layers.py 文件源码

def forward(self, x, y, x_mask):
        """
        x = batch * len * h1
        y = batch * h2
        x_mask = batch * len
        """
        Wy = self.linear(y) if self.linear is not None else y
        xWy = x.bmm(Wy.unsqueeze(2)).squeeze(2)
        xWy.data.masked_fill_(x_mask.data, -float('inf'))
        if self.training:
            # In training we output log-softmax for NLL
            alpha = F.log_softmax(xWy, dim=1)
        else:
            # ...Otherwise 0-1 probabilities
            alpha = F.softmax(xWy, dim=1)
        return alpha