tensor2tensor/data_generators/scitail.py [43:66]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  @property
  def is_generate_per_split(self):
    return True

  @property
  def dataset_splits(self):
    return [{
        "split": problem.DatasetSplit.TRAIN,
        "shards": 10,
    }, {
        "split": problem.DatasetSplit.EVAL,
        "shards": 1,
    }]

  @property
  def approx_vocab_size(self):
    return 2**13

  @property
  def num_classes(self):
    return 2

  def class_labels(self, data_dir):
    del data_dir
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensor2tensor/data_generators/yelp_polarity.py [37:60]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  @property
  def is_generate_per_split(self):
    return True

  @property
  def dataset_splits(self):
    return [{
        "split": problem.DatasetSplit.TRAIN,
        "shards": 10,
    }, {
        "split": problem.DatasetSplit.EVAL,
        "shards": 1,
    }]

  @property
  def approx_vocab_size(self):
    return 2**13  # 8k vocab suffices for this small dataset.

  @property
  def num_classes(self):
    return 2

  def class_labels(self, data_dir):
    del data_dir
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -