python create_pretraining_data.py \
  --input_file=./sample_text.txt \
  --output_file=/tmp/tf_examples.tfrecord \
  --vocab_file=$BERT_BASE_DIR/vocab.txt \
  --do_lower_case=True \
  --max_seq_length=128 \
  --max_predictions_per_seq=20 \
  --masked_lm_prob=0.15 \
  --random_seed=12345 \
  --dupe_factor=5

def create_training_instances(input_files, tokenizer, max_seq_length,
                              dupe_factor, short_seq_prob, masked_lm_prob,
                              max_predictions_per_seq, rng):
  """Create `TrainingInstance`s from raw text."""
  all_documents = [[]]

  # Input file format:
  # (1) One sentence per line. These should ideally be actual sentences, not
  # entire paragraphs or arbitrary spans of text. (Because we use the
  # sentence boundaries for the "next sentence prediction" task).
  # (2) Blank lines between documents. Document boundaries are needed so
  # that the "next sentence prediction" task doesn't span between documents.
  for input_file in input_files:
    with tf.gfile.GFile(input_file, "r") as reader:
      while True:
        line = tokenization.convert_to_unicode(reader.readline())
        if not line:
          break
        line = line.strip()

        # Empty lines are used as document delimiters
        if not line:
          all_documents.append([])
        tokens = tokenizer.tokenize(line)
        if tokens:
          all_documents[-1].append(tokens)

  # Remove empty documents
  all_documents = [x for x in all_documents if x]
  rng.shuffle(all_documents)

  vocab_words = list(tokenizer.vocab.keys())
  instances = []
  for _ in range(dupe_factor):
    for document_index in range(len(all_documents)):
      instances.extend(
          create_instances_from_document(
              all_documents, document_index, max_seq_length, short_seq_prob,
              masked_lm_prob, max_predictions_per_seq, vocab_words, rng))

  rng.shuffle(instances)
  return instances

def create_instances_from_document(
    all_documents, document_index, max_seq_length, short_seq_prob,
    masked_lm_prob, max_predictions_per_seq, vocab_words, rng):
  """Creates `TrainingInstance`s for a single document."""
  document = all_documents[document_index]

  # Account for [CLS], [SEP], [SEP]
  max_num_tokens = max_seq_length - 3

  # We *usually* want to fill up the entire sequence since we are padding
  # to `max_seq_length` anyways, so short sequences are generally wasted
  # computation. However, we *sometimes*
  # (i.e., short_seq_prob == 0.1 == 10% of the time) want to use shorter
  # sequences to minimize the mismatch between pre-training and fine-tuning.
  # The `target_seq_length` is just a rough target however, whereas
  # `max_seq_length` is a hard limit.
  target_seq_length = max_num_tokens
  if rng.random() < short_seq_prob:
    target_seq_length = rng.randint(2, max_num_tokens)

  # We DON'T just concatenate all of the tokens from a document into a long
  # sequence and choose an arbitrary split point because this would make the
  # next sentence prediction task too easy. Instead, we split the input into
  # segments "A" and "B" based on the actual "sentences" provided by the user
  # input.
  instances = []
  current_chunk = []
  current_length = 0
  i = 0
  while i < len(document):
    segment = document[i]
    current_chunk.append(segment)
    current_length += len(segment)
    if i == len(document) - 1 or current_length >= target_seq_length:
      if current_chunk:
        # `a_end` is how many segments from `current_chunk` go into the `A`
        # (first) sentence.
        a_end = 1
        if len(current_chunk) >= 2:
          a_end = rng.randint(1, len(current_chunk) - 1)

        tokens_a = []
        for j in range(a_end):
          tokens_a.extend(current_chunk[j])

        tokens_b = []
        # Random next
        is_random_next = False
        if len(current_chunk) == 1 or rng.random() < 0.5:
          is_random_next = True
          target_b_length = target_seq_length - len(tokens_a)

          # This should rarely go for more than one iteration for large
          # corpora. However, just to be careful, we try to make sure that
          # the random document is not the same as the document
          # we're processing.
          for _ in range(10):
            random_document_index = rng.randint(0, len(all_documents) - 1)
            if random_document_index != document_index:
              break

          random_document = all_documents[random_document_index]
          random_start = rng.randint(0, len(random_document) - 1)
          for j in range(random_start, len(random_document)):
            tokens_b.extend(random_document[j])
            if len(tokens_b) >= target_b_length:
              break
          # We didn't actually use these segments so we "put them back" so
          # they don't go to waste.
          num_unused_segments = len(current_chunk) - a_end
          i -= num_unused_segments
        # Actual next
        else:
          is_random_next = False
          for j in range(a_end, len(current_chunk)):
            tokens_b.extend(current_chunk[j])
        truncate_seq_pair(tokens_a, tokens_b, max_num_tokens, rng)

        assert len(tokens_a) >= 1
        assert len(tokens_b) >= 1

        tokens = []
        segment_ids = []
        tokens.append("[CLS]")
        segment_ids.append(0)
        for token in tokens_a:
          tokens.append(token)
          segment_ids.append(0)

        tokens.append("[SEP]")
        segment_ids.append(0)

        for token in tokens_b:
          tokens.append(token)
          segment_ids.append(1)
        tokens.append("[SEP]")
        segment_ids.append(1)

        (tokens, masked_lm_positions,
         masked_lm_labels) = create_masked_lm_predictions(
             tokens, masked_lm_prob, max_predictions_per_seq, vocab_words, rng)
        instance = TrainingInstance(
            tokens=tokens,
            segment_ids=segment_ids,
            is_random_next=is_random_next,
            masked_lm_positions=masked_lm_positions,
            masked_lm_labels=masked_lm_labels)
        instances.append(instance)
      current_chunk = []
      current_length = 0
    i += 1

  return instances

def create_masked_lm_predictions(tokens, masked_lm_prob,
                                 max_predictions_per_seq, vocab_words, rng):
  """Creates the predictions for the masked LM objective."""

  cand_indexes = []
  for (i, token) in enumerate(tokens):
    if token == "[CLS]" or token == "[SEP]":
      continue
    # Whole Word Masking means that if we mask all of the wordpieces
    # corresponding to an original word. When a word has been split into
    # WordPieces, the first token does not have any marker and any subsequence
    # tokens are prefixed with ##. So whenever we see the ## token, we
    # append it to the previous set of word indexes.
    #
    # Note that Whole Word Masking does *not* change the training code
    # at all -- we still predict each WordPiece independently, softmaxed
    # over the entire vocabulary.
    if (FLAGS.do_whole_word_mask and len(cand_indexes) >= 1 and
        token.startswith("##")):
      cand_indexes[-1].append(i)
    else:
      cand_indexes.append([i])

  rng.shuffle(cand_indexes)

  output_tokens = list(tokens)

  num_to_predict = min(max_predictions_per_seq,
                       max(1, int(round(len(tokens) * masked_lm_prob))))

  masked_lms = []
  covered_indexes = set()
  for index_set in cand_indexes:
    if len(masked_lms) >= num_to_predict:
      break
    # If adding a whole-word mask would exceed the maximum number of
    # predictions, then just skip this candidate.
    if len(masked_lms) + len(index_set) > num_to_predict:
      continue
    is_any_index_covered = False
    for index in index_set:
      if index in covered_indexes:
        is_any_index_covered = True
        break
    if is_any_index_covered:
      continue
    for index in index_set:
      covered_indexes.add(index)

      masked_token = None
      # 80% of the time, replace with [MASK]
      if rng.random() < 0.8:
        masked_token = "[MASK]"
      else:
        # 10% of the time, keep original
        if rng.random() < 0.5:
          masked_token = tokens[index]
        # 10% of the time, replace with random word
        else:
          masked_token = vocab_words[rng.randint(0, len(vocab_words) - 1)]

      output_tokens[index] = masked_token

      masked_lms.append(MaskedLmInstance(index=index, label=tokens[index]))
  assert len(masked_lms) <= num_to_predict
  masked_lms = sorted(masked_lms, key=lambda x: x.index)

  masked_lm_positions = []
  masked_lm_labels = []
  for p in masked_lms:
    masked_lm_positions.append(p.index)
    masked_lm_labels.append(p.label)

  return (output_tokens, masked_lm_positions, masked_lm_labels)

def write_instance_to_example_files(instances, tokenizer, max_seq_length,
                                    max_predictions_per_seq, output_files):
  """Create TF example files from `TrainingInstance`s."""
  writers = []
  for output_file in output_files:
    writers.append(tf.python_io.TFRecordWriter(output_file))

  writer_index = 0

  total_written = 0
  for (inst_index, instance) in enumerate(instances):
    input_ids = tokenizer.convert_tokens_to_ids(instance.tokens)
    input_mask = [1] * len(input_ids)
    segment_ids = list(instance.segment_ids)
    assert len(input_ids) <= max_seq_length

    while len(input_ids) < max_seq_length:
      input_ids.append(0)
      input_mask.append(0)
      segment_ids.append(0)

    assert len(input_ids) == max_seq_length
    assert len(input_mask) == max_seq_length
    assert len(segment_ids) == max_seq_length

    masked_lm_positions = list(instance.masked_lm_positions)
    masked_lm_ids = tokenizer.convert_tokens_to_ids(instance.masked_lm_labels)
    masked_lm_weights = [1.0] * len(masked_lm_ids)

    while len(masked_lm_positions) < max_predictions_per_seq:
      masked_lm_positions.append(0)
      masked_lm_ids.append(0)
      masked_lm_weights.append(0.0)

    next_sentence_label = 1 if instance.is_random_next else 0

    features = collections.OrderedDict()
    features["input_ids"] = create_int_feature(input_ids)
    features["input_mask"] = create_int_feature(input_mask)
    features["segment_ids"] = create_int_feature(segment_ids)
    features["masked_lm_positions"] = create_int_feature(masked_lm_positions)
    features["masked_lm_ids"] = create_int_feature(masked_lm_ids)
    features["masked_lm_weights"] = create_float_feature(masked_lm_weights)
    features["next_sentence_labels"] = create_int_feature([next_sentence_label])

    tf_example = tf.train.Example(features=tf.train.Features(feature=features))

    writers[writer_index].write(tf_example.SerializeToString())
    writer_index = (writer_index + 1) % len(writers)

    total_written += 1

    if inst_index < 20:
      tf.logging.info("*** Example ***")
      tf.logging.info("tokens: %s" % " ".join(
          [tokenization.printable_text(x) for x in instance.tokens]))

      for feature_name in features.keys():
        feature = features[feature_name]
        values = []
        if feature.int64_list.value:
          values = feature.int64_list.value
        elif feature.float_list.value:
          values = feature.float_list.value
        tf.logging.info(
            "%s: %s" % (feature_name, " ".join([str(x) for x in values])))

  for writer in writers:
    writer.close()

  tf.logging.info("Wrote %d total instances", total_written)

python run_pretraining.py \
  --input_file=/tmp/tf_examples.tfrecord \
  --output_dir=/tmp/pretraining_output \
  --do_train=True \
  --do_eval=True \
  --bert_config_file=$BERT_BASE_DIR/bert_config.json \
  --init_checkpoint=$BERT_BASE_DIR/bert_model.ckpt \
  --train_batch_size=32 \
  --max_seq_length=128 \
  --max_predictions_per_seq=20 \
  --num_train_steps=20 \
  --num_warmup_steps=10 \
  --learning_rate=2e-5

def input_fn_builder(input_files,
                     max_seq_length,
                     max_predictions_per_seq,
                     is_training,
                     num_cpu_threads=4):
  """Creates an `input_fn` closure to be passed to TPUEstimator."""

  def input_fn(params):
    """The actual input function."""
    batch_size = params["batch_size"]

    name_to_features = {
        "input_ids":
            tf.FixedLenFeature([max_seq_length], tf.int64),
        "input_mask":
            tf.FixedLenFeature([max_seq_length], tf.int64),
        "segment_ids":
            tf.FixedLenFeature([max_seq_length], tf.int64),
        "masked_lm_positions":
            tf.FixedLenFeature([max_predictions_per_seq], tf.int64),
        "masked_lm_ids":
            tf.FixedLenFeature([max_predictions_per_seq], tf.int64),
        "masked_lm_weights":
            tf.FixedLenFeature([max_predictions_per_seq], tf.float32),
        "next_sentence_labels":
            tf.FixedLenFeature([1], tf.int64),
    }

    # For training, we want a lot of parallel reading and shuffling.
    # For eval, we want no shuffling and parallel reading doesn't matter.
    if is_training:
      tf.logging.info(f'input_files---:{input_files}')
      tf.logging.info(f'tf.constant(input_files)---:{tf.constant(input_files)}')
      d = tf.data.Dataset.from_tensor_slices(tf.constant(input_files))  # ???
      d = d.repeat()
      d = d.shuffle(buffer_size=len(input_files))

      # `cycle_length` is the number of parallel files that get read.
      cycle_length = min(num_cpu_threads, len(input_files))

      # `sloppy` mode means that the interleaving is not exact. This adds
      # even more randomness to the training pipeline.
      d = d.apply(
          tf.contrib.data.parallel_interleave(
              tf.data.TFRecordDataset,
              sloppy=is_training,
              cycle_length=cycle_length))
      d = d.shuffle(buffer_size=100)
    else:
      d = tf.data.TFRecordDataset(input_files)
      # Since we evaluate for a fixed number of steps we don't want to encounter
      # out-of-range exceptions.
      d = d.repeat()

    # We must `drop_remainder` on training because the TPU requires fixed
    # size dimensions. For eval, we assume we are evaluating on the CPU or GPU
    # and we *don't* want to drop the remainder, otherwise we wont cover
    # every sample.
    d = d.apply(
        tf.contrib.data.map_and_batch(
            lambda record: _decode_record(record, name_to_features),
            batch_size=batch_size,
            num_parallel_batches=num_cpu_threads,
            drop_remainder=True))
    return d

  return input_fn

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]. <==> segment id
      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:
      input_mask = tf.ones(shape=[batch_size, seq_length], dtype=tf.int32)

    if token_type_ids is None:
      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)

        # Add 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_output` shape = [batch_size, seq_length, hidden_size].
        self.all_encoder_layers = transformer_model(
            input_tensor=self.embedding_output,
            attention_mask=attention_mask,
            hidden_size=config.hidden_size,
            num_hidden_layers=config.num_hidden_layers,
            num_attention_heads=config.num_attention_heads,
            intermediate_size=config.intermediate_size,
            intermediate_act_fn=get_activation(config.hidden_act),
            hidden_dropout_prob=config.hidden_dropout_prob,
            attention_probs_dropout_prob=config.attention_probs_dropout_prob,
            initializer_range=config.initializer_range,
            do_return_all_layers=True)

      self.sequence_output = self.all_encoder_layers[-1]
      # The "pooler" converts the encoded sequence tensor of shape
      # [batch_size, seq_length, hidden_size] to a tensor of shape
      # [batch_size, hidden_size]. This is necessary for segment-level
      # (or segment-pair-level) classification tasks where we need a fixed
      # dimensional representation of the segment.
      with tf.variable_scope("pooler"):
        # We "pool" the model by simply taking the hidden state corresponding
        # to the first token. We assume that this has been pre-trained
        first_token_tensor = tf.squeeze(self.sequence_output[:, 0:1, :], axis=1)
        self.pooled_output = tf.layers.dense(
            first_token_tensor,
            config.hidden_size,
            activation=tf.tanh,
            kernel_initializer=create_initializer(config.initializer_range))

def embedding_lookup(input_ids,
                     vocab_size,
                     embedding_size=128,
                     initializer_range=0.02,
                     word_embedding_name="word_embeddings",
                     use_one_hot_embeddings=False):
  """Looks up words embeddings for id tensor.

  Args:
    input_ids: int32 Tensor of shape [batch_size, seq_length] containing word
      ids.
    vocab_size: int. Size of the embedding vocabulary.
    embedding_size: int. Width of the word embeddings.
    initializer_range: float. Embedding initialization range.
    word_embedding_name: string. Name of the embedding table.
    use_one_hot_embeddings: bool. If True, use one-hot method for word
      embeddings. If False, use `tf.gather()`.

  Returns:
    float Tensor of shape [batch_size, seq_length, embedding_size].
  """
  # This function assumes that the input is of shape [batch_size, seq_length,
  # num_inputs].
  #
  # If the input is a 2D tensor of shape [batch_size, seq_length], we
  # reshape to [batch_size, seq_length, 1].
  if input_ids.shape.ndims == 2:
    input_ids = tf.expand_dims(input_ids, axis=[-1])

  embedding_table = tf.get_variable(
      name=word_embedding_name,
      shape=[vocab_size, embedding_size],
      initializer=create_initializer(initializer_range))

  flat_input_ids = tf.reshape(input_ids, [-1])   # [batch_size*seq_length]
  if use_one_hot_embeddings:
    one_hot_input_ids = tf.one_hot(flat_input_ids, depth=vocab_size)
    output = tf.matmul(one_hot_input_ids, embedding_table)
  else:
    output = tf.gather(embedding_table, flat_input_ids)  # [batch_size*seq_length,embedding_size]

  input_shape = get_shape_list(input_ids)

  output = tf.reshape(output,
                      input_shape[0:-1] + [input_shape[-1] * embedding_size]) # [batch_size,seq_length,embedding_size]
  return (output, embedding_table)

def embedding_postprocessor(input_tensor,
                            use_token_type=False,
                            token_type_ids=None,
                            token_type_vocab_size=16,
                            token_type_embedding_name="token_type_embeddings",
                            use_position_embeddings=True,
                            position_embedding_name="position_embeddings",
                            initializer_range=0.02,
                            max_position_embeddings=512,
                            dropout_prob=0.1):
  """Performs various post-processing on a word embedding tensor.

  Args:
    input_tensor: float Tensor of shape [batch_size, seq_length,
      embedding_size].
    use_token_type: bool. Whether to add embeddings for `token_type_ids`.
    token_type_ids: (optional) int32 Tensor of shape [batch_size, seq_length].
      Must be specified if `use_token_type` is True.
    token_type_vocab_size: int. The vocabulary size of `token_type_ids`.
    token_type_embedding_name: string. The name of the embedding table variable
      for token type ids.
    use_position_embeddings: bool. Whether to add position embeddings for the
      position of each token in the sequence.
    position_embedding_name: string. The name of the embedding table variable
      for positional embeddings.
    initializer_range: float. Range of the weight initialization.
    max_position_embeddings: int. Maximum sequence length that might ever be
      used with this model. This can be longer than the sequence length of
      input_tensor, but cannot be shorter.
    dropout_prob: float. Dropout probability applied to the final output tensor.

  Returns:
    float tensor with same shape as `input_tensor`.

  Raises:
    ValueError: One of the tensor shapes or input values is invalid.
  """
  input_shape = get_shape_list(input_tensor, expected_rank=3)
  batch_size = input_shape[0]
  seq_length = input_shape[1]
  width = input_shape[2]

  output = input_tensor  # [batch_size, seq_length,embedding_size]

  if use_token_type:
    if token_type_ids is None:
      raise ValueError("`token_type_ids` must be specified if"
                       "`use_token_type` is True.")
    token_type_table = tf.get_variable(
        name=token_type_embedding_name,
        shape=[token_type_vocab_size, width],
        initializer=create_initializer(initializer_range))
    # This vocab will be small so we always do one-hot here, since it is always
    # faster for a small vocabulary.
    flat_token_type_ids = tf.reshape(token_type_ids, [-1]) # [batch_size, seq_length] --> [batch_size*seq_length]
    one_hot_ids = tf.one_hot(flat_token_type_ids, depth=token_type_vocab_size)  # [batch_size*seq_length,token_type_vocab_size]
    token_type_embeddings = tf.matmul(one_hot_ids, token_type_table)
    token_type_embeddings = tf.reshape(token_type_embeddings,
                                       [batch_size, seq_length, width])
    output += token_type_embeddings

  if use_position_embeddings:
    assert_op = tf.assert_less_equal(seq_length, max_position_embeddings)
    with tf.control_dependencies([assert_op]):
      full_position_embeddings = tf.get_variable(
          name=position_embedding_name,
          shape=[max_position_embeddings, width],
          initializer=create_initializer(initializer_range))
      # Since the position embedding table is a learned variable, we create it
      # using a (long) sequence length `max_position_embeddings`. The actual
      # sequence length might be shorter than this, for faster training of
      # tasks that do not have long sequences.
      #
      # So `full_position_embeddings` is effectively an embedding table
      # for position [0, 1, 2, ..., max_position_embeddings-1], and the current
      # sequence has positions [0, 1, 2, ... seq_length-1], so we can just
      # perform a slice.
      position_embeddings = tf.slice(full_position_embeddings, [0, 0],
                                     [seq_length, -1])  # [max_position_embeddings, width] --> [seq_length, width]
      num_dims = len(output.shape.as_list()) # [batch_size, seq_length,embedding_size]

      # Only the last two dimensions are relevant (`seq_length` and `width`), so
      # we broadcast among the first dimensions, which is typically just
      # the batch size.
      position_broadcast_shape = []
      for _ in range(num_dims - 2):
        position_broadcast_shape.append(1)
      position_broadcast_shape.extend([seq_length, width]) # [1,seq_length,width]
      position_embeddings = tf.reshape(position_embeddings,
                                       position_broadcast_shape)
      output += position_embeddings

  output = layer_norm_and_dropout(output, dropout_prob)
  return output

def transformer_model(input_tensor,
                      attention_mask=None,
                      hidden_size=768,
                      num_hidden_layers=12,
                      num_attention_heads=12,
                      intermediate_size=3072,
                      intermediate_act_fn=gelu,
                      hidden_dropout_prob=0.1,
                      attention_probs_dropout_prob=0.1,
                      initializer_range=0.02,
                      do_return_all_layers=False):
  """Multi-headed, multi-layer Transformer from "Attention is All You Need".

  This is almost an exact implementation of the original Transformer encoder.

  See the original paper:
  https://arxiv.org/abs/1706.03762

  Also see:
  https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/transformer.py

  Args:
    input_tensor: float Tensor of shape [batch_size, seq_length, hidden_size].
    attention_mask: (optional) int32 Tensor of shape [batch_size, seq_length,
      seq_length], with 1 for positions that can be attended to and 0 in
      positions that should not be.
    hidden_size: int. Hidden size of the Transformer.
    num_hidden_layers: int. Number of layers (blocks) in the Transformer.
    num_attention_heads: int. Number of attention heads in the Transformer.
    intermediate_size: int. The size of the "intermediate" (a.k.a., feed
      forward) layer.
    intermediate_act_fn: function. The non-linear activation function to apply
      to the output of the intermediate/feed-forward layer.
    hidden_dropout_prob: float. Dropout probability for the hidden layers.
    attention_probs_dropout_prob: float. Dropout probability of the attention
      probabilities.
    initializer_range: float. Range of the initializer (stddev of truncated
      normal).
    do_return_all_layers: Whether to also return all layers or just the final
      layer.

  Returns:
    float Tensor of shape [batch_size, seq_length, hidden_size], the final
    hidden layer of the Transformer.

  Raises:
    ValueError: A Tensor shape or parameter is invalid.
  """
  if hidden_size % num_attention_heads != 0:
    raise ValueError(
        "The hidden size (%d) is not a multiple of the number of attention "
        "heads (%d)" % (hidden_size, num_attention_heads))

  attention_head_size = int(hidden_size / num_attention_heads)
  input_shape = get_shape_list(input_tensor, expected_rank=3)
  batch_size = input_shape[0]
  seq_length = input_shape[1]
  input_width = input_shape[2]

  # The Transformer performs sum residuals on all layers so the input needs
  # to be the same as the hidden size.
  if input_width != hidden_size:
    raise ValueError("The width of the input tensor (%d) != hidden size (%d)" %
                     (input_width, hidden_size))

  # We keep the representation as a 2D tensor to avoid re-shaping it back and
  # forth from a 3D tensor to a 2D tensor. Re-shapes are normally free on
  # the GPU/CPU but may not be free on the TPU, so we want to minimize them to
  # help the optimizer.
  prev_output = reshape_to_matrix(input_tensor)

  all_layer_outputs = []
  for layer_idx in range(num_hidden_layers):
    with tf.variable_scope("layer_%d" % layer_idx):
      layer_input = prev_output

      with tf.variable_scope("attention"):
        attention_heads = []
        with tf.variable_scope("self"):
          attention_head = attention_layer(   # [B*F, N*H] / [B, F, N*H]
              from_tensor=layer_input,
              to_tensor=layer_input,
              attention_mask=attention_mask,
              num_attention_heads=num_attention_heads,
              size_per_head=attention_head_size,
              attention_probs_dropout_prob=attention_probs_dropout_prob,
              initializer_range=initializer_range,
              do_return_2d_tensor=True,
              batch_size=batch_size,
              from_seq_length=seq_length,
              to_seq_length=seq_length)
          attention_heads.append(attention_head)

        attention_output = None
        if len(attention_heads) == 1:
          attention_output = attention_heads[0]
        else:  # ??? 什么情况没想到啊。。。先不考率
          # In the case where we have other sequences, we just concatenate
          # them to the self-attention head before the projection.
          attention_output = tf.concat(attention_heads, axis=-1)

        # Run a linear projection of `hidden_size` then add a residual
        # with `layer_input`.
        with tf.variable_scope("output"):
          attention_output = tf.layers.dense(
              attention_output,
              hidden_size,
              kernel_initializer=create_initializer(initializer_range))
          attention_output = dropout(attention_output, hidden_dropout_prob)
          attention_output = layer_norm(attention_output + layer_input)

      # The activation is only applied to the "intermediate" hidden layer.
      with tf.variable_scope("intermediate"):
        intermediate_output = tf.layers.dense(
            attention_output,
            intermediate_size,
            activation=intermediate_act_fn,
            kernel_initializer=create_initializer(initializer_range))

      # Down-project back to `hidden_size` then add the residual.
      with tf.variable_scope("output"):
        layer_output = tf.layers.dense(
            intermediate_output,
            hidden_size,
            kernel_initializer=create_initializer(initializer_range))
        layer_output = dropout(layer_output, hidden_dropout_prob)
        layer_output = layer_norm(layer_output + attention_output)
        prev_output = layer_output
        all_layer_outputs.append(layer_output)

  if do_return_all_layers:
    final_outputs = []
    for layer_output in all_layer_outputs:
      final_output = reshape_from_matrix(layer_output, input_shape)
      final_outputs.append(final_output)
    return final_outputs
  else:
    final_output = reshape_from_matrix(prev_output, input_shape)
    return final_output

def attention_layer(from_tensor,
                    to_tensor,
                    attention_mask=None,
                    num_attention_heads=1,
                    size_per_head=512,
                    query_act=None,
                    key_act=None,
                    value_act=None,
                    attention_probs_dropout_prob=0.0,
                    initializer_range=0.02,
                    do_return_2d_tensor=False,
                    batch_size=None,
                    from_seq_length=None,
                    to_seq_length=None):
  """Performs multi-headed attention from `from_tensor` to `to_tensor`.

  This is an implementation of multi-headed attention based on "Attention
  is all you Need". If `from_tensor` and `to_tensor` are the same, then
  this is self-attention. Each timestep in `from_tensor` attends to the
  corresponding sequence in `to_tensor`, and returns a fixed-with vector.

  This function first projects `from_tensor` into a "query" tensor and
  `to_tensor` into "key" and "value" tensors. These are (effectively) a list
  of tensors of length `num_attention_heads`, where each tensor is of shape
  [batch_size, seq_length, size_per_head].

  Then, the query and key tensors are dot-producted and scaled. These are
  softmaxed to obtain attention probabilities. The value tensors are then
  interpolated by these probabilities, then concatenated back to a single
  tensor and returned.

  In practice, the multi-headed attention are done with transposes and
  reshapes rather than actual separate tensors.

  Args:
    from_tensor: float Tensor of shape [batch_size, from_seq_length,
      from_width].
    to_tensor: float Tensor of shape [batch_size, to_seq_length, to_width].
    attention_mask: (optional) int32 Tensor of shape [batch_size,
      from_seq_length, to_seq_length]. The values should be 1 or 0. The
      attention scores will effectively be set to -infinity for any positions in
      the mask that are 0, and will be unchanged for positions that are 1.
    num_attention_heads: int. Number of attention heads.
    size_per_head: int. Size of each attention head.
    query_act: (optional) Activation function for the query transform.
    key_act: (optional) Activation function for the key transform.
    value_act: (optional) Activation function for the value transform.
    attention_probs_dropout_prob: (optional) float. Dropout probability of the
      attention probabilities.
    initializer_range: float. Range of the weight initializer.
    do_return_2d_tensor: bool. If True, the output will be of shape [batch_size
      * from_seq_length, num_attention_heads * size_per_head]. If False, the
      output will be of shape [batch_size, from_seq_length, num_attention_heads
      * size_per_head].
    batch_size: (Optional) int. If the input is 2D, this might be the batch size
      of the 3D version of the `from_tensor` and `to_tensor`.
    from_seq_length: (Optional) If the input is 2D, this might be the seq length
      of the 3D version of the `from_tensor`.
    to_seq_length: (Optional) If the input is 2D, this might be the seq length
      of the 3D version of the `to_tensor`.

  Returns:
    float Tensor of shape [batch_size, from_seq_length,
      num_attention_heads * size_per_head]. (If `do_return_2d_tensor` is
      true, this will be of shape [batch_size * from_seq_length,
      num_attention_heads * size_per_head]).

  Raises:
    ValueError: Any of the arguments or tensor shapes are invalid.
  """

  def transpose_for_scores(input_tensor, batch_size, num_attention_heads,
                           seq_length, width):
    output_tensor = tf.reshape(
        input_tensor, [batch_size, seq_length, num_attention_heads, width])

    output_tensor = tf.transpose(output_tensor, [0, 2, 1, 3])
    return output_tensor

  from_shape = get_shape_list(from_tensor, expected_rank=[2, 3])
  to_shape = get_shape_list(to_tensor, expected_rank=[2, 3])

  if len(from_shape) != len(to_shape):
    raise ValueError(
        "The rank of `from_tensor` must match the rank of `to_tensor`.")

  if len(from_shape) == 3:
    batch_size = from_shape[0]
    from_seq_length = from_shape[1]
    to_seq_length = to_shape[1]
  elif len(from_shape) == 2:
    if (batch_size is None or from_seq_length is None or to_seq_length is None):
      raise ValueError(
          "When passing in rank 2 tensors to attention_layer, the values "
          "for `batch_size`, `from_seq_length`, and `to_seq_length` "
          "must all be specified.")

  # Scalar dimensions referenced here:
  #   B = batch size (number of sequences)
  #   F = `from_tensor` sequence length
  #   T = `to_tensor` sequence length
  #   N = `num_attention_heads`
  #   H = `size_per_head`

  from_tensor_2d = reshape_to_matrix(from_tensor)
  to_tensor_2d = reshape_to_matrix(to_tensor)

  # `query_layer` = [B*F, N*H]
  query_layer = tf.layers.dense(
      from_tensor_2d,
      num_attention_heads * size_per_head,
      activation=query_act,
      name="query",
      kernel_initializer=create_initializer(initializer_range))

  # `key_layer` = [B*T, N*H]
  key_layer = tf.layers.dense(
      to_tensor_2d,
      num_attention_heads * size_per_head,
      activation=key_act,
      name="key",
      kernel_initializer=create_initializer(initializer_range))

  # `value_layer` = [B*T, N*H]
  value_layer = tf.layers.dense(
      to_tensor_2d,
      num_attention_heads * size_per_head,
      activation=value_act,
      name="value",
      kernel_initializer=create_initializer(initializer_range))

  # `query_layer` = [B, N, F, H]
  query_layer = transpose_for_scores(query_layer, batch_size,
                                     num_attention_heads, from_seq_length,
                                     size_per_head)

  # `key_layer` = [B, N, T, H]
  key_layer = transpose_for_scores(key_layer, batch_size, num_attention_heads,
                                   to_seq_length, size_per_head)

  # Take the dot product between "query" and "key" to get the raw
  # attention scores.
  # `attention_scores` = [B, N, F, T]
  attention_scores = tf.matmul(query_layer, key_layer, transpose_b=True)
  attention_scores = tf.multiply(attention_scores,
                                 1.0 / math.sqrt(float(size_per_head)))

  if attention_mask is not None:
    # `attention_mask` = [B, 1, F, T]
    attention_mask = tf.expand_dims(attention_mask, axis=[1])

    # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
    # masked positions, this operation will create a tensor which is 0.0 for
    # positions we want to attend and -10000.0 for masked positions.
    adder = (1.0 - tf.cast(attention_mask, tf.float32)) * -10000.0

    # Since we are adding it to the raw scores before the softmax, this is
    # effectively the same as removing these entirely.
    attention_scores += adder

  # Normalize the attention scores to probabilities.
  # `attention_probs` = [B, N, F, T]
  attention_probs = tf.nn.softmax(attention_scores)

  # This is actually dropping out entire tokens to attend to, which might
  # seem a bit unusual, but is taken from the original Transformer paper.
  attention_probs = dropout(attention_probs, attention_probs_dropout_prob)

  # `value_layer` = [B, T, N, H]
  value_layer = tf.reshape(
      value_layer,
      [batch_size, to_seq_length, num_attention_heads, size_per_head])

  # `value_layer` = [B, N, T, H]
  value_layer = tf.transpose(value_layer, [0, 2, 1, 3])

  # `context_layer` = [B, N, F, H]
  context_layer = tf.matmul(attention_probs, value_layer)

  # `context_layer` = [B, F, N, H]
  context_layer = tf.transpose(context_layer, [0, 2, 1, 3])

  if do_return_2d_tensor:
    # `context_layer` = [B*F, N*H]
    context_layer = tf.reshape(
        context_layer,
        [batch_size * from_seq_length, num_attention_heads * size_per_head])
  else:
    # `context_layer` = [B, F, N*H]
    context_layer = tf.reshape(
        context_layer,
        [batch_size, from_seq_length, num_attention_heads * size_per_head])

  return context_layer