BERT源码剖析

今天要介绍的是BERT最主要的模型实现部分-----BertModel，代码位于

modeling.py模块
如有解读不正确，请务必指出~

1、配置类（BertConfig）

这部分代码主要定义了BERT模型的一些默认参数，另外包括了一些文件处理函数。

class BertConfig(object):
  """BERT模型的配置类."""

  def __init__(self,
               vocab_size,
               hidden_size=768,
               num_hidden_layers=12,
               num_attention_heads=12,
               intermediate_size=3072,
               hidden_act="gelu",
               hidden_dropout_prob=0.1,
               attention_probs_dropout_prob=0.1,
               max_position_embeddings=512,
               type_vocab_size=16,
               initializer_range=0.02):
 
    self.vocab_size = vocab_size
    self.hidden_size = hidden_size
    self.num_hidden_layers = num_hidden_layers
    self.num_attention_heads = num_attention_heads
    self.hidden_act = hidden_act
    self.intermediate_size = intermediate_size
    self.hidden_dropout_prob = hidden_dropout_prob
    self.attention_probs_dropout_prob = attention_probs_dropout_prob
    self.max_position_embeddings = max_position_embeddings
    self.type_vocab_size = type_vocab_size
    self.initializer_range = initializer_range

  @classmethod
  def from_dict(cls, json_object):
    """Constructs a `BertConfig` from a Python dictionary of parameters."""
    config = BertConfig(vocab_size=None)
    for (key, value) in six.iteritems(json_object):
      config.__dict__[key] = value
    return config

  @classmethod
  def from_json_file(cls, json_file):
    """Constructs a `BertConfig` from a json file of parameters."""
    with tf.gfile.GFile(json_file, "r") as reader:
      text = reader.read()
    return cls.from_dict(json.loads(text))

  def to_dict(self):
    """Serializes this instance to a Python dictionary."""
    output = copy.deepcopy(self.__dict__)
    return output

  def to_json_string(self):
    """Serializes this instance to a JSON string."""
    return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"

参数具体含义：

vocab_size： 单词表大小
hidden_size： 隐藏层神经元节点数 H（指Feed Forward输出向量的维数）
num_hidden_layers： Transformer encoder中的隐藏层数 L
num_attention_heads： multi-head attention 的head数 A
intermediate_size： encoder的“中间”隐层神经元数（例如feed-forward layer）
hidden_act： 隐藏层激活函数
hidden_dropout_prob： 隐层dropout率
attention_probs_dropout_prob： 注意力部分的dropout
max_position_embeddings： 最大位置编码
type_vocab_size： token_type_ids的词典大小,这个名字很模糊
initializer_range： truncated_normal_initializer初始化方法的stdev

这里要注意一点，可能刚看的时候对 type_vocab_size这个参数会有点不理解，其实就是在next sentence prediction任务里的Segment A和 Segment B，用在multi-sentence任务中。在下载的bert_config.json文件里也有说明，默认值应该为2。

论文定义了两个版本，一个是base版本，一个是large版本。Large版本（L=24, H=1024, A=16, Total Parameters=340M）。base版本（ L=12, H=768, A=12, Total Parameters=110M）。L代表网络层数，H代表隐藏层神经元节点数，A代表self attention head的数量。

BertModel模型详解：

class BertModel(object):
  """BERT model ("Bidirectional Encoder Representations from Transformers").

  Example usage:

  ```python
  # Already been converted into WordPiece token ids
  input_ids = tf.constant([[31, 51, 99], [15, 5, 0]])
  input_mask = tf.constant([[1, 1, 1], [1, 1, 0]])
  token_type_ids = tf.constant([[0, 0, 1], [0, 2, 0]])

  config = modeling.BertConfig(vocab_size=32000, hidden_size=512,
    num_hidden_layers=8, num_attention_heads=6, intermediate_size=1024)

  model = modeling.BertModel(config=config, is_training=True,
    input_ids=input_ids, input_mask=input_mask, token_type_ids=token_type_ids)

  label_embeddings = tf.get_variable(...)
  pooled_output = model.get_pooled_output()
  logits = tf.matmul(pooled_output, label_embeddings)
  ...
  """

  def __init__(self,
               config,
               is_training,
               input_ids,
               input_mask=None,
               token_type_ids=None,
               use_one_hot_embeddings=False,
               scope=None):
    """Constructor for BertModel.

    Args:
      config: `BertConfig` instance.
      is_training: bool. true for training model, false for eval model. Controls
        whether dropout will be applied.
      input_ids: int32 Tensor of shape [batch_size, seq_length].
      input_mask: (optional) int32 Tensor of shape [batch_size, seq_length].
      token_type_ids: (optional) int32 Tensor of shape [batch_size, seq_length].
      use_one_hot_embeddings: (optional) bool. Whether to use one-hot word
        embeddings or tf.embedding_lookup() for the word embeddings.
      scope: (optional) variable scope. Defaults to "bert".

    Raises:
      ValueError: The config is invalid or one of the input tensor shapes
        is invalid.
    """
    config = copy.deepcopy(config)
    if not is_training:
      config.hidden_dropout_prob = 0.0
      config.attention_probs_dropout_prob = 0.0

    input_shape = get_shape_list(input_ids, expected_rank=2)
    batch_size = input_shape[0]
    seq_length = input_shape[1]

    if input_mask is None:#输入没有被masked
      input_mask = tf.ones(shape=[batch_size, seq_length], dtype=tf.int32)

    if token_type_ids is None:#只有一个句子，不用区分token属于哪个句子
      token_type_ids = tf.zeros(shape=[batch_size, seq_length], dtype=tf.int32)

    with tf.variable_scope(scope, default_name="bert"):
      with tf.variable_scope("embeddings"):
        # Perform embedding lookup on the word ids.
        (self.embedding_output, self.embedding_table) = embedding_lookup(
            input_ids=input_ids,
            vocab_size=config.vocab_size,
            embedding_size=config.hidden_size,
            initializer_range=config.initializer_range,
            word_embedding_name="word_embeddings",
            use_one_hot_embeddings=use_one_hot_embeddings)

        # 添加 positional embeddings and token type embeddings, then layer
        # normalize and perform dropout.
        self.embedding_output = embedding_postprocessor(
            input_tensor=self.embedding_output,
            use_token_type=True,
            token_type_ids=token_type_ids,
            token_type_vocab_size=config.type_vocab_size,
            token_type_embedding_name="token_type_embeddings",
            use_position_embeddings=True,
            position_embedding_name="position_embeddings",
            initializer_range=config.initializer_range,
            max_position_embeddings=config.max_position_embeddings,
            dropout_prob=config.hidden_dropout_prob)

      with tf.variable_scope("encoder"):
        # This converts a 2D mask of shape [batch_size, seq_length] to a 3D
        # mask of shape [batch_size, seq_length, seq_length] which is used
        # for the attention scores.
        attention_mask = create_attention_mask_from_input_mask(
            input_ids, input_mask)

        # Run the stacked transformer.
        # `sequence_outpu