dern.py 文件源码

def attention_history(self, dL, cue, train=True):
        D = F.concat(dL, axis=0)
        D, Cue = F.broadcast(D, cue)
        S = self.m(F.tanh(self.W_dm(D) + Cue))
        S = F.softmax(F.reshape(S, (1, len(dL))))
        pre_v = F.matmul(S, D)
        return pre_v