a3_entity_network.py 文件源码

def rnn_story(self):
        """
        run rnn for story to get last hidden state
        input is:  story:                 [batch_size,story_length,embed_size]
        :return:   last hidden state.     [batch_size,embed_size]
        """
        # 1.split input to get lists.
        input_split=tf.split(self.story_embedding,self.story_length,axis=1) #a list.length is:story_length.each element is:[batch_size,1,embed_size]
        input_list=[tf.squeeze(x,axis=1) for x in input_split]           #a list.length is:story_length.each element is:[batch_size,embed_size]
        # 2.init keys(w_all) and values(h_all) of memory
        h_all=tf.get_variable("hidden_states",shape=[self.block_size,self.dimension],initializer=self.initializer)# [block_size,hidden_size]
        w_all=tf.get_variable("keys",          shape=[self.block_size,self.dimension],initializer=self.initializer)# [block_size,hidden_size]
        # 3.expand keys and values to prepare operation of rnn
        w_all_expand=tf.tile(tf.expand_dims(w_all,axis=0),[self.batch_size,1,1]) #[batch_size,block_size,hidden_size]
        h_all_expand=tf.tile(tf.expand_dims(h_all,axis=0),[self.batch_size,1,1]) #[batch_size,block_size,hidden_size]
        # 4. run rnn using input with cell.
        for i,input in enumerate(input_list):
            h_all_expand=self.cell(input,h_all_expand,w_all_expand,i) #w_all:[batch_size,block_size,hidden_size]; h_all:[batch_size,block_size,hidden_size]
        return h_all_expand #[batch_size,block_size,hidden_size]