yolov5加入yolov7的ELAN、MP结构

一 common.py加入代码

# yolov7改进 ------------------------------
class SiLU(nn.Module):  
    @staticmethod
    def forward(x):
        return x * torch.sigmoid(x)
    
 
class ELAN(nn.Module):
    def __init__(self, c1, c2, c3=0, n=4, e=1, ids=[-1, -3, -5, -6]):
        super(ELAN, self).__init__()
        c_ = c1//2
        
        self.ids = ids
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = nn.ModuleList(
            [Conv(c_ if i ==0 else c_, c_, 3, 1) for i in range(n)]
        )
        self.cv4 = Conv(c1*2, c2, 1, 1)

    def forward(self, x):
        x_1 = self.cv1(x)
        x_2 = self.cv2(x)
        
        x_all = [x_1, x_2]
        # [-1, -3, -5, -6] => [5, 3, 1, 0]
        for i in range(len(self.cv3)):
            x_2 = self.cv3[i](x_2)
            x_all.append(x_2)
            
        out = self.cv4(torch.cat([x_all[id] for id in self.ids], 1))
        return out

class MP(nn.Module):
    def __init__(self, k=2):
        super(MP, self).__init__()
        self.m = nn.MaxPool2d(kernel_size=k, stride=k)

    def forward(self, x):
        return self.m(x)
    
class M_P(nn.Module):
    def __init__(self, c1, c2):
        super(M_P, self).__init__()
        c_=c2//2
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 2)
        
        self.mp  = MP()

    def forward(self, x):
        # 160, 160, 256 => 80, 80, 256 => 80, 80, 128
        x_1 = self.mp(x)
        x_1 = self.cv1(x_1)
        
        # 160, 160, 256 => 160, 160, 128 => 80, 80, 128
        x_2 = self.cv2(x)
        x_2 = self.cv3(x_2)
        
        # 80, 80, 128 cat 80, 80, 128 => 80, 80, 256
        return torch.cat([x_2, x_1], 1)
# yolov7改进 ------------------------------

二、 yolo.py的parse_model函数加入M_P、ELAN

        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
        if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, C2f, SE, CBAM, ECA, CoordAtt
                , GSConv, VoVGSCSP, VoVGSCSPC,MHSA,BoT3, M_P, ELAN}:

三、修改配置文件

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license

# Parameters
nc: 6  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
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 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, 3, ELAN, [256]],
   [-1, 1, M_P, [512]],  # 5-P4/16
   [-1, 3, ELAN, [512]],
   [-1, 1, M_P, [1024]],  # 7-P5/32  
   [-1, 3, ELAN, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# 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, 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)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]