Python tensorflow.compat.v1.TFRecordReader() Examples

def reader(self):
    return tf.TFRecordReader() 

def get_example(self, batch_size):
    """Get a single example from the tfrecord file.

    Args:
      batch_size: Int, minibatch size.

    Returns:
      tf.Example protobuf parsed from tfrecord.
    """
    reader = tf.TFRecordReader()
    num_epochs = None if self.is_training else 1
    capacity = batch_size
    path_queue = tf.train.input_producer(
        [self.record_path],
        num_epochs=num_epochs,
        shuffle=self.is_training,
        capacity=capacity)
    unused_key, serialized_example = reader.read(path_queue)
    features = {
        "note_str": tf.FixedLenFeature([], dtype=tf.string),
        "pitch": tf.FixedLenFeature([1], dtype=tf.int64),
        "velocity": tf.FixedLenFeature([1], dtype=tf.int64),
        "audio": tf.FixedLenFeature([64000], dtype=tf.float32),
        "qualities": tf.FixedLenFeature([10], dtype=tf.int64),
        "instrument_source": tf.FixedLenFeature([1], dtype=tf.int64),
        "instrument_family": tf.FixedLenFeature([1], dtype=tf.int64),
    }
    example = tf.parse_single_example(serialized_example, features)
    return example 

def reader(self):
    """Return a reader for a single entry from the data set.

    See io_ops.py for details of Reader class.

    Returns:
      Reader object that reads the data set.
    """
    return tf.TFRecordReader() 

def build_input(tfrecord_paths):
  """Builds the graph's input.

  Args:
    tfrecord_paths: List of paths to the input TFRecords

  Returns:
    serialized_example_tensor: The next serialized example. String scalar Tensor
    image_tensor: The decoded image of the example. Uint8 tensor,
        shape=[1, None, None,3]
  """
  filename_queue = tf.train.string_input_producer(
      tfrecord_paths, shuffle=False, num_epochs=1)

  tf_record_reader = tf.TFRecordReader()
  _, serialized_example_tensor = tf_record_reader.read(filename_queue)
  features = tf.parse_single_example(
      serialized_example_tensor,
      features={
          standard_fields.TfExampleFields.image_encoded:
              tf.FixedLenFeature([], tf.string),
      })
  encoded_image = features[standard_fields.TfExampleFields.image_encoded]
  image_tensor = tf.image.decode_image(encoded_image, channels=3)
  image_tensor.set_shape([None, None, 3])
  image_tensor = tf.expand_dims(image_tensor, 0)

  return serialized_example_tensor, image_tensor 

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) 

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) 

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) 

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) 

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) 

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) 

def build(input_reader_config):
  """Builds a tensor dictionary based on the InputReader config.

  Args:
    input_reader_config: A input_reader_pb2.InputReader object.

  Returns:
    A tensor dict based on the input_reader_config.

  Raises:
    ValueError: On invalid input reader proto.
    ValueError: If no input paths are specified.
  """
  if not isinstance(input_reader_config, input_reader_pb2.InputReader):
    raise ValueError('input_reader_config not of type '
                     'input_reader_pb2.InputReader.')

  if input_reader_config.WhichOneof('input_reader') == 'tf_record_input_reader':
    config = input_reader_config.tf_record_input_reader
    if not config.input_path:
      raise ValueError('At least one input path must be specified in '
                       '`input_reader_config`.')
    _, string_tensor = parallel_reader.parallel_read(
        config.input_path[:],  # Convert `RepeatedScalarContainer` to list.
        reader_class=tf.TFRecordReader,
        num_epochs=(input_reader_config.num_epochs
                    if input_reader_config.num_epochs else None),
        num_readers=input_reader_config.num_readers,
        shuffle=input_reader_config.shuffle,
        dtypes=[tf.string, tf.string],
        capacity=input_reader_config.queue_capacity,
        min_after_dequeue=input_reader_config.min_after_dequeue)

    label_map_proto_file = None
    if input_reader_config.HasField('label_map_path'):
      label_map_proto_file = input_reader_config.label_map_path
    input_type = input_reader_config.input_type
    if input_type == input_reader_pb2.InputType.Value('TF_EXAMPLE'):
      decoder = tf_example_decoder.TfExampleDecoder(
          load_instance_masks=input_reader_config.load_instance_masks,
          instance_mask_type=input_reader_config.mask_type,
          label_map_proto_file=label_map_proto_file,
          load_context_features=input_reader_config.load_context_features)
      return decoder.decode(string_tensor)
    elif input_type == input_reader_pb2.InputType.Value('TF_SEQUENCE_EXAMPLE'):
      decoder = tf_sequence_example_decoder.TfSequenceExampleDecoder(
          label_map_proto_file=label_map_proto_file,
          load_context_features=input_reader_config.load_context_features)
      return decoder.decode(string_tensor)
    raise ValueError('Unsupported input_type.')
  raise ValueError('Unsupported input_reader_config.')