p1_HierarchicalAttention_model_transformer.py 文件源码

def gru_forward_word_level(self, embedded_words):
        """
        :param embedded_words:[batch_size*num_sentences,sentence_length,embed_size]
        :return:forward hidden state: a list.length is sentence_length, each element is [batch_size*num_sentences,hidden_size]
        """
        # split embedded_words
        embedded_words_splitted = tf.split(embedded_words, self.sequence_length,
                                           axis=1)  # it is a list,length is sentence_length, each element is [batch_size*num_sentences,1,embed_size]
        embedded_words_squeeze = [tf.squeeze(x, axis=1) for x in
                                  embedded_words_splitted]  # it is a list,length is sentence_length, each element is [batch_size*num_sentences,embed_size]
        # demension_1=embedded_words_squeeze[0].get_shape().dims[0]
        h_t = tf.ones((self.batch_size * self.num_sentences,
                       self.hidden_size))  #TODO self.hidden_size h_t =int(tf.get_shape(embedded_words_squeeze[0])[0]) # tf.ones([self.batch_size*self.num_sentences, self.hidden_size]) # [batch_size*num_sentences,embed_size]
        h_t_forward_list = []
        for time_step, Xt in enumerate(embedded_words_squeeze):  # Xt: [batch_size*num_sentences,embed_size]
            h_t = self.gru_single_step_word_level(Xt,h_t)  # [batch_size*num_sentences,embed_size]<------Xt:[batch_size*num_sentences,embed_size];h_t:[batch_size*num_sentences,embed_size]
            h_t_forward_list.append(h_t)
        return h_t_forward_list  # a list,length is sentence_length, each element is [batch_size*num_sentences,hidden_size]

    # backward gru for first level: word level