def random_square_crop(image_size, min_scale):
"""Generates a random square crop within an image.
Args:
image_size: a [height, width] tensor.
min_scale: how much the minimum dimension can be scaled down when taking a
crop. (e.g. if the image is 480 x 640, a min_scale of 0.8 means the output
crop can have a height and width between 480 and 384, which is 480 * 0.8.)
Returns:
output_begin, output_size and image_size.
output_begin and output_size are three element tensors specifying the shape
to crop using crop_sequence below. image_size is a two element
[height, width] tensor from the input.
"""
min_dim = tf.reduce_min(image_size[0:2])
sampled_size = tf.to_int32(
tf.to_float(min_dim) * tf.random_uniform([], min_scale, 1.0))
output_size = tf.stack([sampled_size, sampled_size, -1])
height_offset = tf.random_uniform([],
0,
image_size[0] - sampled_size + 1,
dtype=tf.int32)
width_offset = tf.random_uniform([],
0,
image_size[1] - sampled_size + 1,
dtype=tf.int32)
output_begin = tf.stack([height_offset, width_offset, 0])
return output_begin, output_size, image_size
def largest_square_crop(image_size):
"""For given image size, returns the maximum square, central crop.
Args:
image_size: a [height, width] tensor.
Returns:
output_begin, output_size and image_size.
output_begin and output_size are three element tensors specifying the shape
to crop using crop_sequence below. image_size is a two element
[height, width] tensor from the input.
"""
min_dim = tf.reduce_min(image_size[0:2])
output_size = tf.stack([min_dim, min_dim, -1])
height_offset = tf.to_int32((image_size[0] - min_dim) / 2)
width_offset = tf.to_int32((image_size[1] - min_dim) / 2)
output_begin = tf.stack([height_offset, width_offset, 0])
return output_begin, output_size, image_size
