python类string()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 transform_wav_data_op(wav_data_tensor, hparams, is_training,
                          jitter_amount_sec):
  """Transforms wav data."""
  def transform_wav_data(wav_data):
    """Transforms wav data."""
    # Only do audio transformations during training.
    if is_training:
      wav_data = audio_io.jitter_wav_data(wav_data, hparams.sample_rate,
                                          jitter_amount_sec)

    # Normalize.
    if hparams.normalize_audio:
      wav_data = audio_io.normalize_wav_data(wav_data, hparams.sample_rate)

    return [wav_data]

  return tf.py_func(
      transform_wav_data,
      [wav_data_tensor],
      tf.string,
      name='transform_wav_data_op')

def build_inputs_and_outputs(self):
    if self.frame_features:
      serialized_examples = tf.placeholder(tf.string, shape=(None,))

      fn = lambda x: self.build_prediction_graph(x)
      video_id_output, top_indices_output, top_predictions_output = (
          tf.map_fn(fn, serialized_examples,
                    dtype=(tf.string, tf.int32, tf.float32)))

    else:
      serialized_examples = tf.placeholder(tf.string, shape=(None,))

      video_id_output, top_indices_output, top_predictions_output = (
          self.build_prediction_graph(serialized_examples))

    inputs = {"example_bytes":
              saved_model_utils.build_tensor_info(serialized_examples)}

    outputs = {
        "video_id": saved_model_utils.build_tensor_info(video_id_output),
        "class_indexes": saved_model_utils.build_tensor_info(top_indices_output),
        "predictions": saved_model_utils.build_tensor_info(top_predictions_output)}

    return inputs, outputs

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 __init__(self):
    # Create a single Session to run all image coding calls.
    self._sess = tf.Session()

    # Initializes function that converts PNG to JPEG data.
    self._png_data = tf.placeholder(dtype=tf.string)
    image = tf.image.decode_png(self._png_data, channels=3)
    self._png_to_jpeg = tf.image.encode_jpeg(image, format='rgb', quality=100)

    # Initializes function that converts CMYK JPEG data to RGB JPEG data.
    self._cmyk_data = tf.placeholder(dtype=tf.string)
    image = tf.image.decode_jpeg(self._cmyk_data, channels=0)
    self._cmyk_to_rgb = tf.image.encode_jpeg(image, format='rgb', quality=100)

    # Initializes function that decodes RGB JPEG data.
    self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
    self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)

def _is_cmyk(filename):
  """Determine if file contains a CMYK JPEG format image.
  Args:
    filename: string, path of the image file.
  Returns:
    boolean indicating if the image is a JPEG encoded with CMYK color space.
  """
  # File list from:
  # https://github.com/cytsai/ilsvrc-cmyk-image-list
  blacklist = ['n01739381_1309.JPEG', 'n02077923_14822.JPEG',
               'n02447366_23489.JPEG', 'n02492035_15739.JPEG',
               'n02747177_10752.JPEG', 'n03018349_4028.JPEG',
               'n03062245_4620.JPEG', 'n03347037_9675.JPEG',
               'n03467068_12171.JPEG', 'n03529860_11437.JPEG',
               'n03544143_17228.JPEG', 'n03633091_5218.JPEG',
               'n03710637_5125.JPEG', 'n03961711_5286.JPEG',
               'n04033995_2932.JPEG', 'n04258138_17003.JPEG',
               'n04264628_27969.JPEG', 'n04336792_7448.JPEG',
               'n04371774_5854.JPEG', 'n04596742_4225.JPEG',
               'n07583066_647.JPEG', 'n13037406_4650.JPEG']
  return filename.split('/')[-1] in blacklist

def _find_image_bounding_boxes(filenames, image_to_bboxes):
  """Find the bounding boxes for a given image file.
  Args:
    filenames: list of strings; each string is a path to an image file.
    image_to_bboxes: dictionary mapping image file names to a list of
      bounding boxes. This list contains 0+ bounding boxes.
  Returns:
    List of bounding boxes for each image. Note that each entry in this
    list might contain from 0+ entries corresponding to the number of bounding
    box annotations for the image.
  """
  num_image_bbox = 0
  bboxes = []
  for f in filenames:
    basename = os.path.basename(f)
    if basename in image_to_bboxes:
      bboxes.append(image_to_bboxes[basename])
      num_image_bbox += 1
    else:
      bboxes.append([])
  print('Found %d images with bboxes out of %d images' % (
      num_image_bbox, len(filenames)))
  return bboxes

def _process_dataset(name, directory, num_shards, synset_to_human,
                     image_to_bboxes):
  """Process a complete data set and save it as a TFRecord.
  Args:
    name: string, unique identifier specifying the data set.
    directory: string, root path to the data set.
    num_shards: integer number of shards for this data set.
    synset_to_human: dict of synset to human labels, e.g.,
      'n02119022' --> 'red fox, Vulpes vulpes'
    image_to_bboxes: dictionary mapping image file names to a list of
      bounding boxes. This list contains 0+ bounding boxes.
  """
  filenames, synsets, labels = _find_image_files(directory, FLAGS.labels_file)
  humans = _find_human_readable_labels(synsets, synset_to_human)
  bboxes = _find_image_bounding_boxes(filenames, image_to_bboxes)
  _process_image_files(name, filenames, synsets, labels,
                       humans, bboxes, num_shards)

def _build_synset_lookup(imagenet_metadata_file):
  """Build lookup for synset to human-readable label.
  Args:
    imagenet_metadata_file: string, path to file containing mapping from
      synset to human-readable label.
      Assumes each line of the file looks like:
        n02119247    black fox
        n02119359    silver fox
        n02119477    red fox, Vulpes fulva
      where each line corresponds to a unique mapping. Note that each line is
      formatted as <synset>\t<human readable label>.
  Returns:
    Dictionary of synset to human labels, such as:
      'n02119022' --> 'red fox, Vulpes vulpes'
  """
  lines = tf.gfile.FastGFile(imagenet_metadata_file, 'r').readlines()
  synset_to_human = {}
  for l in lines:
    if l:
      parts = l.strip().split('\t')
      assert len(parts) == 2
      synset = parts[0]
      human = parts[1]
      synset_to_human[synset] = human
  return synset_to_human

def __init__(self):
    # Create a single Session to run all image coding calls.
    self._sess = tf.Session()

    # Initializes function that converts PNG to JPEG data.
    self._png_data = tf.placeholder(dtype=tf.string)
    image = tf.image.decode_png(self._png_data, channels=3)
    self._png_to_jpeg = tf.image.encode_jpeg(image, format='rgb', quality=100)

    # Initializes function that converts CMYK JPEG data to RGB JPEG data.
    self._cmyk_data = tf.placeholder(dtype=tf.string)
    image = tf.image.decode_jpeg(self._cmyk_data, channels=0)
    self._cmyk_to_rgb = tf.image.encode_jpeg(image, format='rgb', quality=100)

    # Initializes function that decodes RGB JPEG data.
    self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
    self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)

def _is_cmyk(filename):
  """Determine if file contains a CMYK JPEG format image.
  Args:
    filename: string, path of the image file.
  Returns:
    boolean indicating if the image is a JPEG encoded with CMYK color space.
  """
  # File list from:
  # https://github.com/cytsai/ilsvrc-cmyk-image-list
  blacklist = ['n01739381_1309.JPEG', 'n02077923_14822.JPEG',
               'n02447366_23489.JPEG', 'n02492035_15739.JPEG',
               'n02747177_10752.JPEG', 'n03018349_4028.JPEG',
               'n03062245_4620.JPEG', 'n03347037_9675.JPEG',
               'n03467068_12171.JPEG', 'n03529860_11437.JPEG',
               'n03544143_17228.JPEG', 'n03633091_5218.JPEG',
               'n03710637_5125.JPEG', 'n03961711_5286.JPEG',
               'n04033995_2932.JPEG', 'n04258138_17003.JPEG',
               'n04264628_27969.JPEG', 'n04336792_7448.JPEG',
               'n04371774_5854.JPEG', 'n04596742_4225.JPEG',
               'n07583066_647.JPEG', 'n13037406_4650.JPEG']
  return filename.split('/')[-1] in blacklist

def _find_image_bounding_boxes(filenames, image_to_bboxes):
  """Find the bounding boxes for a given image file.
  Args:
    filenames: list of strings; each string is a path to an image file.
    image_to_bboxes: dictionary mapping image file names to a list of
      bounding boxes. This list contains 0+ bounding boxes.
  Returns:
    List of bounding boxes for each image. Note that each entry in this
    list might contain from 0+ entries corresponding to the number of bounding
    box annotations for the image.
  """
  num_image_bbox = 0
  bboxes = []
  for f in filenames:
    basename = os.path.basename(f)
    if basename in image_to_bboxes:
      bboxes.append(image_to_bboxes[basename])
      num_image_bbox += 1
    else:
      bboxes.append([])
  print('Found %d images with bboxes out of %d images' % (
      num_image_bbox, len(filenames)))
  return bboxes

def _process_dataset(name, directory, num_shards, synset_to_human,
                     image_to_bboxes):
  """Process a complete data set and save it as a TFRecord.
  Args:
    name: string, unique identifier specifying the data set.
    directory: string, root path to the data set.
    num_shards: integer number of shards for this data set.
    synset_to_human: dict of synset to human labels, e.g.,
      'n02119022' --> 'red fox, Vulpes vulpes'
    image_to_bboxes: dictionary mapping image file names to a list of
      bounding boxes. This list contains 0+ bounding boxes.
  """
  filenames, synsets, labels = _find_image_files(directory, FLAGS.labels_file)
  humans = _find_human_readable_labels(synsets, synset_to_human)
  bboxes = _find_image_bounding_boxes(filenames, image_to_bboxes)
  _process_image_files(name, filenames, synsets, labels,
                       humans, bboxes, num_shards)

def read_and_decode(self, example_serialized):
        """ Read and decode binarized, raw MNIST dataset from .tfrecords file generated by MNIST.py """
        num = self.flags['num_classes']

        # Parse features from binary file
        features = tf.parse_single_example(
            example_serialized,
            features={
                'image': tf.FixedLenFeature([], tf.string),
                'label': tf.FixedLenFeature([num], tf.int64, default_value=[-1] * num),
                'height': tf.FixedLenFeature([], tf.int64),
                'width': tf.FixedLenFeature([], tf.int64),
                'depth': tf.FixedLenFeature([], tf.int64),
            })
        # Return the converted data
        label = features['label']
        image = tf.decode_raw(features['image'], tf.float32)
        image.set_shape([784])
        image = tf.reshape(image, [28, 28, 1])
        image = (image - 0.5) * 2  # max value = 1, min value = -1
        return image, tf.cast(label, tf.int32)

def read_and_decode(self, example_serialized):
        """ Read and decode binarized, raw MNIST dataset from .tfrecords file generated by MNIST.py """
        features = tf.parse_single_example(
            example_serialized,
            features={
                'image': tf.FixedLenFeature([], tf.string),
                'label': tf.FixedLenFeature([self.flags['num_classes']], tf.int64, default_value=[-1]*self.flags['num_classes']),
                'height': tf.FixedLenFeature([], tf.int64),
                'width': tf.FixedLenFeature([], tf.int64),
                'depth': tf.FixedLenFeature([], tf.int64),
            })
        # now return the converted data
        label = features['label']
        image = tf.decode_raw(features['image'], tf.float32)
        image.set_shape([784])
        image = tf.reshape(image, [28, 28, 1])
        image = (image - 0.5) * 2  # max value = 1, min value = -1
        return image, tf.cast(label, tf.int32)

def testSimple(self):
    labels = [9, 3, 0]
    records = [self._record(labels[0], 0, 128, 255),
               self._record(labels[1], 255, 0, 1),
               self._record(labels[2], 254, 255, 0)]
    contents = b"".join([record for record, _ in records])
    expected = [expected for _, expected in records]
    filename = os.path.join(self.get_temp_dir(), "cifar")
    open(filename, "wb").write(contents)

    with self.test_session() as sess:
      q = tf.FIFOQueue(99, [tf.string], shapes=())
      q.enqueue([filename]).run()
      q.close().run()
      result = cifar10_input.read_cifar10(q)

      for i in range(3):
        key, label, uint8image = sess.run([
            result.key, result.label, result.uint8image])
        self.assertEqual("%s:%d" % (filename, i), tf.compat.as_text(key))
        self.assertEqual(labels[i], label)
        self.assertAllEqual(expected[i], uint8image)

      with self.assertRaises(tf.errors.OutOfRangeError):
        sess.run([result.key, result.uint8image])

def __init__(self, data_dir, data_list, input_size, random_scale, coord):
        '''Initialise an ImageReader.

        Args:
          data_dir: path to the directory with images and masks.
          data_list: path to the file with lines of the form '/path/to/image /path/to/mask'.
          input_size: a tuple with (height, width) values, to which all the images will be resized.
          random_scale: whether to randomly scale the images prior to random crop.
          coord: TensorFlow queue coordinator.
        '''
        self.data_dir = data_dir
        self.data_list = data_list
        self.input_size = input_size
        self.coord = coord

        self.image_list, self.label_list = read_labeled_image_list(self.data_dir, self.data_list)
        self.images = tf.convert_to_tensor(self.image_list, dtype=tf.string)
        self.labels = tf.convert_to_tensor(self.label_list, dtype=tf.string)
        self.queue = tf.train.slice_input_producer([self.images, self.labels],
                                                   shuffle=input_size is not None) # Not shuffling if it is val.
        self.image, self.label = read_images_from_disk(self.queue, self.input_size, random_scale)

def decode_jpeg(image_buffer, scope=None):
    """Decode a JPEG string into one 3-D float image Tensor.

  Args:
    image_buffer: scalar string Tensor.
    scope: Optional scope for op_scope.
  Returns:
    3-D float Tensor with values ranging from [0, 1).
  """
    with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
        # Decode the string as an RGB JPEG.
        # Note that the resulting image contains an unknown height and width
        # that is set dynamically by decode_jpeg. In other words, the height
        # and width of image is unknown at compile-time.
        image = tf.image.decode_jpeg(image_buffer, channels=3)

        # After this point, all image pixels reside in [0,1)
        # until the very end, when they're rescaled to (-1, 1).  The various
        # adjust_* ops all require this range for dtype float.
        image = tf.image.convert_image_dtype(image, dtype=tf.float32)
        return image

def decode_jpeg(image_buffer, scope=None):
    """Decode a JPEG string into one 3-D float image Tensor.

  Args:
    image_buffer: scalar string Tensor.
    scope: Optional scope for op_scope.
  Returns:
    3-D float Tensor with values ranging from [0, 1).
  """
    with tf.name_scope(values=[image_buffer], name=scope, default_name='decode_jpeg'):
        # Decode the string as an RGB JPEG.
        # Note that the resulting image contains an unknown height and width
        # that is set dynamically by decode_jpeg. In other words, the height
        # and width of image is unknown at compile-time.
        image = tf.image.decode_jpeg(image_buffer, channels=3)

        # After this point, all image pixels reside in [0,1)
        # until the very end, when they're rescaled to (-1, 1).  The various
        # adjust_* ops all require this range for dtype float.
        image = tf.image.convert_image_dtype(image, dtype=tf.float32)
        return image

def _test_metric_spec(self, metric_spec, hyps, refs, expected_scores):
    """Tests a MetricSpec"""
    predictions = {"predicted_tokens": tf.placeholder(dtype=tf.string)}
    labels = {"target_tokens": tf.placeholder(dtype=tf.string)}

    value, update_op = metric_spec.create_metric_ops(None, labels, predictions)

    with self.test_session() as sess:
      sess.run(tf.global_variables_initializer())
      sess.run(tf.local_variables_initializer())

      scores = []
      for hyp, ref in zip(hyps, refs):
        hyp = hyp.split(" ")
        ref = ref.split(" ")
        sess.run(update_op, {
            predictions["predicted_tokens"]: [hyp],
            labels["target_tokens"]: [ref]
        })
        scores.append(sess.run(value))

      for score, expected in zip(scores, expected_scores):
        np.testing.assert_almost_equal(score, expected, decimal=2)
        np.testing.assert_almost_equal(score, expected, decimal=2)