def transform(image: tf.Tensor, transforms) -> tf.Tensor:
"""Prepares input data for `image_ops.transform`."""
original_ndims = tf.rank(image)
transforms = tf.convert_to_tensor(transforms, dtype=tf.float32)
if transforms.shape.rank == 1:
transforms = transforms[None]
image = to_4d(image)
image = image_ops.transform(
images=image, transforms=transforms, interpolation='nearest')
return from_4d(image, original_ndims)
def rotate(inputs):
"""rotate image."""
inputs_shape = tf.shape(inputs)
batch_size = inputs_shape[0]
img_hd = tf.cast(inputs_shape[1], tf.float32)
img_wd = tf.cast(inputs_shape[2], tf.float32)
min_angle = LOWER * 2. * np.pi
max_angle = UPPER * 2. * np.pi
angles = tf.random.uniform(
shape=[batch_size], minval=min_angle, maxval=max_angle)
return image_preprocessing.transform(
inputs, image_preprocessing.get_rotation_matrix(angles, img_hd, img_wd))
def zoom(inputs):
"""zoom image."""
inputs_shape = tf.shape(inputs)
batch_size = inputs_shape[0]
img_hd = tf.cast(inputs_shape[1], tf.float32)
img_wd = tf.cast(inputs_shape[2], tf.float32)
height_zoom = tf.random.uniform(
shape=[batch_size, 1], minval=1. + LOWER, maxval=1. + UPPER)
width_zoom = tf.random.uniform(
shape=[batch_size, 1], minval=1. + LOWER, maxval=1. + UPPER)
zooms = tf.cast(
tf.concat([width_zoom, height_zoom], axis=1), dtype=tf.float32)
return image_preprocessing.transform(
inputs, image_preprocessing.get_zoom_matrix(zooms, img_hd, img_wd))