深度学习实战 2 YOLOv5 添加CBAM、CA、ShuffleAttention注意力机制

目录

1. CBAM

1.1 替换C3，C3CBAM

1.1.1在Common.py中添加定义模块

1.1.2  修改yolo.py 

1.1.3 修改配置文件，yolov5s.yaml 

1.2 在backbone最后单独加入CBAM

1.2.1 在Common.py中添加定义模块

1.2.2 修改yolo.py 

1.2.3 修改配置文件，yolov5s.yaml 

2. Coordinate Attention（CA）注意力机制

2.1 在Common.py中添加定义模块

2.2 修改yolo.py 

2.3 修改配置文件，yolov5s.yaml 

3.ShuffleAttention

3.1  在Common.py中添加定义模块

3.2 修改yolo.py  

3.3 修改配置文件，yolov5s.yaml 

---

YOLOv5结合注意力机制有两种策略：

1. 注意力机制结合Bottleneck，替换backbone中的所有C3模块
2. 在backbone单独加入注意力模块

1. CBAM

论文《CBAM: Convolutional Block Attention Module》：https://arxiv.org/pdf/1807.06521.pdf 

 核心算法是：通道注意力模块（Channel Attention Module，CAM) +空间注意力模块（Spartial Attention Module，SAM) ，分别进行通道与空间上的 Attention。

1.1 替换C3，C3CBAM

1.1.1在Common.py中添加定义模块

# ---------------------------- CBAM start ---------------------------------
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):
        # 全局平均池化—>MLP两层卷积
        avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
        # 全局最大池化—>MLP两层卷积
        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
        self.conv = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # 基于channel的全局平均池化(channel=1)
        avg_out = torch.mean(x, dim=1, keepdim=True)
        # 基于channel的全局最大池化(channel=1)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        # channel拼接(channel=2)
        x = torch.cat([avg_out, max_out], dim=1)
        # channel=1
        x = self.conv(x)
        return self.sigmoid(x)

    
class CBAMBottleneck(nn.Module):
    # ch_in, ch_out, shortcut, groups, expansion, ratio, kernel_size
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16, kernel_size=7):
        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
        # 加入CBAM模块
        self.channel_attention = ChannelAttention(c2, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)
    
    def forward(self, x):
        # 考虑加入CBAM模块的位置：bottleneck模块刚开始时、bottleneck模块中shortcut之前，这里选择在shortcut之前
        x2 = self.cv2(self.cv1(x))  # x和x2的channel数相同
        # 在bottleneck模块中shortcut之前加入CBAM模块
        out = self.channel_attention(x2) * x2
        # 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)  # 引入C3(父类)的属性
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(CBAMBottleneck(c_, c_, shortcut) for _ in range(n)))


# ----------------------------- CBAM end ----------------------------------

1.1.2  修改yolo.py 

在yolo.py的parse_model函数中加入CBAMBottleneck, C3CBAM两个模块 

1.1.3 修改配置文件，yolov5s.yaml 

# YOLOv5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3CBAM, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 9, C3CBAM, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3CBAM, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, C3CBAM, [1024, False]],  # 9
  ]

1.2 在backbone最后单独加入CBAM

1.2.1 在Common.py中添加定义模块

# ---------------------------- CBAM start ---------------------------------
class ChannelAttentionModule(nn.Module):
    def __init__(self, c1, reduction=16):
        super(ChannelAttentionModule, self).__init__()
        mid_channel = c1 // reduction
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        self.shared_MLP = nn.Sequential(
            nn.Linear(in_features=c1, out_features=mid_channel),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Linear(in_features=mid_channel, out_features=c1)
        )
        self.act = nn.Sigmoid()
        #self.act=nn.SiLU()
    def forward(self, x):
        avgout = self.shared_MLP(self.avg_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
        maxout = self.shared_MLP(self.max_pool(x).view(x.size(0),-1)).unsqueeze(2).unsqueeze(3)
        return self.act(avgout + maxout)
        
class SpatialAttentionModule(nn.Module):
    def __init__(self):
        super(SpatialAttentionModule, self).__init__()
        self.conv2d = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3)
        self.act = nn.Sigmoid()
    def forward(self, x):
        avgout = torch.mean(x, dim=1, keepdim=True)
        maxout, _ = torch.max(x, dim=1, keepdim=True)
        out = torch.cat([avgout, maxout], dim=1)
        out = self.act(self.conv2d(out))
        return out

class CBAM(nn.Module):
    def __init__(self, c1,c2):
        super(CBAM, self).__init__()
        self.channel_attention = ChannelAttentionModule(c1)
        self.spatial_attention = SpatialAttentionModule()

    def forward(self, x):
        out = self.channel_attention(x) * x
        out = self.spatial_attention(out) * out
        return out
  
# ---------------------------- CBAM end ---------------------------------

1.2.2 修改yolo.py 

在models/yolo.py中的parse_model函数中添加CBAM模块

for i, (f, n, m, args) in enumerate(d['backbone'] + d['head'])，对应位置 下方只需要新增以下代码

elif m is CBAM:
    c1, c2 = ch[f], args[0]
    if c2 != no:
        c2 = make_divisible(c2 * gw, 8)
    args = [c1, c2]

1.2.3 修改配置文件，yolov5s.yaml 

注意head层数的变化

# YOLOv5 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)
   [-1, 1, CBAM, [1024]],

   [[17, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

2. Coordinate Attention（CA）注意力机制

论文《Coordinate Attention for Efficient Mobile Network Design》地址：https://arxiv.org/abs/2103.02907

核心算法：将通道注意力分解为两个并行（x和y方向）的1D特征编码过程，这两个嵌入特定方向信息的特征图分别被编码为两个注意力图，每个注意力图都捕获了输入特征图沿着一个空间方向的长程依赖。

2.1 在Common.py中添加定义模块

# ----------------------------- CABlock start ----------------------------------
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__()
        # height方向上的均值池化
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        # width方向上的均值池化
        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()
        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

# ----------------------------- CoordAtt end ----------------------------------

2.2 修改yolo.py 

在models/yolo.py中的parse_model函数中添加CA模块，并新增以下代码 

        elif m is CoordAtt:
            inp, oup, re = args[0], args[1], args[2]
            oup = make_divisible(oup * gw, 8) if oup != no else oup
            args = [inp, oup, re]

2.3 修改配置文件，yolov5s.yaml 

注意backbone层数的变化

# parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 9, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, C3, [1024, False]],  # 9
  ]

# YOLOv5 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, CoordAtt, [512]],

   [-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]],  # 18 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 15], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 21 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 24 (P5/32-large)

   [[18, 21, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

3.ShuffleAttention

来源《SA-NET: SHUFFLE ATTENTION FOR DEEP CONVOLUTIONAL NEURAL NETWORKS》

论文地址：https://arxiv.org/pdf/2102.00240.pdf

论文讲解：论文阅读之：SA-NET: SHUFFLE ATTENTION FOR DEEP CONVOLUTIONAL NEURAL NETWORKS_暖仔会飞的博客-CSDN博客文章目录AbstractIntroduction相关工作多分支网络 （multi-branch architectures）分组特征（grouped features）attention 机制（attention mechanism）Shuffle Attentionpipeline特征分组（feature grouping）channel attention（通道 attention）空间 attention（spatial attention）Aggregation代码和资源链接Abstract之https://blog.csdn.net/qq_42902997/article/details/122709326

3.1  在Common.py中添加定义模块

from torch.nn.parameter import Parameter 

# -----------------------------ShuffleAttention start ----------------------------------

class ShuffleAttention(nn.Module):

    def __init__(self, channel=512,reduction=16,G=8):
        super().__init__()
        self.G=G
        self.channel=channel
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.gn = nn.GroupNorm(channel // (2 * G), channel // (2 * G))
        self.cweight = Parameter(torch.zeros(1, channel // (2 * G), 1, 1))
        self.cbias = Parameter(torch.ones(1, channel // (2 * G), 1, 1))
        self.sweight = Parameter(torch.zeros(1, channel // (2 * G), 1, 1))
        self.sbias = Parameter(torch.ones(1, channel // (2 * G), 1, 1))
        self.sigmoid=nn.Sigmoid()


    def init_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant_(m.weight, 1)
                init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal_(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant_(m.bias, 0)


    @staticmethod
    def channel_shuffle(x, groups):
        b, c, h, w = x.shape
        x = x.reshape(b, groups, -1, h, w)
        x = x.permute(0, 2, 1, 3, 4)

        # flatten
        x = x.reshape(b, -1, h, w)

        return x

    def forward(self, x):
        b, c, h, w = x.size()
        #group into subfeatures
        x=x.view(b*self.G,-1,h,w) #bs*G,c//G,h,w

        #channel_split
        x_0,x_1=x.chunk(2,dim=1) #bs*G,c//(2*G),h,w

        #channel attention
        x_channel=self.avg_pool(x_0) #bs*G,c//(2*G),1,1
        x_channel=self.cweight*x_channel+self.cbias #bs*G,c//(2*G),1,1
        x_channel=x_0*self.sigmoid(x_channel)

        #spatial attention
        x_spatial=self.gn(x_1) #bs*G,c//(2*G),h,w
        x_spatial=self.sweight*x_spatial+self.sbias #bs*G,c//(2*G),h,w
        x_spatial=x_1*self.sigmoid(x_spatial) #bs*G,c//(2*G),h,w

        # concatenate along channel axis
        out=torch.cat([x_channel,x_spatial],dim=1)  #bs*G,c//G,h,w
        out=out.contiguous().view(b,-1,h,w)

        # channel shuffle
        out = self.channel_shuffle(out, 2)
        return out
# -----------------------------ShuffleAttention end ----------------------------------

3.2 修改yolo.py  

在models/yolo.py中的parse_model函数中添加ShuffleAttention模块，并新增以下代码

elif m is ShuffleAttention:
    c1, c2 = ch[f], args[0]
    if c2 != no:
        c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]

3.3 修改配置文件，yolov5s.yaml 

# parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 9, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, C3, [1024, False]],  # 9
  ]

# YOLOv5 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, 15], 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)
   [-1, 1, ShuffleAttention, [1024]], # 修改

   [[17, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]