YOLOv5添加注意力机制

不废话，上干货！

第一步：在common.py最后面添加注意力机制类

#-----------------------------------------添加SE注意力机制---------------------------
class SE(nn.Module):
    def __init__(self, c1, c2, r=16):
        super(SE, self).__init__()
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.l1 = nn.Linear(c1, c1 // r, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.l2 = nn.Linear(c1 // r, c1, bias=False)
        self.sig = nn.Sigmoid()
    def forward(self, x):
        print(x.size())
        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)
#-----------------------------------------SE  end---------------------------

第二步：在yolo.py这里面加上需要添加的注意力机制名称

 if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, CoordAtt,CBAM,SE,ShuffleAttention,SimAM]:

第三步：复制yolo5s.yam文件改名为yolo5sSE.yam，在最后一层添加[-1, 3, SE,[1024]],后续head里的数字都得改，跟我一样就行。

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 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, SPPF, [1024, 5]],  # 9
   [-1, 3, SE,[1024]],

  ]
# 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, 15], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 11], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

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

第四步：在train.py里的parser.add_argument(‘–cfg’, type=str, default=ROOT / ‘models/yolov5sSE.yaml’, help=‘model.yaml path’) 改为yolo5sSE.yam

def parse_opt(known=False):
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5 5.0版本的pt/yolov5s.pt', help='initial weights path')
    parser.add_argument('--cfg', type=str, default=ROOT / 'models/yolov5s.yaml', help='model.yaml path')

运行train.py就完事了然后对比与添加前的检测精度是否有提升？
关注 双击 三连