p1_HierarchicalAttention_model_transformer.py 文件源码

def gru_backward_sentence_level(self, sentence_representation):
        """
        :param sentence_representation: [batch_size,num_sentences,hidden_size*2]
        :return:forward hidden state: a list,length is num_sentences, each element is [batch_size,hidden_size]
        """
        # split embedded_words
        sentence_representation_splitted = tf.split(sentence_representation, self.num_sentences,
                                                    axis=1)  # it is a list.length is num_sentences,each element is [batch_size,1,hidden_size*2]
        sentence_representation_squeeze = [tf.squeeze(x, axis=1) for x in
                                           sentence_representation_splitted]  # it is a list.length is num_sentences,each element is [batch_size, hidden_size*2]
        sentence_representation_squeeze.reverse()
        # demension_1 = int(tf.get_shape(sentence_representation_squeeze[0])[0])  # scalar: batch_size
        h_t = tf.ones((self.batch_size, self.hidden_size * 2))
        h_t_forward_list = []
        for time_step, Xt in enumerate(sentence_representation_squeeze):  # Xt:[batch_size, hidden_size*2]
            h_t = self.gru_single_step_sentence_level(Xt,h_t)  # h_t:[batch_size,hidden_size]<---------Xt:[batch_size, hidden_size*2]; h_t:[batch_size, hidden_size*2]
            h_t_forward_list.append(h_t)
        h_t_forward_list.reverse() #ADD 2017.06.14
        return h_t_forward_list  # a list,length is num_sentences, each element is [batch_size,hidden_size]