import math
import random
import numpy as np
from PIL import Image
def resize(img, size, interpolation=Image.BILINEAR):
r"""Resize the input PIL Image to the given size.
Args:
img (PIL Image): Image to be resized.
size (sequence or int): Desired output size. If size is a sequence like
(h, w), the output size will be matched to this. If size is an int,
the smaller edge of the image will be matched to this number maintaing
the aspect ratio. i.e, if height > width, then image will be rescaled to
:math:`\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)`
interpolation (int, optional): Desired interpolation. Default is
``PIL.Image.BILINEAR``
Returns:
PIL Image: Resized image.
"""
if isinstance(size, int):
w, h = img.size
if (w <= h and w == size) or (h <= w and h == size):
return img
if w < h:
ow = size
oh = int(size * h / w)
return img.resize((ow, oh), interpolation)
else:
oh = size
ow = int(size * w / h)
return img.resize((ow, oh), interpolation)
else:
return img.resize(size[::-1], interpolation)
def crop(img, i, j, h, w):
"""Crop the given PIL Image.
Args:
img (PIL Image): Image to be cropped.
i (int): i in (i,j) i.e coordinates of the upper left corner.
j (int): j in (i,j) i.e coordinates of the upper left corner.
h (int): Height of the cropped image.
w (int): Width of the cropped image.
Returns:
PIL Image: Cropped image.
"""
return img.crop((j, i, j + w, i + h))
def resized_crop(img, i, j, h, w, size, interpolation=Image.BILINEAR):
"""Crop the given PIL Image and resize it to desired size.
Notably used in :class:`~torchvision.transforms.RandomResizedCrop`.
Args:
img (PIL Image): Image to be cropped.
i (int): i in (i,j) i.e coordinates of the upper left corner
j (int): j in (i,j) i.e coordinates of the upper left corner
h (int): Height of the cropped image.
w (int): Width of the cropped image.
size (sequence or int): Desired output size. Same semantics as ``resize``.
interpolation (int, optional): Desired interpolation. Default is
``PIL.Image.BILINEAR``.
Returns:
PIL Image: Cropped image.
"""
img = crop(img, i, j, h, w)
img = resize(img, size, interpolation)
return img
class RandomResizedCrop(object):
"""Crop the given PIL Image to random size and aspect ratio.
A crop of random size (default: of 0.08 to 1.0) of the original size and a random
aspect ratio (default: of 3/4 to 4/3) of the original aspect ratio is made. This crop
is finally resized to given size.
This is popularly used to train the Inception networks.
Args:
size: expected output size of each edge
scale: range of size of the origin size cropped
ratio: range of aspect ratio of the origin aspect ratio cropped
interpolation: Default: PIL.Image.BILINEAR
"""
def __init__(self, size=None, scale=(0.08, 1.0), ratio=(3. / 4., 4. / 3.), interpolation=Image.BILINEAR):
if isinstance(size, tuple) or size is None:
self.size = size
else:
self.size = (size, size)
if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
warnings.warn("range should be of kind (min, max)")
self.interpolation = interpolation
self.scale = scale
self.ratio = ratio
@staticmethod
def get_params(img, scale, ratio):
"""Get parameters for ``crop`` for a random sized crop.
Args:
img (PIL Image): Image to be cropped.
scale (tuple): range of size of the origin size cropped
ratio (tuple): range of aspect ratio of the origin aspect ratio cropped
Returns:
tuple: params (i, j, h, w) to be passed to ``crop`` for a random
sized crop.
"""
area = img.size[0] * img.size[1]
for attempt in range(10):
target_area = random.uniform(*scale) * area
log_ratio = (math.log(ratio[0]), math.log(ratio[1]))
aspect_ratio = math.exp(random.uniform(*log_ratio))
w = int(round(math.sqrt(target_area * aspect_ratio)))
h = int(round(math.sqrt(target_area / aspect_ratio)))
if w <= img.size[0] and h <= img.size[1]:
i = random.randint(0, img.size[1] - h)
j = random.randint(0, img.size[0] - w)
return i, j, h, w
# Fallback to central crop
in_ratio = img.size[0] / img.size[1]
if (in_ratio < min(ratio)):
w = img.size[0]
h = w / min(ratio)
elif (in_ratio > max(ratio)):
h = img.size[1]
w = h * max(ratio)
else: # whole image
w = img.size[0]
h = img.size[1]
i = (img.size[1] - h) // 2
j = (img.size[0] - w) // 2
return i, j, h, w
def __call__(self, np_image):
"""
Args:
img (PIL Image): Image to be cropped and resized.
Returns:
PIL Image: Randomly cropped and resized image.
"""
if self.size is None:
size = np_image.shape
else:
size = self.size
image = Image.fromarray(np_image)
i, j, h, w = self.get_params(image, self.scale, self.ratio)
image = resized_crop(image, i, j, h, w, size, self.interpolation)
np_image = np.array(image)
return np_image
def __repr__(self):
interpolate_str = _pil_interpolation_to_str[self.interpolation]
format_string = self.__class__.__name__ + '(size={0}'.format(self.size)
format_string += ', scale={0}'.format(tuple(round(s, 4) for s in self.scale))
format_string += ', ratio={0}'.format(tuple(round(r, 4) for r in self.ratio))
format_string += ', interpolation={0})'.format(interpolate_str)
return format_string
