涨点技巧:注意力机制—Yolov5/Yolov7引入CBAM、GAM、Resnet_CBAM

1.计算机视觉中的注意力机制

一般来说,注意力机制通常被分为以下基本四大类:

通道注意力 Channel Attention

空间注意力机制 Spatial Attention

时间注意力机制 Temporal Attention

分支注意力机制 Branch Attention

1.1.CBAM:通道注意力和空间注意力的集成者

轻量级的卷积注意力模块,它结合了通道和空间的注意力机制模块

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

上图可以看到,CBAM包含CAM(Channel Attention Module)和SAM(Spartial Attention Module)两个子模块,分别进行通道和空间上的Attention。这样不只能够节约参数和计算力,并且保证了其能够做为即插即用的模块集成到现有的网络架构中去。

1.2 GAM:Global Attention Mechanism

超越CBAM,全新注意力GAM:不计成本提高精度!
论文题目:Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions
论文地址:https://paperswithcode.com/paper/global-attention-mechanism-retain-information

从整体上可以看出,GAM和CBAM注意力机制还是比较相似的,同样是使用了通道注意力机制和空间注意力机制。但是不同的是对通道注意力和空间注意力的处理。
图片

1.3 ResBlock_CBAM

CBAM结构其实就是将通道注意力信息核空间注意力信息在一个block结构中进行运用。

在resnet中实现cbam:即在原始block和残差结构连接前,依次通过channel attention和spatial attention即可。

1.4性能评价

 2.Yolov5加入CBAM、GAM

2.1 CBAM加入common.py

class ChannelAttentionModule(nn.Module):  
    def __init__(self, c1, reduction=16,light=False):
        super(ChannelAttentionModule, self).__init__()
        mid_channel = c1 // reduction
        self.light=light
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        if self.light:
            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)
            )
        else:

            self.shared_MLP = nn.Conv2d(c1, c1, 1, 1, 0, bias=True)    
        self.act = nn.Sigmoid()
       
    def forward(self, x):
        if self.light: 
            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)
            fc_out=(avgout + maxout)
        else:
            fc_out=(self.shared_MLP(self.avg_pool(x)))
        return x * self.act(fc_out)
        
class SpatialAttentionModule(nn.Module): ##update:coding-style FOR LIGHTING
    def __init__(self, kernel_size=7):
        super().__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.act = nn.Sigmoid()
    def forward(self, x):
        return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))

class CBAM(nn.Module):
    def __init__(self, c1,c2,k=7):
        super().__init__()
        self.channel_attention = ChannelAttentionModule(c1)
        self.spatial_attention = SpatialAttentionModule(k)

    def forward(self, x):
        return self.spatial_attention(self.channel_attention(x))

2.2  GAM加入common.py

def channel_shuffle(x, groups=2):   ##shuffle channel 
        #RESHAPE----->transpose------->Flatten 
        B, C, H, W = x.size()
        out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous()
        out=out.view(B, C, H, W) 
        return out

class GAM_Attention(nn.Module):
   #https://paperswithcode.com/paper/global-attention-mechanism-retain-information
    def __init__(self, c1, c2, group=True,rate=4):
        super(GAM_Attention, self).__init__()
        
        self.channel_attention = nn.Sequential(
            nn.Linear(c1, int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Linear(int(c1 / rate), c1)
        )
        
        
        self.spatial_attention = nn.Sequential(
            
            nn.Conv2d(c1, c1//rate, kernel_size=7, padding=3,groups=rate)if group else nn.Conv2d(c1, int(c1 / rate), kernel_size=7, padding=3), 
            nn.BatchNorm2d(int(c1 /rate)),
            nn.ReLU(inplace=True),
            nn.Conv2d(c1//rate, c2, kernel_size=7, padding=3,groups=rate) if group else nn.Conv2d(int(c1 / rate), c2, kernel_size=7, padding=3), 
            nn.BatchNorm2d(c2)
        )

    def forward(self, x):
        
        b, c, h, w = x.shape
        x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
        x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
        x_channel_att = x_att_permute.permute(0, 3, 1, 2)
       # x_channel_att=channel_shuffle(x_channel_att,4) #last shuffle 
        x = x * x_channel_att
 
        x_spatial_att = self.spatial_attention(x).sigmoid()
        x_spatial_att=channel_shuffle(x_spatial_att,4) #last shuffle 
        out = x * x_spatial_att
        #out=channel_shuffle(out,4) #last shuffle 
        return out    

2.4 GAM加入common.py中加入common.py

class ResBlock_CBAM(nn.Module):
    def __init__(self, in_places, places, stride=1, downsampling=False, expansion=4):
        super(ResBlock_CBAM, self).__init__()
        self.expansion = expansion
        self.downsampling = downsampling

        self.bottleneck = nn.Sequential(
            nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(places),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1,
                        bias=False),
            nn.BatchNorm2d(places * self.expansion),
        )
        self.cbam = CBAM(c1=places * self.expansion, c2=places * self.expansion, )

        if self.downsampling:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride,
                            bias=False),
                nn.BatchNorm2d(places * self.expansion)
            )
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        residual = x
        out = self.bottleneck(x)
        out = self.cbam(out)
        if self.downsampling:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)
        return out

2.3 CBAM、GAM加入yolo.py

if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, C2f,CBAM,ResBlock_CBAM,GAM_Attention}:

2.4 CBAM、GAM修改对应yaml

2.4.1 修改 yolov5s_cbam.yaml

# parameters
nc: 10  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # 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, [1024,7]], #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, [256,7]],   #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, [512,7]],


   [-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, [1024,7]],     
 

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

2.4.2 修改 yolov5s_gam.yaml

# parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # 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, GAM_Attention, [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, GAM_Attention, [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, GAM_Attention, [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, GAM_Attention, [1024,1024]], #
 

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

文章出处登录后可见!

已经登录?立即刷新

共计人评分,平均

到目前为止还没有投票!成为第一位评论此文章。

(0)
xiaoxingxing的头像xiaoxingxing管理团队
上一篇 2023年5月3日
下一篇 2023年5月3日

相关推荐