对 Tensorflow 中的多层双向 RNN 感到困惑

Posted 2023-02-16

【中文标题】对 Tensorflow 中的多层双向 RNN 感到困惑

【英文标题】：Confused about multi-layered Bidirectional RNN in Tensorflow

【发布时间】：2019-01-25 18:45:24

【问题描述】：

我正在使用 Tensorflow 构建一个多层双向 RNN。不过我对实现有点困惑。

我已经构建了两个创建多层双向 RNN 的函数，第一个可以正常工作，但我不确定它的预测，因为它作为单向多层 RNN 执行。下面是我的实现：

def encoding_layer_old(rnn_inputs, rnn_size, num_layers, keep_prob, 
                   source_sequence_length, source_vocab_size, 
                   encoding_embedding_size):
    """
    Create encoding layer
    :param rnn_inputs: Inputs for the RNN
    :param rnn_size: RNN Size
    :param num_layers: Number of layers
    :param keep_prob: Dropout keep probability
    :param source_sequence_length: a list of the lengths of each sequence in the batch
    :param source_vocab_size: vocabulary size of source data
    :param encoding_embedding_size: embedding size of source data
    :return: tuple (RNN output, RNN state)
    """
    # Encoder embedding
    enc_embed = tf.contrib.layers.embed_sequence(rnn_inputs, source_vocab_size, encoding_embedding_size)
    
    def create_cell_fw(rnn_size):
        with tf.variable_scope("create_cell_fw"):
            lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size,initializer=tf.random_uniform_initializer(-0.1,0.1,seed=2), reuse=False)
            drop = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
        return drop
    def create_cell_bw(rnn_size):
        with tf.variable_scope("create_cell_bw"):
            lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size,initializer=tf.random_uniform_initializer(-0.1,0.1,seed=2), reuse=False)
            drop = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
        return drop    
    
    
    enc_cell_fw = tf.contrib.rnn.MultiRNNCell([create_cell_fw(rnn_size) for _ in range(num_layers)])
    enc_cell_bw = tf.contrib.rnn.MultiRNNCell([create_cell_bw(rnn_size) for _ in range(num_layers)])
    ((encoder_fw_outputs, encoder_bw_outputs),(encoder_fw_final_state,encoder_bw_final_state)) = tf.nn.bidirectional_dynamic_rnn(enc_cell_fw,enc_cell_bw, enc_embed, 
                                                        sequence_length=source_sequence_length,dtype=tf.float32)
    encoder_outputs = tf.concat([encoder_fw_outputs, encoder_bw_outputs], 2)
    print(encoder_outputs)
    #encoder_final_state_c=[]#tf.Variable([num_layers] , dtype=tf.int32)
    #encoder_final_state_h=[]#tf.Variable([num_layers] , dtype=tf.int32)
    encoder_final_state = ()
    for x in range((num_layers)):
        encoder_final_state_c=tf.concat((encoder_fw_final_state[x].c, encoder_bw_final_state[x].c), 1)#tf.stack(tf.concat((encoder_fw_final_state[x].c, encoder_bw_final_state[x].c), 1))
        encoder_final_state_h=tf.concat((encoder_fw_final_state[x].h, encoder_bw_final_state[x].h), 1)# tf.stack(tf.concat((encoder_fw_final_state[x].h, encoder_bw_final_state[x].h), 1))
        encoder_final_state =encoder_final_state+ (tf.contrib.rnn.LSTMStateTuple(c=encoder_final_state_c,h=encoder_final_state_h),)
    
    #encoder_final_state = tf.contrib.rnn.LSTMStateTuple(c=encoder_final_state_c,h=encoder_final_state_h)
    print('before')
    print(encoder_fw_final_state)
    return encoder_outputs, encoder_final_state

  

我找到了另一个实现here，如下所示：

t

def encoding_layer(rnn_inputs, rnn_size, num_layers, keep_prob, 
                   source_sequence_length, source_vocab_size, 
                   encoding_embedding_size):
    """
    Create encoding layer
    :param rnn_inputs: Inputs for the RNN
    :param rnn_size: RNN Size
    :param num_layers: Number of layers
    :param keep_prob: Dropout keep probability
    :param source_sequence_length: a list of the lengths of each sequence in the batch
    :param source_vocab_size: vocabulary size of source data
    :param encoding_embedding_size: embedding size of source data
    :return: tuple (RNN output, RNN state)
    """
    # Encoder embedding
    enc_embed = tf.contrib.layers.embed_sequence(rnn_inputs, source_vocab_size, encoding_embedding_size)
    
    def create_cell_fw(rnn_size,x):
        with tf.variable_scope("create_cell_fw_"+str(x)):
            lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size,initializer=tf.random_uniform_initializer(-0.1,0.1,seed=2) , reuse=tf.AUTO_REUSE )
            drop = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
        return drop
    def create_cell_bw(rnn_size,x):
        with tf.variable_scope("create_cell_bw_"+str(x)):
            lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size,initializer=tf.random_uniform_initializer(-0.1,0.1,seed=2) ,reuse=tf.AUTO_REUSE )
            drop = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=keep_prob)
        return drop
    enc_cell_fw = [create_cell_fw(rnn_size,x) for x in range(num_layers)]
    enc_cell_bw = [create_cell_bw(rnn_size,x) for x in range(num_layers)]
    
    output=enc_embed
    for n in range(num_layers):
            cell_fw = enc_cell_fw[n]
            cell_bw = enc_cell_bw[n]
            state_fw = cell_fw.zero_state(batch_size, tf.float32)
            state_bw = cell_bw.zero_state(batch_size, tf.float32)
            
            ((output_fw, output_bw),(encoder_fw_final_state,encoder_bw_final_state))= tf.nn.bidirectional_dynamic_rnn(cell_fw, cell_bw, output,source_sequence_length,
                                                              state_fw, state_bw, dtype=tf.float32)

            output = tf.concat([output_fw, output_bw], axis=2)
            final_state=tf.concat([encoder_fw_final_state,encoder_bw_final_state], axis=2 )
    return output , final_state

这个实现的问题是我得到一个形状错误：

Trying to share variable bidirectional_rnn/fw/lstm_cell/kernel, but specified shape (168, 224) and found shape (256, 224).

似乎其他人在创建 RNN 单元格时也遇到过类似的情况，解决方案是使用 MultiRNNCell 来创建分层单元格。但是如果使用 MultiRNNCell 我将无法使用第二个实现，因为 multiRNNCell 不支持索引。因此，我将无法遍历单元列表并创建多个 RNN。

非常感谢您在这方面的帮助。

我使用的是 tensorflow 1.3

【参考方案1】：

这两个代码确实看起来有点过于复杂。无论如何，我尝试了一个更简单的版本并且它有效。在您的代码中，尝试从create_cell_fw 和create_cell_bw 中删除reuse=tf.AUTO_REUSE。下面是我更简单的实现。

def encoding_layer(input_data, num_layers, rnn_size, sequence_length, keep_prob):

    output = input_data
    for layer in range(num_layers):
        with tf.variable_scope('encoder_'.format(layer),reuse=tf.AUTO_REUSE):

            cell_fw = tf.contrib.rnn.LSTMCell(rnn_size, initializer=tf.truncated_normal_initializer(-0.1, 0.1, seed=2))
            cell_fw = tf.contrib.rnn.DropoutWrapper(cell_fw, input_keep_prob = keep_prob)

            cell_bw = tf.contrib.rnn.LSTMCell(rnn_size, initializer=tf.truncated_normal_initializer(-0.1, 0.1, seed=2))
            cell_bw = tf.contrib.rnn.DropoutWrapper(cell_bw, input_keep_prob = keep_prob)

            outputs, states = tf.nn.bidirectional_dynamic_rnn(cell_fw, 
                                                              cell_bw, 
                                                              output,
                                                              sequence_length,
                                                              dtype=tf.float32)
            output = tf.concat(outputs,2)
            state = tf.concat(states,2)

    return output, state

【讨论】：

确实有效。我昨天尝试了类似的东西，效果很好。但这返回的结果类似于我的第一个函数，即使用 MultiRNNCell 的函数。任何想法，如果使用 MultiRNNCell 和将多个 bidirectional_dynamic_rnns 连接在一起有什么不同。如果您认为这应该在单独的堆栈溢出问题中提出，请不要犹豫。

没关系@mousaalsulaimi 我相信this 的帖子应该可以消除您的所有疑虑。那里解释得很漂亮。