 $eq?Y$ 。

总结：这种结构旨在通过细致地处理各个通道，减少不必要的信息，并提高网络的整体性能和效率。通过这一过程，CRU有效地提高了特征的表征效率，同时减少了模型的参数数量和计算成本。

三、核心代码

核心代码的使用方式看章节四！

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

__all__ = ['ScConv', 'C3k2_ScConv']

class GroupBatchnorm2d(nn.Module):
    def __init__(self, c_num: int,
                 group_num: int = 16,
                 eps: float = 1e-10
                 ):
        super(GroupBatchnorm2d, self).__init__()
        assert c_num >= group_num
        self.group_num = group_num
        self.weight = nn.Parameter(torch.randn(c_num, 1, 1))
        self.bias = nn.Parameter(torch.zeros(c_num, 1, 1))
        self.eps = eps

    def forward(self, x):
        N, C, H, W = x.size()
        x = x.view(N, self.group_num, -1)
        mean = x.mean(dim=2, keepdim=True)
        std = x.std(dim=2, keepdim=True)
        x = (x - mean) / (std + self.eps)
        x = x.view(N, C, H, W)
        return x * self.weight + self.bias


class SRU(nn.Module):
    def __init__(self,
                 oup_channels: int,
                 group_num: int = 16,
                 gate_treshold: float = 0.5,
                 torch_gn: bool = True
                 ):
        super().__init__()

        self.gn = nn.GroupNorm(num_channels=oup_channels, num_groups=group_num) if torch_gn else GroupBatchnorm2d(
            c_num=oup_channels, group_num=group_num)
        self.gate_treshold = gate_treshold
        self.sigomid = nn.Sigmoid()

    def forward(self, x):
        gn_x = self.gn(x)
        w_gamma = self.gn.weight / sum(self.gn.weight)
        w_gamma = w_gamma.view(1, -1, 1, 1)
        reweigts = self.sigomid(gn_x * w_gamma)
        # Gate
        w1 = torch.where(reweigts > self.gate_treshold, torch.ones_like(reweigts), reweigts)  # 大于门限值的设为1，否则保留原值
        w2 = torch.where(reweigts > self.gate_treshold, torch.zeros_like(reweigts), reweigts)  # 大于门限值的设为0，否则保留原值
        x_1 = w1 * x
        x_2 = w2 * x
        y = self.reconstruct(x_1, x_2)
        return y

    def reconstruct(self, x_1, x_2):
        x_11, x_12 = torch.split(x_1, x_1.size(1) // 2, dim=1)
        x_21, x_22 = torch.split(x_2, x_2.size(1) // 2, dim=1)
        return torch.cat([x_11 + x_22, x_12 + x_21], dim=1)


class CRU(nn.Module):
    '''
    alpha: 0<alpha<1
    '''

    def __init__(self,
                 op_channel: int,
                 alpha: float = 1 / 2,
                 squeeze_radio: int = 2,
                 group_size: int = 2,
                 group_kernel_size: int = 3,
                 ):
        super().__init__()
        self.up_channel = up_channel = int(alpha * op_channel)
        self.low_channel = low_channel = op_channel - up_channel
        self.squeeze1 = nn.Conv2d(up_channel, up_channel // squeeze_radio, kernel_size=1, bias=False)
        self.squeeze2 = nn.Conv2d(low_channel, low_channel // squeeze_radio, kernel_size=1, bias=False)
        # up
        self.GWC = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=group_kernel_size, stride=1,
                             padding=group_kernel_size // 2, groups=group_size)
        self.PWC1 = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=1, bias=False)
        # low
        self.PWC2 = nn.Conv2d(low_channel // squeeze_radio, op_channel - low_channel // squeeze_radio, kernel_size=1,
                              bias=False)
        self.advavg = nn.AdaptiveAvgPool2d(1)

    def forward(self, x):
        # Split
        up, low = torch.split(x, [self.up_channel, self.low_channel], dim=1)
        up, low = self.squeeze1(up), self.squeeze2(low)
        # Transform
        Y1 = self.GWC(up) + self.PWC1(up)
        Y2 = torch.cat([self.PWC2(low), low], dim=1)
        # Fuse
        out = torch.cat([Y1, Y2], dim=1)
        out = F.softmax(self.advavg(out), dim=1) * out
        out1, out2 = torch.split(out, out.size(1) // 2, dim=1)
        return out1 + out2


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 ScConv(nn.Module):
    def __init__(self,
                 op_channel: int,
                 group_num: int = 4,
                 gate_treshold: float = 0.5,
                 alpha: float = 1 / 2,
                 squeeze_radio: int = 2,
                 group_size: int = 2,
                 group_kernel_size: int = 3,
                 ):
        super().__init__()
        self.SRU = SRU(op_channel,
                       group_num=group_num,
                       gate_treshold=gate_treshold)
        self.CRU = CRU(op_channel,
                       alpha=alpha,
                       squeeze_radio=squeeze_radio,
                       group_size=group_size,
                       group_kernel_size=group_kernel_size)

    def forward(self, x):
        x = self.SRU(x)
        x = self.CRU(x)
        return x


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

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

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


class Bottleneck_ScConv(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_ = c2   # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = ScConv(c_)
        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(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(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_ScConv(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_ScConv(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))


class C3k2_ScConv(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_ScConv(self.c, self.c, shortcut, g),
                PSABlock(self.c, attn_ratio=0.5, num_heads=max(self.c // 64, 1)),
            )
            if attn
            else C3k_ScConv(self.c, self.c, 2, shortcut, g)
            if c3k
            else Bottleneck_ScConv(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 = ScConv(64)

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

四、手把手教你添加本文机制！

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）。

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，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-C3k2-ScConv-1 summary: 297 layers, 2,435,148 parameters, 2,435,148 gradients, 5.7 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_ScConv, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_ScConv, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_ScConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_ScConv, [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)

5.1.2 yaml文件2

训练信息：YOLO26-C3k2-ScConv-2 summary: 303 layers, 2,503,132 parameters, 2,503,132 gradients, 5.7 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, [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_ScConv, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_ScConv, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_ScConv, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2_ScConv, [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-ScConv-3 summary: 339 layers, 2,432,140 parameters, 2,432,140 gradients, 5.6 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_ScConv, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_ScConv, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_ScConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_ScConv, [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_ScConv, [512, True]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_ScConv, [256, True]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_ScConv, [512, True]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 1, C3k2_ScConv, [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(
        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='MuSGD', # 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

Codex CLI 小白上手指南：花 10 分钟用 AI 搓一个小游戏

AtomGit开源社区

Advanced RAG系统实战：从向量检索到智能召回的完整演进

AtomGit开源社区

【VMD-SSA-LSSVM】基于变分模态分解与麻雀优化Lssvm的负荷预测【多变量】（Matlab代码实现）

本文提出了一种结合变分模态分解（VMD）、麻雀搜索算法（SSA）和最小二乘支持向量机（LSSVM）的多变量负荷预测模型（VMD-SSA-LSSVM）。该模型通过VMD将原始负荷数据分解为不同频率的本征模态函数（IMF），降低数据的复杂性和非平稳性；利用SSA优化LSSVM的核函数参数和正则化参数，提高模型的预测精度；最后将各IMF分量的预测结果叠加，得到最终的负荷预测值。实验结果表明，VMD-SS