class Partial_conv3(nn.Module): def __init__(self, dim, n_div, forward): super().__init__() self.dim_conv3 = dim // n_div self.dim_untouched = dim - self.dim_conv3 self.partial_conv3 = nn.Conv2d(self.dim_conv3, self.dim_conv3, 3, 1, 1, bias=False) self.global_pool = GlobalAvgPool2d() if forward == 'slicing': self.forward = self.forward_slicing elif forward == 'split_cat': self.forward = self.forward_split_cat else: raise NotImplementedError def forward_slicing(self, x: Tensor) -> Tensor: # only for inference x = x.clone() # !!! Keep the original input intact for the residual connection later x[:, :self.dim_conv3, :, :] = self.partial_conv3(x[:, :self.dim_conv3, :, :]) return x def forward_split_cat(self, x: Tensor) -> Tensor: x1, x2 = torch.split(x, [self.dim_conv3, self.dim_untouched], dim=1) x1 = self.partial_conv3(x1) x1 = self.global_pool(x1) x = torch.cat((x1, x2), 1) return x在这段代码中插入全局平均池化做通道增强的模块

你可以在forward_slicing和forward_split_cat的输出结果之前加入一个全局平均池化层进行通道增强，代码如下：

class Partial_conv3(nn.Module):
    def __init__(self, dim, n_div, forward):
        super().__init__()
        self.dim_conv3 = dim // n_div
        self.dim_untouched = dim - self.dim_conv3
        self.partial_conv3 = nn.Conv2d(self.dim_conv3, self.dim_conv3, 3, 1, 1, bias=False)
        self.global_pool = GlobalAvgPool2d()
        self.channel_enhance = nn.Sequential(
            nn.Conv2d(dim, dim, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(dim),
            nn.ReLU(inplace=True),
            self.global_pool
        )
        if forward == 'slicing':
            self.forward = self.forward_slicing
        elif forward == 'split_cat':
            self.forward = self.forward_split_cat
        else:
            raise NotImplementedError

    def forward_slicing(self, x: Tensor) -> Tensor:
        # only for inference
        x = x.clone()   # !!! Keep the original input intact for the residual connection later
        x[:, :self.dim_conv3, :, :] = self.partial_conv3(x[:, :self.dim_conv3, :, :])
        x = self.channel_enhance(x)
        return x

    def forward_split_cat(self, x: Tensor) -> Tensor:
        x1, x2 = torch.split(x, [self.dim_conv3, self.dim_untouched], dim=1)
        x1 = self.partial_conv3(x1)
        x1 = self.channel_enhance(x1)
        x = torch.cat((x1, x2), 1)
        return x

这里使用了一个nn.Sequential模块，包含了一个1x1的卷积层、BatchNorm层、ReLU激活层和全局平均池化层，对输入的特征图进行通道增强，从而提高模型的性能。在forward_slicing和forward_split_cat的输出结果之前，将输入特征图通过这个通道增强模块之后再输出。