【目标检测实验系列】YOLOv5模型改进：融入坐标注意力机制CA，多维度关注数据特征，高效涨点！（内含源代码，超详细改进代码流程）

自我介绍：本人硕士期间全程放养，目前成果:一篇北大核心CSCD录用,两篇中科院三区已见刊，一篇中科院四区在投。如何找创新点，如何放养过程厚积薄发，如何写中英论文，找期刊等等。本人后续会以自己实战经验详细写出来，还请大家能够点个关注和赞，收藏一下，谢谢大家。

1. 文章主要内容

本篇博客主要涉及坐标注意力机制CA结构融合到YOLOv5模型中。（通读本篇博客需要7分钟左右的时间）。

2. 详细代码改进流程

2.1 CA源代码

博主这里使用YOLOv5的C3结构与坐标注意力机制CA结合的新结构C3CA，并提供的main函数的测试代码。其源代码如下：

import torch
import torch.nn as nn


from models.common import Conv, Bottleneck


class h_sigmoid(nn.Module):
    def __init__(self, inplace=True):
        super(h_sigmoid, self).__init__()
        self.relu = nn.ReLU6(inplace=inplace)

    def forward(self, x):
        return self.relu(x + 3) / 6


class h_swish(nn.Module):
    def __init__(self, inplace=True):
        super(h_swish, self).__init__()
        self.sigmoid = h_sigmoid(inplace=inplace)

    def forward(self, x):
        return x * self.sigmoid(x)


class CoordAtt(nn.Module):
    def __init__(self, inp, reduction=32):
        super(CoordAtt, self).__init__()
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))

        mip = max(8, inp // reduction)

        self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()

        self.conv_h = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)

    def forward(self, x):
        identity = x

        n, c, h, w = x.size()
        x_h = self.pool_h(x)
        x_w = self.pool_w(x).permute(0, 1, 3, 2)

        y = torch.cat([x_h, x_w], dim=2)
        y = self.conv1(y)
        y = self.bn1(y)
        y = self.act(y)

        x_h, x_w = torch.split(y, [h, w], dim=2)
        x_w = x_w.permute(0, 1, 3, 2)

        a_h = self.conv_h(x_h).sigmoid()
        a_w = self.conv_w(x_w).sigmoid()

        out = identity * a_w * a_h

        return out

class C3CA(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1,
                 e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion #iscyy

        super(C3CA, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.CA = CoordAtt(2 * c_)
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
        # self.m = nn.Sequential(*[CB2d(c_) for _ in range(n)])
        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])

    def forward(self, x):
        out = torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1)
        out = self.CA(out) # C3 concat之后加入CA
        out = self.cv3(out)
        return out

if __name__ == '__main__':
    input = torch.randn(512, 512, 7, 7)
    pna = C3CA(512, 512)
    output = pna(input)
    print(output.shape)

2.2 建立一个yolov5-C3CA.yaml文件

注意到，这里博主直接使用C3CA代替Backbone部分的四个C3结构,另外注意nc改为自己数据集的类别数。

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 4  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8  小目标
  - [30,61, 62,45, 59,119]  # P4/16 中目标
  - [116,90, 156,198, 373,326]  # P5/32  大目标

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2  output_channel, kernel_size, stride, padding
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3CA, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3CA, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3CA, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3CA, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
  
   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]