Python tokenization.validate_case_matches_checkpoint() Examples

The following are 22 code examples of tokenization.validate_case_matches_checkpoint(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tokenization , or try the search function .
Example #1
Source File: run_KorQuAD.py    From KorQuAD-beginner with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")

  # if FLAGS.do_predict:
  #   if not FLAGS.predict_faile:
  #     raise ValueError(
  #         "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #2
Source File: run_squad.py    From coref with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #3
Source File: run_squad.py    From MedicalRelationExtraction with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #4
Source File: run_squad.py    From BERT-for-Sequence-Labeling-and-Text-Classification with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #5
Source File: run_squad.py    From pynlp with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #6
Source File: run_squad.py    From training with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #7
Source File: run_squad.py    From BERT-sentiment--classification with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #8
Source File: run_squad.py    From QGforQA with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #9
Source File: run_squad.py    From bert-qa with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #10
Source File: run_squad.py    From delft with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #11
Source File: run_squad.py    From uai-sdk with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #12
Source File: run_squad.py    From Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #13
Source File: run_squad.py    From KorQuAD-beginner with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #14
Source File: run_squad.py    From bert with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #15
Source File: run_squad.py    From nlp_research with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #16
Source File: run_squad.py    From gobbli with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #17
Source File: run_squad.py    From BERT-Chinese-Annotation with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #18
Source File: run_squad.py    From text_bert_cnn with MIT License 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #19
Source File: run_squad.py    From models with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)
  if FLAGS.disable_v2_bevior:
    tf.compat.v1.disable_v2_behavior()

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  bert_config.set_additional_options(FLAGS.precision, 
                                     FLAGS.experimental_gelu)

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #20
Source File: run_squad.py    From models with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)
  if FLAGS.disable_v2_bevior:
    tf.compat.v1.disable_v2_behavior()

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  bert_config.set_additional_options(FLAGS.precision, 
                                     FLAGS.experimental_gelu, 
                                     FLAGS.optimized_softmax)

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #21
Source File: run_squad.py    From models with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)

  if not FLAGS.do_train and not FLAGS.do_predict:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")

  if FLAGS.precision:
    bert_config.precision = FLAGS.precision

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))
Example #22
Source File: run_clmrc.py    From Cross-Lingual-MRC with Apache License 2.0 5 votes vote down vote up 
def validate_flags_or_throw(bert_config):
  """Validate the input FLAGS or throw an exception."""
  tokenization.validate_case_matches_checkpoint(FLAGS.do_lower_case,
                                                FLAGS.init_checkpoint)
  
  if not FLAGS.do_train and not FLAGS.do_predict and not FLAGS.do_eval:
    raise ValueError("At least one of `do_train` or `do_predict` must be True.")

  if FLAGS.do_train:
    if not FLAGS.train_file:
      raise ValueError(
          "If `do_train` is True, then `train_file` must be specified.")
  if FLAGS.do_predict:
    if not FLAGS.predict_file:
      raise ValueError(
          "If `do_predict` is True, then `predict_file` must be specified.")
  if FLAGS.do_eval:
    if not FLAGS.eval_file:
      raise ValueError(
          "If `do_eval` is True, then `eval_file` must be specified.")

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  if FLAGS.max_seq_length <= FLAGS.max_query_length + 3:
    raise ValueError(
        "The max_seq_length (%d) must be greater than max_query_length "
        "(%d) + 3" % (FLAGS.max_seq_length, FLAGS.max_query_length))


############################