class Conv(nn.Module): # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation) default_act = nn.SiLU() # default activation def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): super().__init__() self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) self.bn = nn.BatchNorm2d(c2) self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() def forward(self, x): return self.act(self.bn(self.conv(x))) def forward_fuse(self, x): return self.act(self.conv(x)) 替换成动态卷积

下面是将上述代码中的标准卷积替换成动态卷积的代码示例：

class DynamicConv(nn.Module):
    default_act = nn.SiLU() # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()
        self.dconv = nn.Conv2d(c1, c1 * k * k, kernel_size=k, stride=s, padding=p, dilation=d, groups=c1, bias=False)
        self.pwconv = nn.Conv2d(c1 * k * k, c2, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        x = self.dconv(x)
        x = self.pwconv(x)
        x = self.bn(x)
        x = self.act(x)
        return x

该代码使用了深度可分离卷积的思想，将动态卷积分解成深度卷积和逐点卷积两个部分。其中，深度卷积用于对每个通道进行卷积，而逐点卷积用于将所有通道的输出合并成最终的输出特征图。深度卷积的卷积核是动态生成的，可以根据输入特征图的大小和形状动态调整。