YOLOv5改进之添加SE注意力机制的详细过程

class seC3(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super(seC3, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
        self.m = nn.Sequential(*[seBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
 
    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
 
class seBottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(seBottleneck, 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
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.l1 = nn.Linear(c1, c1 // 4, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.l2 = nn.Linear(c1 // 4, c1, bias=False)
        self.sig = nn.Sigmoid()
 
    def forward(self, x):
        x = self.cv1(x)
        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)
        x = x * y.expand_as(x)
        return x + self.cv2(x) if self.add else self.cv2(self.cv1(x))

        if m in [Conv, GhostConv, Bottleneck, Bottleneck_cot,TransformerC3,GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
                 C3,seC3]:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)
            args = [c1, c2, *args[1:]]
            if m in [BottleneckCSP, seC3]:
                args.insert(2, n)  # number of repeats
                n = 1