YOLOv5-6.1添加注意力机制（SE、CBAM、ECA、CA）

0. 添加方法

主要步骤：
（1）在models/common.py中注册注意力模块
（2）在models/yolo.py中的parse_model函数中添加注意力模块
（3）修改配置文件yolov5s.yaml
（4）运行yolo.py进行验证
各个注意力机制模块的添加方法类似，各注意力模块的修改参照SE。
本文添加注意力完整代码：https://github.com/double-vin/yolov5_attention

1. SE

Squeeze-and-Excitation Networks
https://github.com/hujie-frank/SENet

1.1 SE

1. 在models/common.py中注册SE模块

class SE(nn.Module):
    def __init__(self, c1, c2, ratio=16):
        super(SE, self).__init__()
        #c*1*1
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.l1 = nn.Linear(c1, c1 // ratio, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.l2 = nn.Linear(c1 // ratio, c1, bias=False)
        self.sig = nn.Sigmoid()

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avgpool(x).view(b, c)
        y = self.l1(y)
        y = self.relu(y)
        y = self.l2(y)
        y = self.sig(y)
        y = y.view(b, c, 1, 1)
        return x * y.expand_as(x)

2. 在models/yolo.py中的parse_model函数中添加SE模块
   
3. 修改配置文件yolov5s.yaml。
   添加注意力的两种方法：一是在backbone的最后一层添加注意力；二是将backbone中的C3全部替换。
   这里使用第一种，第二种见下文中的C3SE
   
   注意：SE添加至第9层，第9层之后所有的编号都要+1，则：
   1>两个Concat的from系数分别由[-1, 14]，[-1, 10]改为[-1, 15]，[-1, 11]
   2>Detect的from系数由[17, 20, 23]改为[18,21,24]
   
4. 验证：运行yolo.py
   

1.2 C3-SE

1. 在models/common.py中注册C3SE模块：

class SEBottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2
        # self.se=SE(c1,c2,ratio)
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.l1 = nn.Linear(c1, c1 // ratio, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.l2 = nn.Linear(c1 // ratio, c1, bias=False)
        self.sig = nn.Sigmoid()

    def forward(self, x):
        x1 = self.cv2(self.cv1(x))
        b, c, _, _ = x.size()
        y = self.avgpool(x1).view(b, c)
        y = self.l1(y)
        y = self.relu(y)
        y = self.l2(y)
        y = self.sig(y)
        y = y.view(b, c, 1, 1)
        out = x1 * y.expand_as(x1)

        # out=self.se(x1)*x1
        return x + out if self.add else out


class C3SE(C3):
    # C3 module with SEBottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(SEBottleneck(c_, c_, shortcut) for _ in range(n)))

2. 在models/yolo.py中的parse_model函数中添加C3SE模块
   
3. 修改配置文件yolov5s.yaml。
   
4. 验证：运行yolo.py
   

2. CBAM

《CBAM: Convolutional Block Attention Module》

2.1 CBAM

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.f1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
        self.relu = nn.ReLU()
        self.f2 = nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
        max_out = self.f2(self.relu(self.f1(self.max_pool(x))))
        out = self.sigmoid(avg_out + max_out)
        return out


class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        # (特征图的大小-算子的size+2*padding)/步长+1
        self.conv = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # 1*h*w
        avg_out = torch.mean(x, dim=1, keepdim=True)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = torch.cat([avg_out, max_out], dim=1)
        #2*h*w
        x = self.conv(x)
        #1*h*w
        return self.sigmoid(x)


class CBAM(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, ratio=16, kernel_size=7):  # ch_in, ch_out, number, shortcut, groups, expansion
        super(CBAM, self).__init__()
        self.channel_attention = ChannelAttention(c1, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)

    def forward(self, x):
        out = self.channel_attention(x) * x
        # c*h*w
        # c*h*w * 1*h*w
        out = self.spatial_attention(out) * out
        return out

2.2 C3-CBAM

class CBAMBottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5,ratio=16,kernel_size=7):  # ch_in, ch_out, shortcut, groups, expansion
        super(CBAMBottleneck,self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2
        self.channel_attention = ChannelAttention(c2, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)
        #self.cbam=CBAM(c1,c2,ratio,kernel_size)

    def forward(self, x):
        x1 = self.cv2(self.cv1(x))
        out = self.channel_attention(x1) * x1
        # print('outchannels:{}'.format(out.shape))
        out = self.spatial_attention(out) * out
        return x + out if self.add else out


class C3CBAM(C3):
    # C3 module with CBAMBottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(CBAMBottleneck(c_, c_, shortcut) for _ in range(n)))

3. ECA

《ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks》
https://github.com/BangguWu/ECANet

3.1 ECA

class ECA(nn.Module):
    """Constructs a ECA module.
    Args:
        channel: Number of channels of the input feature map
        k_size: Adaptive selection of kernel size
    """

    def __init__(self, c1, c2, k_size=3):
        super(ECA, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # feature descriptor on the global spatial information
        y = self.avg_pool(x)

        # print(y.shape,y.squeeze(-1).shape,y.squeeze(-1).transpose(-1, -2).shape)
        # Two different branches of ECA module
        # 50*C*1*1
        # 50*C*1
        # 50*1*C
        y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)

        # Multi-scale information fusion
        y = self.sigmoid(y)

        return x * y.expand_as(x)

3.2 C3-ECA

class ECABottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16, k_size=3):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2
        # self.eca=ECA(c1,c2)
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x1 = self.cv2(self.cv1(x))
        # out=self.eca(x1)*x1
        y = self.avg_pool(x1)
        y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
        y = self.sigmoid(y)
        out = x1 * y.expand_as(x1)

        return x + out if self.add else out


class C3ECA(C3):
    # C3 module with ECABottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(ECABottleneck(c_, c_, shortcut) for _ in range(n)))

4. CA

Coordinate Attention for Efficient Mobile Network Design
https://github.com/Andrew-Qibin/CoordAttention

4.1 CA

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

    def forward(self, x):
        identity = x
        n, c, h, w = x.size()
        # c*1*W
        x_h = self.pool_h(x)
        # c*H*1
        # C*1*h
        x_w = self.pool_w(x).permute(0, 1, 3, 2)
        y = torch.cat([x_h, x_w], dim=2)
        # C*1*(h+w)
        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

4.2 C3-CA

class CABottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=32):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2
        # self.ca=CoordAtt(c1,c2,ratio)
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))
        mip = max(8, c1 // ratio)
        self.conv1 = nn.Conv2d(c1, mip, kernel_size=1, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()
        self.conv_h = nn.Conv2d(mip, c2, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, c2, kernel_size=1, stride=1, padding=0)
        
    def forward(self, x):
        x1=self.cv2(self.cv1(x))
        n, c, h, w = x.size()
        # c*1*W
        x_h = self.pool_h(x1)
        # c*H*1
        # C*1*h
        x_w = self.pool_w(x1).permute(0, 1, 3, 2)
        y = torch.cat([x_h, x_w], dim=2)
        # C*1*(h+w)
        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 = x1 * a_w * a_h

        # out=self.ca(x1)*x1
        return x + out if self.add else out


class C3CA(C3):
    # C3 module with CABottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(CABottleneck(c_, c_,shortcut) for _ in range(n)))

Tips：添加注意力的位置不局限，可以尝试各种排列组合
参考：
多种注意力介绍
添加注意力视频讲解
添加CBAM