layers.py 文件源码

def forward(self, x, y, x_mask):
        """
        Args:
            x: batch * len * hdim1
            y: batch * hdim2
            x_mask: batch * len (1 for padding, 0 for true)
        Output:
            alpha = 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.normalize:
            if self.training:
                # In training we output log-softmax for NLL
                alpha = F.log_softmax(xWy)
            else:
                # ...Otherwise 0-1 probabilities
                alpha = F.softmax(xWy)
        else:
            alpha = xWy.exp()
        return alpha