YOLOv5 添加CBAM注意力机制

Yaml文件配置

# parameters
nc: 10  # number of classes
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.00  # layer channel multiple

# anchors
anchors:
  #- [5,6, 7,9, 12,10]      # P2/4
  - [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]               # [c=channels,module,kernlsize,strides]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2           [c=3,64*0.5=32,3]
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, 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, 3, C3, [1024]],
   [-1, 1, CBAM, [1024,1024]], #9
   [-1, 1, SPPF, [1024,5]], #10
  ]

# 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]],  # 14

   [-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, CBAM, [256,256]],   #19


   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 15], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 22 (P4/16-medium)       [256, 256, 1, False]
   [-1, 1, CBAM, [512,512]],


   [-1, 1, Conv, [512, 3, 2]],                           #[256, 256, 3, 2]
   [[-1, 11], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 25 (P5/32-large)       [512, 512, 1, False]
   [-1, 1, CBAM, [1024,1024]],


   [[19, 23, 27], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

commom.py 配置

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