basic_seq2seq报错：ValueError: too many values to unpack (expected 2)

[grt1st]

我的python版本是3.6，tensorflow版本是1.2：

➜  ~ python
Python 3.6.2 (default, Jul 20 2017, 03:52:27) 
[GCC 7.1.1 20170630] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorflow as tf
>>> tf.__version__
'1.2.0-rc2'
>>> 

我把basic_seq2seq的代码复制出来，在运行的时候报错如下：

➜  ~ python test.py
Traceback (most recent call last):
  File "test.py", line 224, in <module>
    num_layers)    
  File "test.py", line 184, in seq2seq_model
    decoder_input) 
  File "test.py", line 137, in decoding_layer
    maximum_iterations=max_target_sequence_length)
ValueError: too many values to unpack (expected 2)

复制出来的代码如下(只复制了图算法，反正都是一样的)：

import tensorflow as tf
from tensorflow.python.layers.core import Dense

with open('/home/grt1st/data/letters_source.txt', 'r', encoding='utf-8') as f:
    source_data = f.read()

with open('/home/grt1st/data/letters_target.txt', 'r', encoding='utf-8') as f:
    target_data = f.read()

def extract_character_vocab(data):
    '''
    构造映射表
    '''
    special_words = ['<PAD>', '<UNK>', '<GO>',  '<EOS>']

    set_words = list(set([character for line in data.split('\n') for character in line]))
    # 这里要把四个特殊字符添加进词典
    int_to_vocab = {idx: word for idx, word in enumerate(special_words + set_words)}
    vocab_to_int = {word: idx for idx, word in int_to_vocab.items()}

    return int_to_vocab, vocab_to_int

# 构造映射表
source_int_to_letter, source_letter_to_int = extract_character_vocab(source_data)
target_int_to_letter, target_letter_to_int = extract_character_vocab(target_data)

# 对字母进行转换
source_int = [[source_letter_to_int.get(letter, source_letter_to_int['<UNK>']) 
               for letter in line] for line in source_data.split('\n')]
target_int = [[target_letter_to_int.get(letter, target_letter_to_int['<UNK>']) 
               for letter in line] + [target_letter_to_int['<EOS>']] for line in target_data.split('\n')]

def get_inputs():
    '''
    模型输入tensor
    '''
    inputs = tf.placeholder(tf.int32, [None, None], name='inputs')
    targets = tf.placeholder(tf.int32, [None, None], name='targets')
    learning_rate = tf.placeholder(tf.float32, name='learning_rate')

    # 定义target序列最大长度（之后target_sequence_length和source_sequence_length会作为feed_dict的参数）
    target_sequence_length = tf.placeholder(tf.int32, (None,), name='target_sequence_length')
    max_target_sequence_length = tf.reduce_max(target_sequence_length, name='max_target_len')
    source_sequence_length = tf.placeholder(tf.int32, (None,), name='source_sequence_length')

    return inputs, targets, learning_rate, target_sequence_length, max_target_sequence_length, source_sequence_length

def get_encoder_layer(input_data, rnn_size, num_layers,
                   source_sequence_length, source_vocab_size, 
                   encoding_embedding_size):

    '''
    构造Encoder层

    参数说明：
    - input_data: 输入tensor
    - rnn_size: rnn隐层结点数量
    - num_layers: 堆叠的rnn cell数量
    - source_sequence_length: 源数据的序列长度
    - source_vocab_size: 源数据的词典大小
    - encoding_embedding_size: embedding的大小
    '''
    # Encoder embedding
    encoder_embed_input = tf.contrib.layers.embed_sequence(input_data, source_vocab_size, encoding_embedding_size)

    # RNN cell
    def get_lstm_cell(rnn_size):
        lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size, initializer=tf.random_uniform_initializer(-0.1, 0.1, seed=2))
        return lstm_cell

    cell = tf.contrib.rnn.MultiRNNCell([get_lstm_cell(rnn_size) for _ in range(num_layers)])

    encoder_output, encoder_state = tf.nn.dynamic_rnn(cell, encoder_embed_input, 
                                                      sequence_length=source_sequence_length, dtype=tf.float32)

    return encoder_output, encoder_state

def process_decoder_input(data, vocab_to_int, batch_size):
    '''
    补充<GO>，并移除最后一个字符
    '''
    # cut掉最后一个字符
    ending = tf.strided_slice(data, [0, 0], [batch_size, -1], [1, 1])
    decoder_input = tf.concat([tf.fill([batch_size, 1], vocab_to_int['<GO>']), ending], 1)

    return decoder_input

def decoding_layer(target_letter_to_int, decoding_embedding_size, num_layers, rnn_size,
                   target_sequence_length, max_target_sequence_length, encoder_state, decoder_input):
    '''
    构造Decoder层

    参数：
    - target_letter_to_int: target数据的映射表
    - decoding_embedding_size: embed向量大小
    - num_layers: 堆叠的RNN单元数量
    - rnn_size: RNN单元的隐层结点数量
    - target_sequence_length: target数据序列长度
    - max_target_sequence_length: target数据序列最大长度
    - encoder_state: encoder端编码的状态向量
    - decoder_input: decoder端输入
    '''
    # 1. Embedding
    target_vocab_size = len(target_letter_to_int)
    decoder_embeddings = tf.Variable(tf.random_uniform([target_vocab_size, decoding_embedding_size]))
    decoder_embed_input = tf.nn.embedding_lookup(decoder_embeddings, decoder_input)

    # 2. 构造Decoder中的RNN单元
    def get_decoder_cell(rnn_size):
        decoder_cell = tf.contrib.rnn.LSTMCell(rnn_size,
                                           initializer=tf.random_uniform_initializer(-0.1, 0.1, seed=2))
        return decoder_cell
    cell = tf.contrib.rnn.MultiRNNCell([get_decoder_cell(rnn_size) for _ in range(num_layers)])

    # 3. Output全连接层
    output_layer = Dense(target_vocab_size,
                         kernel_initializer = tf.truncated_normal_initializer(mean = 0.0, stddev=0.1))

    # 4. Training decoder
    with tf.variable_scope("decode"):
        # 得到help对象
        training_helper = tf.contrib.seq2seq.TrainingHelper(inputs=decoder_embed_input,
                                                            sequence_length=target_sequence_length,
                                                            time_major=False)
        # 构造decoder
        training_decoder = tf.contrib.seq2seq.BasicDecoder(cell,
                                                           training_helper,
                                                           encoder_state,
                                                           output_layer) 
        training_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder,
                                                                       impute_finished=True,
                                                                       maximum_iterations=max_target_sequence_length)
    # 5. Predicting decoder
    # 与training共享参数
    with tf.variable_scope("decode", reuse=True):
        # 创建一个常量tensor并复制为batch_size的大小
        start_tokens = tf.tile(tf.constant([target_letter_to_int['<GO>']], dtype=tf.int32), [batch_size], 
                               name='start_tokens')
        predicting_helper = tf.contrib.seq2seq.GreedyEmbeddingHelper(decoder_embeddings,
                                                                start_tokens,
                                                                target_letter_to_int['<EOS>'])
        predicting_decoder = tf.contrib.seq2seq.BasicDecoder(cell,
                                                        predicting_helper,
                                                        encoder_state,
                                                        output_layer)
        predicting_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(predicting_decoder,
                                                            impute_finished=True,
                                                            maximum_iterations=max_target_sequence_length)

    return training_decoder_output, predicting_decoder_output

def seq2seq_model(input_data, targets, lr, target_sequence_length, 
                  max_target_sequence_length, source_sequence_length,
                  source_vocab_size, target_vocab_size,
                  encoder_embedding_size, decoder_embedding_size, 
                  rnn_size, num_layers):

    # 获取encoder的状态输出
    _, encoder_state = get_encoder_layer(input_data, 
                                  rnn_size, 
                                  num_layers, 
                                  source_sequence_length,
                                  source_vocab_size, 
                                  encoding_embedding_size)

    # 预处理后的decoder输入
    decoder_input = process_decoder_input(targets, target_letter_to_int, batch_size)

    # 将状态向量与输入传递给decoder
    training_decoder_output, predicting_decoder_output = decoding_layer(target_letter_to_int, 
                                                                       decoding_embedding_size, 
                                                                       num_layers, 
                                                                       rnn_size,
                                                                       target_sequence_length,
                                                                       max_target_sequence_length,
                                                                       encoder_state, 
                                                                       decoder_input) 

    return training_decoder_output, predicting_decoder_output

# 超参数
# Number of Epochs
epochs = 60
# Batch Size
batch_size = 128
# RNN Size
rnn_size = 50
# Number of Layers
num_layers = 2
# Embedding Size
encoding_embedding_size = 15
decoding_embedding_size = 15
# Learning Rate
learning_rate = 0.001

# 构造graph
train_graph = tf.Graph()

with train_graph.as_default():

    # 获得模型输入    
    input_data, targets, lr, target_sequence_length, max_target_sequence_length, source_sequence_length = get_inputs()

    training_decoder_output, predicting_decoder_output = seq2seq_model(input_data, 
                                                                      targets, 
                                                                      lr, 
                                                                      target_sequence_length, 
                                                                      max_target_sequence_length, 
                                                                      source_sequence_length,
                                                                      len(source_letter_to_int),
                                                                      len(target_letter_to_int),
                                                                      encoding_embedding_size, 
                                                                      decoding_embedding_size, 
                                                                      rnn_size, 
                                                                      num_layers)    

    training_logits = tf.identity(training_decoder_output.rnn_output, 'logits')
    predicting_logits = tf.identity(predicting_decoder_output.sample_id, name='predictions')

    masks = tf.sequence_mask(target_sequence_length, max_target_sequence_length, dtype=tf.float32, name='masks')

    with tf.name_scope("optimization"):

        # Loss function
        cost = tf.contrib.seq2seq.sequence_loss(
            training_logits,
            targets,
            masks)

        # Optimizer
        optimizer = tf.train.AdamOptimizer(lr)

        # Gradient Clipping
        gradients = optimizer.compute_gradients(cost)
        capped_gradients = [(tf.clip_by_value(grad, -5., 5.), var) for grad, var in gradients if grad is not None]
        train_op = optimizer.apply_gradients(capped_gradients)

定位到的位置是decoder的训练中：

    with tf.variable_scope("decode"):
        # 得到help对象
        training_helper = tf.contrib.seq2seq.TrainingHelper(inputs=decoder_embed_input,
                                                            sequence_length=target_sequence_length,
                                                            time_major=False)
        # 构造decoder
        training_decoder = tf.contrib.seq2seq.BasicDecoder(cell,
                                                           training_helper,
                                                           encoder_state,
                                                           output_layer) 
        training_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder,
                                                                       impute_finished=True,
                                                                       maximum_iterations=max_target_sequence_length)

我觉得是helper或者decoder出错了，问题的原因还是版本的变化，但是我找不到解决的办法，谁能帮帮我吗？

[grt1st]

版本问题，改成：

 training_decoder_output, _, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder,
                                                                       impute_finished=True,
                                                                       maximum_iterations=max_target_sequence_length)
......
predicting_decoder_output, _, _ = tf.contrib.seq2seq.dynamic_decode(predicting_decoder,
                                                            impute_finished=True,
                                                            maximum_iterations=max_target_sequence_length)

[CourteousWood]

楼上是正解，多加一个下划线就可以了

[lvjiujin]

我也刚好碰到类似问题，原来是返回值的个数发生变化了。

[jwc19890114]

感谢感谢，我本来以为是那个库更新了