python类sparse_to_indicator()的实例源码

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 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 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])
    ### 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_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, 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 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