YOLO11改进|注意力机制篇|引入MLCA轻量级注意力机制

如果能为勤奋颁奖

于 2024-10-01 20:22:14 发布

阅读量481

点赞数 8

分类专栏： YOLOv11改进专栏文章标签： YOLO

本文链接：https://blog.csdn.net/A1983Z/article/details/142673128

版权

YOLOv11改进专栏专栏收录该内容

4 篇文章 0 订阅

订阅专栏

在这里插入图片描述

一、MLCA注意力机制

1.1MLCA注意力介绍

在这里插入图片描述

MLCA（Multi-Level Channel Attention，多级通道注意力）是一种用于提升卷积神经网络（CNN）性能的注意力机制，主要通过在多个层次上捕捉不同通道间的依赖关系，来增强网络对重要特征的关注。MLCA的工作流程：

特征提取：首先，输入图像经过卷积网络的多层卷积提取出多层次的特征图，这些特征图代表了从不同尺度和不同深度捕捉到的特征信息。
通道权重计算：在每个层次的特征图上，MLCA 分别计算出每个通道的重要性权重，使用类似 SE 模块的全局池化操作得到全局特征表示，然后通过一系列非线性操作（如全连接、激活函数）生成通道权重。
多级加权：通过通道权重对各层次的特征图进行加权操作，增强重要特征通道的响应，抑制无关或冗余的特征。
融合与输出：对不同层次的特征进行融合，形成最终的特征表达，然后将其传递给后续的网络模块（如分类器或检测头）。
工作流程图如下所示：

1.2MLCA核心代码

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
 
 
class MLCA(nn.Module):
    def __init__(self, in_size, local_size=5, gamma=2, b=1, local_weight=0.5):
        super(MLCA, self).__init__()
 
        # ECA 计算方法
        self.local_size = local_size
        self.gamma = gamma
        self.b = b
        t = int(abs(math.log(in_size, 2) + self.b) / self.gamma)  # eca  gamma=2
        k = t if t % 2 else t + 1
 
        self.conv = nn.Conv1d(1, 1, kernel_size=k, padding=(k - 1) // 2, bias=False)
        self.conv_local = nn.Conv1d(1, 1, kernel_size=k, padding=(k - 1) // 2, bias=False)
 
        self.local_weight = local_weight
 
        self.local_arv_pool = nn.AdaptiveAvgPool2d(local_size)
        self.global_arv_pool = nn.AdaptiveAvgPool2d(1)
 
    def forward(self, x):
        local_arv = self.local_arv_pool(x)
        global_arv = self.global_arv_pool(local_arv)
 
        b, c, m, n = x.shape
        b_local, c_local, m_local, n_local = local_arv.shape
 
        # (b,c,local_size,local_size) -> (b,c,local_size*local_size)-> (b,local_size*local_size,c)-> (b,1,local_size*local_size*c)
        temp_local = local_arv.view(b, c_local, -1).transpose(-1, -2).reshape(b, 1, -1)
        temp_global = global_arv.view(b, c, -1).transpose(-1, -2)
 
        y_local = self.conv_local(temp_local)
        y_global = self.conv(temp_global)
 
        # (b,c,local_size,local_size) <- (b,c,local_size*local_size)<-(b,local_size*local_size,c) <- (b,1,local_size*local_size*c)
        y_local_transpose = y_local.reshape(b, self.local_size * self.local_size, c).transpose(-1, -2).view(b, c,
                                                                                                            self.local_size,
                                                                                                            self.local_size)
        # y_global_transpose = y_global.view(b, -1).transpose(-1, -2).unsqueeze(-1)
        y_global_transpose = y_global.view(b, -1).unsqueeze(-1).unsqueeze(-1)  # 代码修正
        # print(y_global_transpose.size())
        # 反池化
        att_local = y_local_transpose.sigmoid()
        att_global = F.adaptive_avg_pool2d(y_global_transpose.sigmoid(), [self.local_size, self.local_size])
        # print(att_local.size())
        # print(att_global.size())
        att_all = F.adaptive_avg_pool2d(att_global * (1 - self.local_weight) + (att_local * self.local_weight), [m, n])
        # print(att_all.size())
        x = x * att_all
        return x
 
 
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 C2f_MLCA(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
 
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
        expansion.
        """
        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 Bottleneck(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 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
        self.MLCA = MLCA(c2)
 
    def forward(self, x):
        """'forward()' applies the YOLO FPN to input data."""
        return x + self.MLCA(self.cv2(self.cv1(x))) if self.add else self.MLCA(self.cv2(self.cv1(x)))
 
 
if __name__ == "__main__":
    attention = MLCA(in_size=64)
    inputs = torch.randn((2, 55, 16, 16))
    result = attention(inputs)
    print(result.shape)

五、添加MLCA注意力机制

5.1STEP1

首先找到ultralytics/nn文件路径下新建一个Add-module的python文件包【这里注意一定是python文件包，新建后会自动生成_init_.py】，如果已经跟着我的教程建立过一次了可以省略此步骤，随后新建一个MLCA.py文件并将上文中提到的注意力机制的代码全部粘贴到此文件中，如下图所示在这里插入图片描述

5.2STEP2

在STEP1中新建的_init_.py文件中导入增加改进模块的代码包如下图所示在这里插入图片描述

5.3STEP3

找到ultralytics/nn文件夹中的task.py文件，在其中按照下图添加在这里插入图片描述

5.4STEP4

定位到ultralytics/nn文件夹中的task.py文件中的def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)函数添加如图代码,【如果不好定位可以直接ctrl+f搜索定位】

在这里插入图片描述

六、yaml文件与运行

6.1yaml文件

以下是添加MLCA注意力机制在Backbone中的yaml文件，大家可以注释自行调节，效果以自己的数据集结果为准

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n 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]] # 9
  - [-1, 1, MLCA, []]
  - [-1, 2, C2PSA, [1024]] # 11

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 14

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 17 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 14], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 20 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 11], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 23 (P5/32-large)

  - [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)