Python dataset_utils.has_labels方法代码示例

# 需要导入模块: from datasets import dataset_utils [as 别名]
# 或者: from datasets.dataset_utils import has_labels [as 别名]
def get_split(split_name, dataset_dir, file_pattern=None):
    """Gets a dataset tuple with instructions for reading flowers.

    Args:
      split_name: A train/validation split name.
      dataset_dir: The base directory of the dataset sources.
      file_pattern: The file pattern to use when matching the dataset sources.
        It is assumed that the pattern contains a '%s' string so that the split
        name can be inserted.
      reader: The TensorFlow reader type.

    Returns:
      A `Dataset` namedtuple.

    Raises:
      ValueError: if `split_name` is not a valid train/validation split.
    """
    if split_name not in SPLITS_TO_SIZES:
        raise ValueError('split name %s was not recognized.' % split_name)

    if not file_pattern:
        file_pattern = _FILE_PATTERN
    file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

    # Allowing None in the signature so that dataset_factory can use the default.
    # if reader is None:
    #     reader = tf.TFRecordReader

    labels_to_names = None
    if dataset_utils.has_labels(dataset_dir):
        labels_to_names = dataset_utils.read_label_file(dataset_dir)

    filenames = tf.gfile.Glob(file_pattern)

    return Dataset(
        filenames=filenames,
        num_samples=SPLITS_TO_SIZES[split_name],
        num_classes=_NUM_CLASSES,
        labels_to_names=labels_to_names,
        items_to_descriptions=_ITEMS_TO_DESCRIPTIONS
    ) 

# 需要导入模块: from datasets import dataset_utils [as 别名]
# 或者: from datasets.dataset_utils import has_labels [as 别名]
def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
  """Gets a dataset tuple with instructions for reading cifar10.

  Args:
    split_name: A train/test split name.
    dataset_dir: The base directory of the dataset sources.
    file_pattern: The file pattern to use when matching the dataset sources.
      It is assumed that the pattern contains a '%s' string so that the split
      name can be inserted.
    reader: The TensorFlow reader type.

  Returns:
    A `Dataset` namedtuple.

  Raises:
    ValueError: if `split_name` is not a valid train/test split.
  """
  if split_name not in SPLITS_TO_SIZES:
    raise ValueError('split name %s was not recognized.' % split_name)

  if not file_pattern:
    file_pattern = _FILE_PATTERN
  file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

  # Allowing None in the signature so that dataset_factory can use the default.
  if not reader:
    reader = tf.TFRecordReader

  keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='png'),
      'image/class/label': tf.FixedLenFeature(
          [], tf.int64, default_value=tf.zeros([], dtype=tf.int64)),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image(shape=[32, 32, 3]),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
  }

  decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

  labels_to_names = None
  if dataset_utils.has_labels(dataset_dir):
    labels_to_names = dataset_utils.read_label_file(dataset_dir)

  return slim.dataset.Dataset(
      data_sources=file_pattern,
      reader=reader,
      decoder=decoder,
      num_samples=SPLITS_TO_SIZES[split_name],
      items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
      num_classes=_NUM_CLASSES,
      labels_to_names=labels_to_names) 

# 需要导入模块: from datasets import dataset_utils [as 别名]
# 或者: from datasets.dataset_utils import has_labels [as 别名]
def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
  """Gets a dataset tuple with instructions for reading flowers.

  Args:
    split_name: A train/validation split name.
    dataset_dir: The base directory of the dataset sources.
    file_pattern: The file pattern to use when matching the dataset sources.
      It is assumed that the pattern contains a '%s' string so that the split
      name can be inserted.
    reader: The TensorFlow reader type.

  Returns:
    A `Dataset` namedtuple.

  Raises:
    ValueError: if `split_name` is not a valid train/validation split.
  """
  if split_name not in SPLITS_TO_SIZES:
    raise ValueError('split name %s was not recognized.' % split_name)

  if not file_pattern:
    file_pattern = _FILE_PATTERN
  file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

  # Allowing None in the signature so that dataset_factory can use the default.
  if reader is None:
    reader = tf.TFRecordReader

  keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='png'),
      'image/class/label': tf.FixedLenFeature(
          [], tf.int64, default_value=tf.zeros([], dtype=tf.int64)),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image(),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
  }

  decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

  labels_to_names = None
  if dataset_utils.has_labels(dataset_dir):
    labels_to_names = dataset_utils.read_label_file(dataset_dir)

  return slim.dataset.Dataset(
      data_sources=file_pattern,
      reader=reader,
      decoder=decoder,
      num_samples=SPLITS_TO_SIZES[split_name],
      items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
      num_classes=_NUM_CLASSES,
      labels_to_names=labels_to_names) 

# 需要导入模块: from datasets import dataset_utils [as 别名]
# 或者: from datasets.dataset_utils import has_labels [as 别名]
def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
  """Gets a dataset tuple with instructions for reading MNIST.

  Args:
    split_name: A train/test split name.
    dataset_dir: The base directory of the dataset sources.
    file_pattern: The file pattern to use when matching the dataset sources.
      It is assumed that the pattern contains a '%s' string so that the split
      name can be inserted.
    reader: The TensorFlow reader type.

  Returns:
    A `Dataset` namedtuple.

  Raises:
    ValueError: if `split_name` is not a valid train/test split.
  """
  if split_name not in _SPLITS_TO_SIZES:
    raise ValueError('split name %s was not recognized.' % split_name)

  if not file_pattern:
    file_pattern = _FILE_PATTERN
  file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

  # Allowing None in the signature so that dataset_factory can use the default.
  if reader is None:
    reader = tf.TFRecordReader

  keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='raw'),
      'image/class/label': tf.FixedLenFeature(
          [1], tf.int64, default_value=tf.zeros([1], dtype=tf.int64)),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image(shape=[28, 28, 1], channels=1),
      'label': slim.tfexample_decoder.Tensor('image/class/label', shape=[]),
  }

  decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

  labels_to_names = None
  if dataset_utils.has_labels(dataset_dir):
    labels_to_names = dataset_utils.read_label_file(dataset_dir)

  return slim.dataset.Dataset(
      data_sources=file_pattern,
      reader=reader,
      decoder=decoder,
      num_samples=_SPLITS_TO_SIZES[split_name],
      num_classes=_NUM_CLASSES,
      items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
      labels_to_names=labels_to_names) 

# 需要导入模块: from datasets import dataset_utils [as 别名]
# 或者: from datasets.dataset_utils import has_labels [as 别名]
def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
  """Gets a dataset tuple with instructions for reading flowers.

  Args:
    split_name: A train/validation split name.
    dataset_dir: The base directory of the dataset sources.
    file_pattern: The file pattern to use when matching the dataset sources.
      It is assumed that the pattern contains a '%s' string so that the split
      name can be inserted.
    reader: The TensorFlow reader type.

  Returns:
    A `Dataset` namedtuple.

  Raises:
    ValueError: if `split_name` is not a valid train/validation split.
  """
  if split_name not in SPLITS_TO_SIZES:
    raise ValueError('split name %s was not recognized.' % split_name)

  if not file_pattern:
    file_pattern = _FILE_PATTERN
  file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

  # Allowing None in the signature so that dataset_factory can use the default.
  if reader is None:
    reader = tf.TFRecordReader

  keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='jpg'),
      'image/class/label': tf.FixedLenFeature(
          [], tf.int64, default_value=tf.zeros([], dtype=tf.int64)),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image(),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
  }

  decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

  labels_to_names = None
  if dataset_utils.has_labels(dataset_dir):
    labels_to_names = dataset_utils.read_label_file(dataset_dir)

  return slim.dataset.Dataset(
      data_sources=file_pattern,
      reader=reader,
      decoder=decoder,
      num_samples=SPLITS_TO_SIZES[split_name],
      items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
      num_classes=_NUM_CLASSES,
      labels_to_names=labels_to_names)