Python tensorflow.uint8方法代码示例

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def __init__(self, resolution=1024, num_channels=3, dtype='uint8', dynamic_range=[0,255], label_size=0, label_dtype='float32'):
        self.resolution         = resolution
        self.resolution_log2    = int(np.log2(resolution))
        self.shape              = [num_channels, resolution, resolution]
        self.dtype              = dtype
        self.dynamic_range      = dynamic_range
        self.label_size         = label_size
        self.label_dtype        = label_dtype
        self._tf_minibatch_var  = None
        self._tf_lod_var        = None
        self._tf_minibatch_np   = None
        self._tf_labels_np      = None

        assert self.resolution == 2 ** self.resolution_log2
        with tf.name_scope('Dataset'):
            self._tf_minibatch_var = tf.Variable(np.int32(0), name='minibatch_var')
            self._tf_lod_var = tf.Variable(np.int32(0), name='lod_var') 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def from_float32_to_uint8(
        tensor,
        tensor_key='tensor',
        min_key='min',
        max_key='max'):
    """

    :param tensor:
    :param tensor_key:
    :param min_key:
    :param max_key:
    :returns:
    """
    tensor_min = tf.reduce_min(tensor)
    tensor_max = tf.reduce_max(tensor)
    return {
        tensor_key: tf.cast(
            (tensor - tensor_min) / (tensor_max - tensor_min + 1e-16)
            * 255.9999, dtype=tf.uint8),
        min_key: tensor_min,
        max_key: tensor_max
    } 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def read_from_tfrecord(filenames):
    tfrecord_file_queue = tf.train.string_input_producer(filenames, name='queue')
    reader = tf.TFRecordReader()
    _, tfrecord_serialized = reader.read(tfrecord_file_queue)

    tfrecord_features = tf.parse_single_example(tfrecord_serialized, features={
        'label': tf.FixedLenFeature([],tf.int64),
        'shape': tf.FixedLenFeature([],tf.string),
        'image': tf.FixedLenFeature([],tf.string),
    }, name='features')

    image = tf.decode_raw(tfrecord_features['image'], tf.uint8)
    shape = tf.decode_raw(tfrecord_features['shape'], tf.int32)

    image = tf.reshape(image, shape)
    label = tfrecord_features['label']
    return label, shape, image 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def _extract_images(filename, num_images):
  """Extract the images into a numpy array.

  Args:
    filename: The path to an MNIST images file.
    num_images: The number of images in the file.

  Returns:
    A numpy array of shape [number_of_images, height, width, channels].
  """
  print('Extracting images from: ', filename)
  with gzip.open(filename) as bytestream:
    bytestream.read(16)
    buf = bytestream.read(
        _IMAGE_SIZE * _IMAGE_SIZE * num_images * _NUM_CHANNELS)
    data = np.frombuffer(buf, dtype=np.uint8)
    data = data.reshape(num_images, _IMAGE_SIZE, _IMAGE_SIZE, _NUM_CHANNELS)
  return data 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def _extract_labels(filename, num_labels):
  """Extract the labels into a vector of int64 label IDs.

  Args:
    filename: The path to an MNIST labels file.
    num_labels: The number of labels in the file.

  Returns:
    A numpy array of shape [number_of_labels]
  """
  print('Extracting labels from: ', filename)
  with gzip.open(filename) as bytestream:
    bytestream.read(8)
    buf = bytestream.read(1 * num_labels)
    labels = np.frombuffer(buf, dtype=np.uint8).astype(np.int64)
  return labels 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def read_and_decode(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    features = tf.parse_single_example(
        serialized_example,
      # Defaults are not specified since both keys are required.
        features={
            'image_raw': tf.FixedLenFeature([], tf.string),
        })

    image = tf.decode_raw(features['image_raw'], tf.uint8)
    image = tf.reshape(image, [227, 227, 6])

  # Convert from [0, 255] -> [-0.5, 0.5] floats.
    image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
    return tf.split(image, 2, 2) # 3rd dimension two parts 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def read_and_decode_aug(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    features = tf.parse_single_example(
        serialized_example,
      # Defaults are not specified since both keys are required.
        features={
            'image_raw': tf.FixedLenFeature([], tf.string),
        })

    image = tf.decode_raw(features['image_raw'], tf.uint8)
    image = tf.image.random_flip_left_right(tf.reshape(image, [227, 227, 6]))
  # Convert from [0, 255] -> [-0.5, 0.5] floats.
    image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
    image = tf.image.random_brightness(image, 0.01)
    image = tf.image.random_contrast(image, 0.95, 1.05)
    return tf.split(image, 2, 2) # 3rd dimension two parts 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def image_summary(predictions, targets, hparams):
  """Reshapes predictions and passes it to tensorboard.

  Args:
    predictions : The predicted image (logits).
    targets : The ground truth.
    hparams: model hparams.

  Returns:
    summary_proto: containing the summary images.
    weights: A Tensor of zeros of the same shape as predictions.
  """
  del hparams
  results = tf.cast(tf.argmax(predictions, axis=-1), tf.uint8)
  gold = tf.cast(targets, tf.uint8)
  summary1 = tf.summary.image("prediction", results, max_outputs=2)
  summary2 = tf.summary.image("data", gold, max_outputs=2)
  summary = tf.summary.merge([summary1, summary2])
  return summary, tf.zeros_like(predictions) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def summarize_video(video, prefix, max_outputs=1):
  """Summarize the video using image summaries starting with prefix."""
  video_shape = shape_list(video)
  if len(video_shape) != 5:
    raise ValueError("Assuming videos given as tensors in the format "
                     "[batch, time, height, width, channels] but got one "
                     "of shape: %s" % str(video_shape))
  if tf.contrib.eager.in_eager_mode():
    return
  if video.get_shape().as_list()[1] is None:
    tf.summary.image(
        "%s_last_frame" % prefix,
        tf.cast(video[:, -1, :, :, :], tf.uint8),
        max_outputs=max_outputs)
  else:
    for k in range(video_shape[1]):
      tf.summary.image(
          "%s_frame_%d" % (prefix, k),
          tf.cast(video[:, k, :, :, :], tf.uint8),
          max_outputs=max_outputs) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def get_mse_per_img(inp, otp, cast_to_int):
        """
        :param inp: NCHW
        :param otp: NCHW
        :param cast_to_int: if True, both inp and otp are casted to int32 before the error is calculated,
        to ensure real world errors (image pixels are always quantized). But the error is always casted back to
        float32 before a mean per image is calculated and returned
        :return: float32 tensor of shape (N,)
        """
        with tf.name_scope('mse_{}'.format('int' if cast_to_int else 'float')):
            if cast_to_int:
                # Values are expected to be in 0...255, i.e., uint8, but tf.square does not support uint8's
                inp, otp = tf.cast(inp, tf.int32), tf.cast(otp, tf.int32)
            squared_error = tf.square(otp - inp)
            squared_error_float = tf.to_float(squared_error)
            mse_per_image = tf.reduce_mean(squared_error_float, axis=[1, 2, 3])
            return mse_per_image 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def main():
    args = parse_args()

    with tf.Session(graph=tf.Graph()) as session:
        input_var = tf.placeholder(
            tf.uint8, (None, 128, 64, 3), name="images")
        image_var = tf.map_fn(
            lambda x: _preprocess(x), tf.cast(input_var, tf.float32),
            back_prop=False)

        factory_fn = _network_factory()
        features, _ = factory_fn(image_var, reuse=None)
        features = tf.identity(features, name="features")

        saver = tf.train.Saver(slim.get_variables_to_restore())
        saver.restore(session, args.checkpoint_in)

        output_graph_def = tf.graph_util.convert_variables_to_constants(
            session, tf.get_default_graph().as_graph_def(),
            [features.name.split(":")[0]])
        with tf.gfile.GFile(args.graphdef_out, "wb") as file_handle:
            file_handle.write(output_graph_def.SerializeToString()) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def __init__(self, fin, scale=1.0, fmask=None):
            self.fin = fin
            # read in distort
            with open(fin, 'r') as f:
                header = f.readline().rstrip()
                chunks = re.sub(r'[^0-9,]', '', header).split(',')
                self.mapu = np.zeros((int(chunks[1]), int(chunks[0])),
                                     dtype=np.float32)
                self.mapv = np.zeros((int(chunks[1]), int(chunks[0])),
                                     dtype=np.float32)
                for line in f.readlines():
                    chunks = line.rstrip().split(' ')
                    self.mapu[int(chunks[0]), int(chunks[1])] = float(chunks[3])
                    self.mapv[int(chunks[0]), int(chunks[1])] = float(chunks[2])
            # generate a mask
            self.mask = np.ones(self.mapu.shape, dtype=np.uint8)
            self.mask = cv2.remap(self.mask, self.mapu, self.mapv, cv2.INTER_LINEAR)
            kernel = np.ones((30, 30), np.uint8)
            self.mask = cv2.erode(self.mask, kernel, iterations=1)
            # crop black regions out
            h, w = self.mask.shape
            self.x_lim = [f(np.where(self.mask[int(h/2), :])[0])
                          for f in [np.min, np.max]]
            self.y_lim = [f(np.where(self.mask[:, int(w/2)])[0])
                          for f in [np.min, np.max]] 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def call(self, inputs):
    """Standard Keras call() method."""
    if inputs.dtype not in [tf.uint8, tf.int32, tf.int64]:
      inputs = tf.cast(inputs, dtype=tf.int32)

    if self.default_input_value is not None:
      default_input_value_tensor = tf.constant(
          int(self.default_input_value),
          dtype=inputs.dtype,
          name=DEFAULT_INPUT_VALUE_NAME)
      replacement = tf.zeros_like(inputs) + (self.num_buckets - 1)
      inputs = tf.where(
          tf.equal(inputs, default_input_value_tensor), replacement, inputs)

    # We can't use tf.gather_nd(self.kernel, inputs) as it doesn't support
    # constraints (constraint functions are not supported for IndexedSlices).
    # Instead we use matrix multiplication by one-hot encoding of the index.
    if self.units == 1:
      # This can be slightly faster as it uses matmul.
      return tf.matmul(
          tf.one_hot(tf.squeeze(inputs, axis=[-1]), depth=self.num_buckets),
          self.kernel)
    return tf.reduce_sum(
        tf.one_hot(inputs, axis=1, depth=self.num_buckets) * self.kernel,
        axis=1) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def parse_fn(self, serialized_example):
        features={
            'image/id_name': tf.FixedLenFeature([], tf.string),
            'image/height' : tf.FixedLenFeature([], tf.int64),
            'image/width'  : tf.FixedLenFeature([], tf.int64),
            'image/encoded': tf.FixedLenFeature([], tf.string),
        }
        for name in self.feature_list:
            features[name] = tf.FixedLenFeature([], tf.int64)

        example = tf.parse_single_example(serialized_example, features=features)
        image = tf.decode_raw(example['image/encoded'], tf.uint8)
        raw_height = tf.cast(example['image/height'], tf.int32)
        raw_width = tf.cast(example['image/width'], tf.int32)
        image = tf.reshape(image, [raw_height, raw_width, 3])
        image = tf.image.resize_images(image, size=[self.height, self.width])
        # from IPython import embed; embed(); exit()

        feature_val_list = [tf.cast(example[name], tf.float32) for name in self.feature_list]
        return image, feature_val_list 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import uint8 [as 别名]
def draw_keypoints_on_image_array(image,
                                  keypoints,
                                  color='red',
                                  radius=2,
                                  use_normalized_coordinates=True):
  """Draws keypoints on an image (numpy array).

  Args:
    image: a numpy array with shape [height, width, 3].
    keypoints: a numpy array with shape [num_keypoints, 2].
    color: color to draw the keypoints with. Default is red.
    radius: keypoint radius. Default value is 2.
    use_normalized_coordinates: if True (default), treat keypoint values as
      relative to the image.  Otherwise treat them as absolute.
  """
  image_pil = Image.fromarray(np.uint8(image)).convert('RGB')
  draw_keypoints_on_image(image_pil, keypoints, color, radius,
                          use_normalized_coordinates)
  np.copyto(image, np.array(image_pil))