一组向量 和 一组向量 的attention计算，pytorch实现

class GetAttentionHiddens(nn.Module):
    def __init__(self, input_size, attention_hidden_size, similarity_attention = False):
        super(GetAttentionHiddens, self).__init__()
        self.scoring = AttentionScore(input_size, attention_hidden_size, similarity_score=similarity_attention)

    def forward(self, x1, x2, x2_mask, x3=None, scores=None, return_scores=False, drop_diagonal=False):
        """
        Using x1, x2 to calculate attention score, but x1 will take back info from x3.
        If x3 is not specified, x1 will attend on x2.

        x1: [batch, len1, x1_input_size]
        x2: [batch, len2, x2_input_size]
        x2_mask: [batch, len2]

        x3: [batch, len2, x3_input_size]
        """
        if x3 is Non