Attention UNet：上采样加入门控

论文题目：Attention U-Net: Learning Where to Look for the Pancreas
论文地址：https://arxiv.org/pdf/1804.03999
代码地址：https://github.com/ozan-oktay/Attention-Gated-Networks

方法：上采样阶段加了门控函数。

代码：

class Attention_block(nn.Module):
    def __init__(self,F_g,F_l,F_int):
        super(Attention_block,self).__init__()
        self.W_g = nn.Sequential(
            nn.Conv2d(F_g, F_int, kernel_size=1,stride=1,padding=0,bias=True),
            nn.BatchNorm2d(F_int)
            )
        
        self.W_x = nn.Sequential(
            nn.Conv2d(F_l, F_int, kernel_size=1,stride=1,padding=0,bias=True),
            nn.BatchNorm2d(F_int)
        )

        self.psi = nn.Sequential(
            nn.Conv2d(F_int, 1, kernel_size=1,stride=1,padding=0,bias=True),
            nn.BatchNorm2d(1),
            nn.Sigmoid()
        )
        
        self.relu = nn.ReLU(inplace=True)
        
    def forward(self,g,x):
        g1 = self.W_g(g) #1x512x64x64->conv(512，256)/B.N.->1x256x64x64
        x1 = self.W_x(x) #1x512x64x64->conv(512，256)/B.N.->1x256x64x64
        psi = self.relu(g1+x1)#1x256x64x64di
        psi = self.psi(psi)#得到权重矩阵  1x256x64x64 -> 1x1x64x64 ->sigmoid 结果到（0，1）

        return x*psi #与low-level feature相乘，将权重矩阵赋值进去

通过sigmoid来对low-level的feature加入attention。