python类VarLenFeature()的实例源码

def prepare_reader(self, filename_queue, batch_size=1024):

    reader = tf.TFRecordReader()
    _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def _make_schema(columns, types, default_values):
  """Input schema definition.

  Args:
    columns: column names for fields appearing in input.
    types: column types for fields appearing in input.
    default_values: default values for fields appearing in input.
  Returns:
    feature_set dictionary of string to *Feature.
  """
  result = {}
  assert len(columns) == len(types)
  assert len(columns) == len(default_values)
  for c, t, v in zip(columns, types, default_values):
    if isinstance(t, list):
      result[c] = tf.VarLenFeature(dtype=t[0])
    else:
      result[c] = tf.FixedLenFeature(shape=[], dtype=t, default_value=v)
  return dataset_schema.from_feature_spec(result)

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)

    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def _deserialize_image_record(cls, record):
        feature_map = {
            'image/encoded': tf.FixedLenFeature([], tf.string, ''),
            'image/class/label': tf.FixedLenFeature([1], tf.int64, -1),
            'image/class/text': tf.FixedLenFeature([], tf.string, ''),
            'image/object/bbox/xmin': tf.VarLenFeature(dtype=tf.float32),
            'image/object/bbox/ymin': tf.VarLenFeature(dtype=tf.float32),
            'image/object/bbox/xmax': tf.VarLenFeature(dtype=tf.float32),
            'image/object/bbox/ymax': tf.VarLenFeature(dtype=tf.float32)
        }
        with tf.name_scope('deserialize_image_record'):
            obj = tf.parse_single_example(record, feature_map)
            imgdata = obj['image/encoded']
            label = tf.cast(obj['image/class/label'], tf.int32)
            bbox = tf.stack([obj['image/object/bbox/%s' % x].values
                             for x in ['ymin', 'xmin', 'ymax', 'xmax']])
            bbox = tf.transpose(tf.expand_dims(bbox, 0), [0, 2, 1])
            text = obj['image/class/text']
            return imgdata, label, bbox, text

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def testWeightedSparseColumnDtypes(self):
    ids = tf.contrib.layers.sparse_column_with_keys(
        "ids", ["marlo", "omar", "stringer"])
    weighted_ids = tf.contrib.layers.weighted_sparse_column(ids, "weights")
    self.assertDictEqual(
        {"ids": tf.VarLenFeature(tf.string),
         "weights": tf.VarLenFeature(tf.float32)},
        weighted_ids.config)

    weighted_ids = tf.contrib.layers.weighted_sparse_column(ids, "weights",
                                                            dtype=tf.int32)
    self.assertDictEqual(
        {"ids": tf.VarLenFeature(tf.string),
         "weights": tf.VarLenFeature(tf.int32)},
        weighted_ids.config)

    with self.assertRaisesRegexp(ValueError,
                                 "dtype is not convertible to float"):
      weighted_ids = tf.contrib.layers.weighted_sparse_column(ids, "weights",
                                                              dtype=tf.string)

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def read_and_decode(filename_queue):
  reader = tf.TFRecordReader()
  _, serialized_example = reader.read(filename_queue)
  features = tf.parse_single_example(
      serialized_example,
      features={
          'height': tf.FixedLenFeature([], tf.int64),
          'width': tf.FixedLenFeature([], tf.int64),
          'image_raw': tf.FixedLenFeature([], tf.string),
          'label': tf.VarLenFeature(tf.int64),
      })

  image = tf.decode_raw(features['image_raw'], tf.uint8)
  image = tf.reshape(image, [730, 38])

  image = tf.cast(image, tf.float32) * (1. / 255) - 0.5

  label = tf.cast(features['label'], tf.int32)

  return image, label

def read_and_decode(filename_queue):
  reader = tf.TFRecordReader()
  _, serialized_example = reader.read(filename_queue)
  features = tf.parse_single_example(
      serialized_example,
      features={
          'height': tf.FixedLenFeature([], tf.int64),
          'width': tf.FixedLenFeature([], tf.int64),
          'image_raw': tf.FixedLenFeature([], tf.string),
          'label': tf.VarLenFeature(tf.int64),
      })

  image = tf.decode_raw(features['image_raw'], tf.uint8)
  image = tf.reshape(image, [730, 38])

  image = tf.cast(image, tf.float32) * (1. / 255) - 0.5

  label = tf.cast(features['label'], tf.int32)

  return image, label

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)

    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def read_and_decode_batch(filename_queue, batch_size, capacity, min_after_dequeue):
    """Dequeue a batch of data from the TFRecord.
    Args:
    filename_queue: Filename Queue of the TFRecord.
    batch_size: How many records dequeued each time.
    capacity: The capacity of the queue.
    min_after_dequeue: Ensures a minimum amount of shuffling of examples.
    Returns:
     List of the dequeued (batch_label, batch_ids, batch_values).
    """
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    batch_serialized_example = tf.train.shuffle_batch([serialized_example], 
        batch_size=batch_size, capacity=capacity, min_after_dequeue=min_after_dequeue)
    # The feature definition here should BE consistent with LibSVM TO TFRecord process.
    features = tf.parse_example(batch_serialized_example,
                                       features={
                                           "label": tf.FixedLenFeature([], tf.float32),
                                           "ids": tf.VarLenFeature(tf.int64),
                                           "values": tf.VarLenFeature(tf.float32)
                                       })
    batch_label = features["label"]
    batch_ids = features["ids"]
    batch_values = features["values"]
    return batch_label, batch_ids, batch_values

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def read_and_decode_single_example(filenames, shuffle=False, num_epochs=None):
    # first construct a queue containing a list of filenames.
    # this lets a user split up there dataset in multiple files to keep size down
    # filename_queue = tf.train.string_input_producer([filename], num_epochs=10)
    filename_queue = tf.train.string_input_producer(filenames,
                                                    shuffle=shuffle, num_epochs=num_epochs)

    reader = tf.TFRecordReader()
    # One can read a single serialized example from a filename
    # serialized_example is a Tensor of type string.
    _, serialized_ex = reader.read(filename_queue)
    context, sequences = tf.parse_single_sequence_example(serialized_ex,
                                                          context_features={
                                                              "seq_length": tf.FixedLenFeature([], dtype=tf.int64)
                                                          },
                                                          sequence_features={
                                                              "seq_feature": tf.VarLenFeature(dtype=tf.int64),
                                                              "label": tf.VarLenFeature(dtype=tf.int64)
                                                          })
    return context, sequences

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    ### Newly
    raw_labels = features["labels"]
    raw_coarse = tf.SparseTensor(indices = raw_labels.indices, values = tf.reshape(tf.gather(tf.constant(self.label_belongs, dtype = tf.int64), raw_labels.values), [-1]), dense_shape = raw_labels.dense_shape)
    coarse_labels = tf.sparse_to_indicator(raw_coarse, self.num_coarse_classes, name = 'coarse_transfer')
    coarse_labels.set_shape([None, self.num_coarse_classes])
    ###
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    # return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])
    ### Newly
    return features["video_id"], concatenated_features, labels, coarse_labels, tf.ones([tf.shape(serialized_examples)[0]])
    ###

def prepare_serialized_examples(self, serialized_examples):
    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_reader(self, filename_queue, batch_size=1024):
    """Creates a single reader thread for pre-aggregated YouTube 8M Examples.

    Args:
      filename_queue: A tensorflow queue of filename locations.

    Returns:
      A tuple of video indexes, features, labels, and padding data.
    """
    reader = tf.TFRecordReader()
    _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_reader(self, filename_queue, batch_size=1024):
    """Creates a single reader thread for pre-aggregated YouTube 8M Examples.

    Args:
      filename_queue: A tensorflow queue of filename locations.

    Returns:
      A tuple of video indexes, features, labels, and padding data.
    """
    reader = tf.TFRecordReader()
    _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "predictions": tf.FixedLenFeature([self.num_classes], tf.float32),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]]), features["predictions"]

def prepare_reader(self, filename_queue, batch_size=1024):
        """Creates a single reader thread for pre-aggregated YouTube 8M Examples.

        Args:
          filename_queue: A tensorflow queue of filename locations.

        Returns:
          A tuple of video indexes, features, labels, and padding data.
        """
        reader = tf.TFRecordReader()
        _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

        # set the mapping from the fields to data types in the proto
        num_features = len(self.feature_names)
        assert num_features > 0, "self.feature_names is empty!"
        assert len(self.feature_names) == len(self.feature_sizes), \
            "length of feature_names (={}) != length of feature_sizes (={})".format( \
                len(self.feature_names), len(self.feature_sizes))

        feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                       "predictions": tf.FixedLenFeature([self.num_classes], tf.float32),
                       "labels": tf.VarLenFeature(tf.int64)}

        features = tf.parse_example(serialized_examples, features=feature_map)

        return features["predictions"]

def prepare_writer(self, filename_queue, batch_size=1024):
    """Creates a single reader thread for pre-aggregated YouTube 8M Examples.

    Args:
      filename_queue: A tensorflow queue of filename locations.

    Returns:
      A tuple of video indexes, features, labels, and padding data.
    """
    reader = tf.TFRecordReader()
    _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_reader(self, filename_queue, batch_size=1024):
    """Creates a single reader thread for pre-aggregated YouTube 8M Examples.

    Args:
      filename_queue: A tensorflow queue of filename locations.

    Returns:
      A tuple of video indexes, features, labels, and padding data.
    """
    reader = tf.TFRecordReader()
    _, serialized_examples = reader.read_up_to(filename_queue, batch_size)

    # set the mapping from the fields to data types in the proto
    num_features = len(self.feature_names)
    assert num_features > 0, "self.feature_names is empty!"
    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    feature_map = {"video_id": tf.FixedLenFeature([], tf.string),
                   "labels": tf.VarLenFeature(tf.int64)}
    for feature_index in range(num_features):
      feature_map[self.feature_names[feature_index]] = tf.FixedLenFeature(
          [self.feature_sizes[feature_index]], tf.float32)

    features = tf.parse_example(serialized_examples, features=feature_map)
    labels = tf.sparse_to_indicator(features["labels"], self.num_classes)
    labels.set_shape([None, self.num_classes])
    concatenated_features = tf.concat([
        features[feature_name] for feature_name in self.feature_names], 1)

    return features["video_id"], concatenated_features, labels, tf.ones([tf.shape(serialized_examples)[0]])

def prepare_reader(self, filename_queue):

    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)

    contexts, features = tf.parse_single_sequence_example(
        serialized_example,
        context_features={
            "video_id": tf.FixedLenFeature([], tf.string),
            "labels": tf.VarLenFeature(tf.int64)},
        sequence_features={
            "rgb": tf.FixedLenSequenceFeature([], dtype=tf.string),
            "audio": tf.FixedLenSequenceFeature([], dtype=tf.string),
        })

    # read ground truth labels
    labels = (tf.cast(
        tf.sparse_to_dense(contexts["labels"].values, (self.num_classes,), 1,
            validate_indices=False),
        tf.bool))

    rgbs, num_frames = self.get_video_matrix(features["rgb"], 1024, self.max_frames)
    audios, num_frames = self.get_video_matrix(features["audio"], 1024, self.max_frames)

    batch_video_ids = tf.expand_dims(contexts["video_id"], 0)
    batch_rgbs = tf.expand_dims(rgbs, 0)
    batch_audios = tf.expand_dims(audios, 0)
    batch_labels = tf.expand_dims(labels, 0)
    batch_frames = tf.expand_dims(num_frames, 0)

    return batch_video_ids, batch_rgbs, batch_audios, batch_labels, batch_frames

def __init__(self, context_keys_to_features, sequence_keys_to_features,
               items_to_handlers):
    """Constructs the decoder.
    Args:
      keys_to_features: a dictionary from TF-Example keys to either
        tf.VarLenFeature or tf.FixedLenFeature instances. See tensorflow's
        parsing_ops.py.
      items_to_handlers: a dictionary from items (strings) to ItemHandler
        instances. Note that the ItemHandler's are provided the keys that they
        use to return the final item Tensors.
    """
    self._context_keys_to_features = context_keys_to_features
    self._sequence_keys_to_features = sequence_keys_to_features
    self._items_to_handlers = items_to_handlers

def decode(filename_queue):
    # Create TFRecords reader
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)

    # Feature keys in TFRecords example
    features = tf.parse_single_example(serialized_example, features={
        'id': tf.FixedLenFeature([], tf.string),
        'vector': tf.FixedLenFeature([], tf.string),
        'label': tf.VarLenFeature(tf.int64)
    })

    video_id = features['id']

    # Decode vector and pad to fixed size
    vector = tf.decode_raw(features['vector'], tf.float32)
    vector = tf.reshape(vector, [-1, 300])
    vector = tf.pad(vector, [[0, 40 - tf.shape(vector)[0]], [0, 0]])
    vector.set_shape([40, 300])

    # Get label index
    label = tf.sparse_to_indicator(features['label'], 4716)
    label.set_shape([4716])
    label = tf.cast(label, tf.float32)

    return video_id, vector, label

# Creates input pipeline for tensorflow networks

def _read_word_record(data_queue):

    reader = tf.TFRecordReader() # Construct a general reader
    key, example_serialized = reader.read(data_queue) 

    feature_map = {
        'image/encoded':  tf.FixedLenFeature( [], dtype=tf.string, 
                                              default_value='' ),
        'image/labels':   tf.VarLenFeature( dtype=tf.int64 ), 
        'image/width':    tf.FixedLenFeature( [1], dtype=tf.int64,
                                              default_value=1 ),
        'image/filename': tf.FixedLenFeature([], dtype=tf.string,
                                             default_value='' ),
        'text/string':     tf.FixedLenFeature([], dtype=tf.string,
                                             default_value='' ),
        'text/length':    tf.FixedLenFeature( [1], dtype=tf.int64,
                                              default_value=1 )
    }
    features = tf.parse_single_example( example_serialized, feature_map )

    image = tf.image.decode_jpeg( features['image/encoded'], channels=1 ) #gray
    width = tf.cast( features['image/width'], tf.int32) # for ctc_loss
    label = tf.serialize_sparse( features['image/labels'] ) # for batching
    length = features['text/length']
    text = features['text/string']
    filename = features['image/filename']
    return image,width,label,length,text,filename

def read_and_decode_single_example(self,filename,test=False):
    with tf.name_scope('TFRecordReader'):
        # first construct a queue containing a list of filenames.
        # this lets a user split up there dataset in multiple files to keep
        # size down
        files = [filename] if self.filenameNr==1 or test else [filename.format(i) for i in range(self.filenameNr)]
        filename_queue = tf.train.string_input_producer(files,
                                                        num_epochs=None)
        # Unlike the TFRecordWriter, the TFRecordReader is symbolic
        reader = tf.TFRecordReader()
        # One can read a single serialized example from a filename
        # serialized_example is a Tensor of type string.
        _, serialized_example = reader.read(filename_queue)
        # The serialized example is converted back to actual values.
        # One needs to describe the format of the objects to be returned
        features = tf.parse_single_example(
            serialized_example,
            features={
                # We know the length of both fields. If not the
                # tf.VarLenFeature could be used
                'seq_len': tf.FixedLenFeature([1], tf.int64),
                'target': tf.VarLenFeature(tf.int64),     
                'imageInput': tf.FixedLenFeature([self.height*self.width], tf.float32)
            })
        # now return the converted data
        imageInput = features['imageInput']
        seq_len     = features['seq_len']
        target     = features['target']
    return imageInput, seq_len , target