SPP的理解

SPP，通过不同池化核大小的最大池化进行特征提取，提高网络的感受野。

值得注意的是：虽然使用了不同大小的池化核，但池化前后每条分支的高宽一致，因为stride=1，padding=(kernel_size-1)/2=kerner//2

class SPPBottleneck(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_sizes=(5, 9, 13), activation="silu"):
        super().__init__()
        hidden_channels = in_channels // 2
        self.conv1      = BaseConv(in_channels, hidden_channels, 1, stride=1, act=activation)
        self.m          = nn.ModuleList([nn.MaxPool2d(kernel_size=ks, stride=1, padding=ks // 2) for ks in kernel_sizes])
        conv2_channels  = hidden_channels * (len(kernel_sizes) + 1)
        self.conv2      = BaseConv(conv2_channels, out_channels, 1, stride=1, act=activation)

    def forward(self, x):
        x = self.conv1(x)
        x = torch.cat([x] + [m(x) for m in self.m], dim=1)
        x = self.conv2(x)
        return x