models/bls2017.py [184:236]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    x_hat = self.synthesis_transform(y_hat)
    # Remove batch dimension, and crop away any extraneous padding.
    x_hat = x_hat[0, :x_shape[0], :x_shape[1], :]
    # Then cast back to 8-bit integer.
    return tf.saturate_cast(tf.round(x_hat), tf.uint8)


def check_image_size(image, patchsize):
  shape = tf.shape(image)
  return shape[0] >= patchsize and shape[1] >= patchsize and shape[-1] == 3


def crop_image(image, patchsize):
  image = tf.image.random_crop(image, (patchsize, patchsize, 3))
  return tf.cast(image, tf.float32)


def get_dataset(name, split, args):
  """Creates input data pipeline from a TF Datasets dataset."""
  with tf.device("/cpu:0"):
    dataset = tfds.load(name, split=split, shuffle_files=True)
    if split == "train":
      dataset = dataset.repeat()
    dataset = dataset.filter(
        lambda x: check_image_size(x["image"], args.patchsize))
    dataset = dataset.map(
        lambda x: crop_image(x["image"], args.patchsize))
    dataset = dataset.batch(args.batchsize, drop_remainder=True)
  return dataset


def get_custom_dataset(split, args):
  """Creates input data pipeline from custom PNG images."""
  with tf.device("/cpu:0"):
    files = glob.glob(args.train_glob)
    if not files:
      raise RuntimeError(f"No training images found with glob "
                         f"'{args.train_glob}'.")
    dataset = tf.data.Dataset.from_tensor_slices(files)
    dataset = dataset.shuffle(len(files), reshuffle_each_iteration=True)
    if split == "train":
      dataset = dataset.repeat()
    dataset = dataset.map(
        lambda x: crop_image(read_png(x), args.patchsize),
        num_parallel_calls=args.preprocess_threads)
    dataset = dataset.batch(args.batchsize, drop_remainder=True)
  return dataset


def train(args):
  """Instantiates and trains the model."""
  if args.check_numerics:
    tf.debugging.enable_check_numerics()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models/ms2020.py [428:480]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    x_hat = self.synthesis_transform(y_hat)
    # Remove batch dimension, and crop away any extraneous padding.
    x_hat = x_hat[0, :x_shape[0], :x_shape[1], :]
    # Then cast back to 8-bit integer.
    return tf.saturate_cast(tf.round(x_hat), tf.uint8)


def check_image_size(image, patchsize):
  shape = tf.shape(image)
  return shape[0] >= patchsize and shape[1] >= patchsize and shape[-1] == 3


def crop_image(image, patchsize):
  image = tf.image.random_crop(image, (patchsize, patchsize, 3))
  return tf.cast(image, tf.float32)


def get_dataset(name, split, args):
  """Creates input data pipeline from a TF Datasets dataset."""
  with tf.device("/cpu:0"):
    dataset = tfds.load(name, split=split, shuffle_files=True)
    if split == "train":
      dataset = dataset.repeat()
    dataset = dataset.filter(
        lambda x: check_image_size(x["image"], args.patchsize))
    dataset = dataset.map(
        lambda x: crop_image(x["image"], args.patchsize))
    dataset = dataset.batch(args.batchsize, drop_remainder=True)
  return dataset


def get_custom_dataset(split, args):
  """Creates input data pipeline from custom PNG images."""
  with tf.device("/cpu:0"):
    files = glob.glob(args.train_glob)
    if not files:
      raise RuntimeError(f"No training images found with glob "
                         f"'{args.train_glob}'.")
    dataset = tf.data.Dataset.from_tensor_slices(files)
    dataset = dataset.shuffle(len(files), reshuffle_each_iteration=True)
    if split == "train":
      dataset = dataset.repeat()
    dataset = dataset.map(
        lambda x: crop_image(read_png(x), args.patchsize),
        num_parallel_calls=args.preprocess_threads)
    dataset = dataset.batch(args.batchsize, drop_remainder=True)
  return dataset


def train(args):
  """Instantiates and trains the model."""
  if args.check_numerics:
    tf.debugging.enable_check_numerics()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -