Python v1.random_crop方法代码示例

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def _distort_image(self, image):
    """Distort one image for training a network.

    Adopted the standard data augmentation scheme that is widely used for
    this dataset: the images are first zero-padded with 4 pixels on each side,
    then randomly cropped to again produce distorted images; half of the images
    are then horizontally mirrored.

    Args:
      image: input image.
    Returns:
      distorted image.
    """
    image = tf.image.resize_image_with_crop_or_pad(
        image, self.height + 8, self.width + 8)
    distorted_image = tf.random_crop(image,
                                     [self.height, self.width, self.depth])
    # Randomly flip the image horizontally.
    distorted_image = tf.image.random_flip_left_right(distorted_image)
    if self.summary_verbosity >= 3:
      tf.summary.image('distorted_image', tf.expand_dims(distorted_image, 0))
    return distorted_image 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def patch_discriminator(x, filters=64, filter_size=5, n=4,
                        name="patch_discrim"):
  """Patch descriminator."""
  with tf.variable_scope(name):
    x_shape = shape_list(x)
    spatial_dims = [x_shape[1] // 4, x_shape[2] // 4]
    x = tf.random_crop(x, [x_shape[0]] + spatial_dims + [x_shape[3]])
    for i in range(n):
      x = general_conv(
          x=x,
          num_filters=filters * 2**i,
          filter_size=filter_size,
          stride=2 if i != n - 1 else 1,
          stddev=0.02,
          padding="SAME",
          name="c%d" % i,
          do_norm="instance" if i != 0 else False,
          do_relu=i != n - 1,
          relufactor=0.2)
    x = tf.reduce_mean(x, [1, 2])
    return x 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def randomize(images, init_shape, expand_shape=None, crop_shape=None,
              vertical_flip=False):
  """Returns a function that randomly translates and flips images."""
  def random_image(image):
    """Randmly translates and flips images."""
    image = tf.reshape(image, init_shape)
    current_shape = init_shape
    if expand_shape is not None and expand_shape != current_shape:
      if expand_shape[-1] != current_shape[-1]:
        raise ValueError('Number channels is not specified correctly.')
      image = tf.image.resize_image_with_crop_or_pad(
          image, expand_shape[0], expand_shape[1])
      current_shape = expand_shape
    if crop_shape is not None and crop_shape != current_shape:
      image = tf.random_crop(image, crop_shape)
    if vertical_flip:
      image = tf.image.random_flip_left_right(image)
    return image
  return tf.map_fn(random_image, images) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def should_distort_images(flip_left_right, random_crop, random_scale,
                          random_brightness):
  """Whether any distortions are enabled, from the input flags.

  Args:
    flip_left_right: Boolean whether to randomly mirror images horizontally.
    random_crop: Integer percentage setting the total margin used around the
    crop box.
    random_scale: Integer percentage of how much to vary the scale by.
    random_brightness: Integer range to randomly multiply the pixel values by.

  Returns:
    Boolean value indicating whether any distortions should be applied.
  """
  return (flip_left_right or (random_crop != 0) or (random_scale != 0) or
          (random_brightness != 0)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def image_augmentation(images, do_colors=False, crop_size=None):
  """Image augmentation: cropping, flipping, and color transforms."""
  if crop_size is None:
    crop_size = [299, 299]
  images = tf.random_crop(images, crop_size + [3])
  images = tf.image.random_flip_left_right(images)
  if do_colors:  # More augmentation, but might be slow.
    images = tf.image.random_brightness(images, max_delta=32. / 255.)
    images = tf.image.random_saturation(images, lower=0.5, upper=1.5)
    images = tf.image.random_hue(images, max_delta=0.2)
    images = tf.image.random_contrast(images, lower=0.5, upper=1.5)
  return images 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def cifar_image_augmentation(images):
  """Image augmentation suitable for CIFAR-10/100.

  As described in https://arxiv.org/pdf/1608.06993v3.pdf (page 5).

  Args:
    images: a Tensor.
  Returns:
    Tensor of the same shape as images.
  """
  images = tf.image.resize_image_with_crop_or_pad(images, 40, 40)
  images = tf.random_crop(images, [32, 32, 3])
  images = tf.image.random_flip_left_right(images)
  return images 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def vqa_v2_preprocess_image(
    image,
    height,
    width,
    mode,
    resize_side=512,
    distort=True,
    image_model_fn="resnet_v1_152",
):
  """vqa v2 preprocess image."""

  image = tf.image.convert_image_dtype(image, dtype=tf.float32)
  assert resize_side > 0
  if resize_side:
    image = _aspect_preserving_resize(image, resize_side)
  if mode == tf.estimator.ModeKeys.TRAIN:
    image = tf.random_crop(image, [height, width, 3])
  else:
    # Central crop, assuming resize_height > height, resize_width > width.
    image = tf.image.resize_image_with_crop_or_pad(image, height, width)

  image = tf.clip_by_value(image, 0.0, 1.0)

  if mode == tf.estimator.ModeKeys.TRAIN and distort:
    image = _flip(image)
    num_distort_cases = 4
    # pylint: disable=unnecessary-lambda
    image = _apply_with_random_selector(
        image, lambda x, ordering: _distort_color(x, ordering),
        num_cases=num_distort_cases)

  if image_model_fn.startswith("resnet_v1"):
    # resnet_v1 uses vgg preprocessing
    image = image * 255.
    image = _mean_image_subtraction(image, [_R_MEAN, _G_MEAN, _B_MEAN])
  elif image_model_fn.startswith("resnet_v2"):
    # resnet v2 uses inception preprocessing
    image = tf.subtract(image, 0.5)
    image = tf.multiply(image, 2.0)

  return image 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def preprocess_example(self, example, mode, hparams):

    # Crop to target shape instead of down-sampling target, leaving target
    # of maximum available resolution.
    target_shape = (self.output_dim, self.output_dim, self.num_channels)
    example["targets"] = tf.random_crop(example["targets"], target_shape)

    example["inputs"] = image_utils.resize_by_area(example["targets"],
                                                   self.input_dim)

    if self.inpaint_fraction is not None and self.inpaint_fraction > 0:

      mask = random_square_mask((self.input_dim,
                                 self.input_dim,
                                 self.num_channels),
                                self.inpaint_fraction)

      example["inputs"] = tf.multiply(
          tf.convert_to_tensor(mask, dtype=tf.int64),
          example["inputs"])

      if self.input_dim is None:
        raise ValueError("Cannot train in-painting for examples with "
                         "only targets (i.e. input_dim is None, "
                         "implying there are only targets to be "
                         "generated).")

    return example 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def get_wavenet_batch(self, batch_size, length=64000):
    """Get the Tensor expressions from the reader.

    Args:
      batch_size: The integer batch size.
      length: Number of timesteps of a cropped sample to produce.

    Returns:
      A dict of key:tensor pairs. This includes "pitch", "wav", and "key".
    """
    example = self.get_example(batch_size)
    wav = example["audio"]
    wav = tf.slice(wav, [0], [64000])
    pitch = tf.squeeze(example["pitch"])
    key = tf.squeeze(example["note_str"])

    if self.is_training:
      # random crop
      crop = tf.random_crop(wav, [length])
      crop = tf.reshape(crop, [1, length])
      key, crop, pitch = tf.train.shuffle_batch(
          [key, crop, pitch],
          batch_size,
          num_threads=4,
          capacity=500 * batch_size,
          min_after_dequeue=200 * batch_size)
    else:
      # fixed center crop
      offset = (64000 - length) // 2  # 24320
      crop = tf.slice(wav, [offset], [length])
      crop = tf.reshape(crop, [1, length])
      key, crop, pitch = tf.train.shuffle_batch(
          [key, crop, pitch],
          batch_size,
          num_threads=4,
          capacity=500 * batch_size,
          min_after_dequeue=200 * batch_size)

    crop = tf.reshape(tf.cast(crop, tf.float32), [batch_size, length])
    pitch = tf.cast(pitch, tf.int32)
    return {"pitch": pitch, "wav": crop, "key": key} 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def crop(image, is_training, crop_size):
  h, w, c = crop_size[0], crop_size[1], image.shape[-1]

  if is_training:
    return tf.random_crop(image, [h, w, c])
  else:
    # Central crop for now. (See Table 5 in Appendix of
    # https://arxiv.org/pdf/1703.07737.pdf for why)
    dy = (tf.shape(image)[0] - h)//2
    dx = (tf.shape(image)[1] - w)//2
    return tf.image.crop_to_bounding_box(image, dy, dx, h, w) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def preprocess_train(x, width, height):
  """Pre-processing applied to training data set.

  Args:
    x: Input image float32 tensor.
    width: int specifying intended width in pixels of image after preprocessing.
    height: int specifying intended height in pixels of image after
      preprocessing.
  Returns:
    x: transformed input with random crops, flips and reflection.
  """
  x = pad_input(x, crop_dim=4)
  x = tf.random_crop(x, [width, height, 3])
  x = tf.image.random_flip_left_right(x)
  return x 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import random_crop [as 别名]
def preprocess_for_train(image,
                         output_height,
                         output_width,
                         padding=_PADDING,
                         add_image_summaries=True,
                         use_grayscale=False):
  """Preprocesses the given image for training.

  Note that the actual resizing scale is sampled from
    [`resize_size_min`, `resize_size_max`].

  Args:
    image: A `Tensor` representing an image of arbitrary size.
    output_height: The height of the image after preprocessing.
    output_width: The width of the image after preprocessing.
    padding: The amound of padding before and after each dimension of the image.
    add_image_summaries: Enable image summaries.
    use_grayscale: Whether to convert the image from RGB to grayscale.

  Returns:
    A preprocessed image.
  """
  if add_image_summaries:
    tf.summary.image('image', tf.expand_dims(image, 0))

  # Transform the image to floats.
  image = tf.to_float(image)
  if use_grayscale:
    image = tf.image.rgb_to_grayscale(image)
  if padding > 0:
    image = tf.pad(image, [[padding, padding], [padding, padding], [0, 0]])
  # Randomly crop a [height, width] section of the image.
  distorted_image = tf.random_crop(image,
                                   [output_height, output_width, 3])

  # Randomly flip the image horizontally.
  distorted_image = tf.image.random_flip_left_right(distorted_image)

  if add_image_summaries:
    tf.summary.image('distorted_image', tf.expand_dims(distorted_image, 0))

  # Because these operations are not commutative, consider randomizing
  # the order their operation.
  distorted_image = tf.image.random_brightness(distorted_image,
                                               max_delta=63)
  distorted_image = tf.image.random_contrast(distorted_image,
                                             lower=0.2, upper=1.8)
  # Subtract off the mean and divide by the variance of the pixels.
  return tf.image.per_image_standardization(distorted_image)