YOLOv9改进策略 | 添加注意力篇 | 挤压和激励单元SENetV2助力YOLOv9细节涨点（全网独家首发）

  • 开发
  • 12

  一、本文介绍

本文给大家带来的改进机制是SENetV2，其是一种通过调整卷积网络中的通道关系来提升性能的网络结构。SENet并不是一个独立的网络模型，而是一个可以和现有的任何一个模型相结合的模块(可以看作是一种通道型的注意力机制但是相对于SENetV1来说V2又在全局的角度进行了考虑)。在SENet中，所谓的挤压和激励（Squeeze-and-Excitation）操作是作为一个单元添加到传统的卷积网络结构中，亲测大中小三中目标检测上都有一定程度的涨点效果。同时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。同时本专栏目前改进基于yolov9.yaml文件，后期如果官方放出轻量化版本，专栏内所有改进也会同步更新，请大家放心，本文提供三种使用方式，下面图片为yaml1对应的结构图。

专栏地址：YOLOv9有效涨点专栏-持续复现各种顶会内容-有效涨点-全网改进最全的专栏 

目录

  一、本文介绍

 二、SENetV2框架原理

三、SENetV2核心代码

四、手把手教你添加SENetV2网络结构

4.1 细节修改教程

4.1.1 修改一

​4.1.2 修改二

 4.1.3 修改三 

4.1.4 修改四

4.2 SENetV2的yaml文件

4.2.1 SENetV2的yaml文件一

4.2.2 SENetV2的yaml文件二

4.2.3 SENetV2的yaml文件三

4.3 SENetV2运行成功截图

五、本文总结 

 二、SENetV2框架原理

​

​

论文地址：官方论文地址点击即可跳转

代码地址：官方代码地址点击即可跳转

​

​

SENetV2介绍了一种改进的SENet架构，该架构通过引入一种称为Squeeze aggregated excitation（SaE）的新模块来提升网络的表征能力。这个模块结合了挤压和激励(SENetV1)操作，通过多分支全连接层增强了网络的全局表示学习。在基准数据集上的实验结果证明了SENetV2模型相较于现有模型在分类精度上的显著提升。这一架构尤其强调在仅略微增加模型参数的情况下，如何有效地提高模型的性能。 

挤压和激励模块大家可以看我发的SENetV1文章里面有介绍。

​

图中展示了三种不同的神经网络模块对比：

a) ResNeXt模块：采用多分支CNN结构，不同分支的特征图通过卷积操作处理后合并（concatenate），再进行额外的卷积操作。

b) SENet模块：标准卷积操作后，利用全局平均池化来挤压特征，然后通过两个尺寸为1x1的全连接层（FC）和Sigmoid激活函数来获取通道权重，最后对卷积特征进行缩放（Scale）。

c) SENetV2模块：结合了ResNeXt和SENet的特点，采用多分支全连接层（FC）来挤压和激励操作，最后进行特征缩放。

其中SENetV2的设计旨在通过多分支结构进一步提升特征表达的精细度和全局信息的整合能力。

前面我们提到了SaE，就是SENetV2相对于SENetV1的主要改进机制，下面的图片介绍了其内部工作原理。

​

SENet V2中所提出的SaE（Squeeze-and-Excitation）模块的内部工作机制。挤压输出后，被输入到多分支的全连接（FC）层，然后进行激励过程。分割的输入在最后被传递以恢复其原始形状。这种设计能够让网络更有效地学习到输入数据的不同特征，并且在进行特征转换时考虑到不同通道之间的相互依赖性。 

三、SENetV2核心代码

下面的代码是SENetV2的核心代码，我们将其复制导'ultralytics/nn/modules'目录下，在其中创建一个文件，我这里起名为SENetV2然后粘贴进去，其余使用方式看章节四。

import torch
from torch import nn
import numpy as np

__all__ = ['SELayerV2', 'RepNCSPELAN4_SENetV2' ]


class SELayerV2(nn.Module):
    def __init__(self, in_channel, reduction=32):
        super(SELayerV2, self).__init__()
        assert in_channel >= reduction and in_channel % reduction == 0, 'invalid in_channel in SaElayer'
        self.reduction = reduction
        self.cardinality = 4
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        # cardinality 1
        self.fc1 = nn.Sequential(
            nn.Linear(in_channel, in_channel // self.reduction, bias=False),
            nn.ReLU(inplace=True)
        )
        # cardinality 2
        self.fc2 = nn.Sequential(
            nn.Linear(in_channel, in_channel // self.reduction, bias=False),
            nn.ReLU(inplace=True)
        )
        # cardinality 3
        self.fc3 = nn.Sequential(
            nn.Linear(in_channel, in_channel // self.reduction, bias=False),
            nn.ReLU(inplace=True)
        )
        # cardinality 4
        self.fc4 = nn.Sequential(
            nn.Linear(in_channel, in_channel // self.reduction, bias=False),
            nn.ReLU(inplace=True)
        )

        self.fc = nn.Sequential(
            nn.Linear(in_channel // self.reduction * self.cardinality, in_channel, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y1 = self.fc1(y)
        y2 = self.fc2(y)
        y3 = self.fc3(y)
        y4 = self.fc4(y)
        y_concate = torch.cat([y1, y2, y3, y4], dim=1)
        y_ex_dim = self.fc(y_concate).view(b, c, 1, 1)

        return x * y_ex_dim.expand_as(x)


class RepConvN(nn.Module):
    """RepConv is a basic rep-style block, including training and deploy status
    This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    """
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

        self.bn = None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

    def forward_fuse(self, x):
        """Forward process"""
        return self.act(self.conv(x))

    def forward(self, x):
        """Forward process"""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)

    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _avg_to_3x3_tensor(self, avgp):
        channels = self.c1
        groups = self.g
        kernel_size = avgp.kernel_size
        input_dim = channels // groups
        k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
        k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
        return k

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        if branch is None:
            return 0, 0
        if isinstance(branch, Conv):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def fuse_convs(self):
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')

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):
        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):
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        return self.act(self.conv(x))


class RepNBottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = RepConvN(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):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class RepNCSP(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        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(*(RepNBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))


class RepNCSPELAN4_SENetV2(nn.Module):
    # csp-elan
    def __init__(self, c1, c2, c3, c4, c5=1):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        self.c = c3//2
        self.cv1 = Conv(c1, c3, 1, 1)
        self.cv2 = nn.Sequential(RepNCSP(c3//2, c4, c5), SELayerV2(c4), Conv(c4, c4, 3, 1))
        self.cv3 = nn.Sequential(RepNCSP(c4, c4, c5), SELayerV2(c4), Conv(c4, c4, 3, 1))
        self.cv4 = Conv(c3+(2*c4), c2, 1, 1)

    def forward(self, x):
        y = list(self.cv1(x).chunk(2, 1))
        y.extend((m(y[-1])) for m in [self.cv2, self.cv3])
        return self.cv4(torch.cat(y, 1))

    def forward_split(self, x):
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in [self.cv2, self.cv3])
        return self.cv4(torch.cat(y, 1))

if __name__ == '__main__':
    x1 = torch.randn(1, 32, 16, 16)
    x2 = torch.randn(1, 32, 16, 16)
    model = RepNCSPELAN4_SENetV2(32, 32, 32, 32)
    x = model(x1)
    print(x.shape)

四、手把手教你添加SENetV2网络结构

4.1 细节修改教程

4.1.1 修改一

我们找到如下的目录'yolov9-main/models'在这个目录下创建一个文件目录(注意是目录，因为我这个专栏会出很多的更新，这里用一种一劳永逸的方法)文件目录起名modules，然后在下面新建一个文件，将我们的代码复制粘贴进去。

​

​

​4.1.2 修改二

然后新建一个__init__.py文件，然后我们在里面添加一行代码。注意标记一个'.'其作用是标记当前目录。

​

​

 4.1.3 修改三 

然后我们找到如下文件''models/yolo.py''在开头的地方导入我们的模块按照如下修改->

(如果你看了我多个改进机制此处只需要添加一个即可，无需重复添加)

注意的添加位置要放在common的导入上面！！！！！

​​​​​

4.1.4 修改四

然后我们找到parse_model方法，按照如下修改->

​

到此就修改完成了，复制下面的ymal文件即可运行。

4.2 SENetV2的yaml文件

4.2.1 SENetV2的yaml文件一

下面的配置文件为我修改的SENetV2的位置，参数的位置里面什么都不用添加空着就行，大家复制粘贴我的就可以运行，同时我提供多个版本给大家，根据我的经验可能涨点的位置。

# YOLOv9

# parameters
nc: 80  # number of classes
depth_multiple: 1  # model depth multiple
width_multiple: 1  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3

# YOLOv9 backbone
backbone:
  [
   [-1, 1, Silence, []],
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]],  # 3
   # conv down
   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 5
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 7
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 8-P5/32
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 9
  ]

# YOLOv9 head
head:
  [
   [-1, 1, SELayerV2, []],  # 添加一行我们的改进机制
   # elan-spp block
   [-1, 1, SPPELAN, [512, 256]],  # 11

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 14

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P3

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]],  # 17 (P3/8-small)

   # conv-down merge
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 20 (P4/16-medium)

   # conv-down merge
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 11], 1, Concat, [1]],  # cat head P5

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 23 (P5/32-large)
   
   # routing
   [5, 1, CBLinear, [[256]]], # 24
   [7, 1, CBLinear, [[256, 512]]], # 25
   [9, 1, CBLinear, [[256, 512, 512]]], # 26
   
   # conv down
   [0, 1, Conv, [64, 3, 2]],  # 27-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 28-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]],  # 29

   # conv down fuse
   [-1, 1, Conv, [256, 3, 2]],  # 30-P3/8
   [[24, 25, 26, -1], 1, CBFuse, [[0, 0, 0]]], # 31

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 32

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 33-P4/16
   [[25, 26, -1], 1, CBFuse, [[1, 1]]], # 34

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 35

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 36-P5/32
   [[26, -1], 1, CBFuse, [[2]]], # 37

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 38

   # detect
   [[32, 35, 38, 17, 20, 23], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]

4.2.2 SENetV2的yaml文件二

# YOLOv9

# parameters
nc: 80  # number of classes
depth_multiple: 1  # model depth multiple
width_multiple: 1  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3

# YOLOv9 backbone
backbone:
  [
   [-1, 1, Silence, []],
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]],  # 3
   # conv down
   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 5
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 7
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 8-P5/32
   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 9
  ]

# YOLOv9 head
head:
  [
   # elan-spp block
   [-1, 1, SPPELAN, [512, 256]],  # 10

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 13

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P3

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]],  # 16 (P3/8-small)
   [-1, 1, SELayerV2, []],  # 17 添加一行我们的改进机制

   # conv-down merge
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 20 (P4/16-medium)
   [-1, 1, SELayerV2, []],  # 21 添加一行我们的改进机制

   # conv-down merge
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 24 (P5/32-large)
   [-1, 1, SELayerV2, []],  # 25 添加一行我们的改进机制

   # routing
   [5, 1, CBLinear, [[256]]], # 26
   [7, 1, CBLinear, [[256, 512]]], # 27
   [9, 1, CBLinear, [[256, 512, 512]]], # 28
   
   # conv down
   [0, 1, Conv, [64, 3, 2]],  # 29-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 30-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]],  # 31

   # conv down fuse
   [-1, 1, Conv, [256, 3, 2]],  # 32-P3/8
   [[26, 27, 28, -1], 1, CBFuse, [[0, 0, 0]]], # 33

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 34
   [-1, 1, SELayerV2, []],  # 35 添加一行我们的改进机制

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 36-P4/16
   [[27, 28, -1], 1, CBFuse, [[1, 1]]], # 37

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 38
   [-1, 1, SELayerV2, []],  # 39 添加一行我们的改进机制

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 40-P5/32
   [[28, -1], 1, CBFuse, [[2]]], # 41

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 42
   [-1, 1, SELayerV2, []],  # 43 添加一行我们的改进机制

   # detect
   [[35, 39, 43, 17, 21, 25], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]

4.2.3 SENetV2的yaml文件三

注意此版本的我再大目标，小目标，中目标三个曾的后面添加了一个注意力机制，此版本需要显存较大，可以根据自己的需求增删，如果修改大家要注意修改Detect里面的检测层数。

# YOLOv9

# parameters
nc: 80  # number of classes
depth_multiple: 1  # model depth multiple
width_multiple: 1  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3

# YOLOv9 backbone
backbone:
  [
   [-1, 1, Silence, []],
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
   # elan-1 block
   [-1, 1, RepNCSPELAN4_SENetV2, [256, 128, 64, 1]],  # 3
   # conv down
   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 256, 128, 1]],  # 5
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 7
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 8-P5/32
   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 9
  ]

# YOLOv9 head
head:
  [
   # elan-spp block
   [-1, 1, SPPELAN, [512, 256]],  # 10

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 13

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P3

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [256, 256, 128, 1]],  # 16 (P3/8-small)

   # conv-down merge
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 19 (P4/16-medium)

   # conv-down merge
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 22 (P5/32-large)
   
   # routing
   [5, 1, CBLinear, [[256]]], # 23
   [7, 1, CBLinear, [[256, 512]]], # 24
   [9, 1, CBLinear, [[256, 512, 512]]], # 25
   
   # conv down
   [0, 1, Conv, [64, 3, 2]],  # 26-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 27-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4_SENetV2, [256, 128, 64, 1]],  # 28

   # conv down fuse
   [-1, 1, Conv, [256, 3, 2]],  # 29-P3/8
   [[23, 24, 25, -1], 1, CBFuse, [[0, 0, 0]]], # 30  

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 256, 128, 1]],  # 31

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 32-P4/16
   [[24, 25, -1], 1, CBFuse, [[1, 1]]], # 33 

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 34

   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 35-P5/32
   [[25, -1], 1, CBFuse, [[2]]], # 36

   # elan-2 block
   [-1, 1, RepNCSPELAN4_SENetV2, [512, 512, 256, 1]],  # 37

   # detect
   [[31, 34, 37, 16, 19, 22], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]

4.3 SENetV2运行成功截图

附上我的运行记录确保我的教程是可用的。 

​

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YOLOv5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，目前本专栏免费阅读(暂时，大家尽早关注不迷路~)，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~

专栏地址：YOLOv9有效涨点专栏-持续复现各种顶会内容-有效涨点-全网改进最全的专栏 

​

阅读全部

相关推荐

  3. YOLOv8改进 | 融合改进篇 | CCFM + Dyhead完美融合突破极限涨点 (全网独家首发)

    2024-04-21 04:50:04       38 阅读

  4. YOLOv5改进 | 融合改进篇 | CCFM + Dyhead完美融合突破极限涨点 (全网独家首发)

    2024-04-21 04:50:04       27 阅读

最近更新

  4. TCP协议是安全的吗?

    2024-04-21 04:50:04       18 阅读

  12. 阿里云服务器执行yum，一直下载docker-ce-stable失败

    2024-04-21 04:50:04       19 阅读

  13. 【Python教程】压缩PDF文件大小

    2024-04-21 04:50:04       18 阅读

  18. 通过文章id递归查询所有评论（xml）

    2024-04-21 04:50:04       20 阅读

热门阅读

  2. c 贪吃蛇的实现

    2024-04-21 04:50:04       11 阅读

  5. 通过实例学C#之Random类

    2024-04-21 04:50:04       14 阅读

  7. Bezout定理

    2024-04-21 04:50:04       16 阅读

  13. Proxmox VE (PVE) 教学 (1) | 介绍与安装

    2024-04-21 04:50:04       35 阅读

  15. 深入解析Python装饰器：从基础到高级应用，掌握代码功能增强的强大工具

    2024-04-21 04:50:04       13 阅读

  20. 基于springboot的工程教育认证的计算机课程管理平台源码数据库

    2024-04-21 04:50:04       17 阅读

  21. git本地提交记录 删除后如何找回

    2024-04-21 04:50:04       15 阅读

  23. 使用 vllm 运行 Llama3-8b-Instruct

    2024-04-21 04:50:04       14 阅读

  24. 【MySQL面试题pro版-13】

    2024-04-21 04:50:04       12 阅读

  25. 2022 E3 算法题第一题（Banana Count in A Given Letters）

    2024-04-21 04:50:04       14 阅读

  26. C++ 抽象

    2024-04-21 04:50:04       13 阅读