Spaces:
Sleeping
Sleeping
File size: 6,682 Bytes
6fc683c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
# --------------------------------------------------------
# BEIT: BERT Pre-Training of Image Transformers (https://arxiv.org/abs/2106.08254)
# Github source: https://github.com/microsoft/unilm/tree/master/beit
# Copyright (c) 2021 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# By Hangbo Bao
# Based on timm code bases
# https://github.com/rwightman/pytorch-image-models/tree/master/timm
# --------------------------------------------------------'
import torch
import torchvision.transforms.functional as F
from PIL import Image
import warnings
import math
import random
import numpy as np
class ToNumpy:
def __call__(self, pil_img):
np_img = np.array(pil_img, dtype=np.uint8)
if np_img.ndim < 3:
np_img = np.expand_dims(np_img, axis=-1)
np_img = np.rollaxis(np_img, 2) # HWC to CHW
return np_img
class ToTensor:
def __init__(self, dtype=torch.float32):
self.dtype = dtype
def __call__(self, pil_img):
np_img = np.array(pil_img, dtype=np.uint8)
if np_img.ndim < 3:
np_img = np.expand_dims(np_img, axis=-1)
np_img = np.rollaxis(np_img, 2) # HWC to CHW
return torch.from_numpy(np_img).to(dtype=self.dtype)
_pil_interpolation_to_str = {
Image.NEAREST: 'PIL.Image.NEAREST',
Image.BILINEAR: 'PIL.Image.BILINEAR',
Image.BICUBIC: 'PIL.Image.BICUBIC',
Image.LANCZOS: 'PIL.Image.LANCZOS',
Image.HAMMING: 'PIL.Image.HAMMING',
Image.BOX: 'PIL.Image.BOX',
}
def _pil_interp(method):
if method == 'bicubic':
return Image.BICUBIC
elif method == 'lanczos':
return Image.LANCZOS
elif method == 'hamming':
return Image.HAMMING
else:
# default bilinear, do we want to allow nearest?
return Image.BILINEAR
_RANDOM_INTERPOLATION = (Image.BILINEAR, Image.BICUBIC)
class RandomResizedCropAndInterpolationWithTwoPic:
"""Crop the given PIL Image to random size and aspect ratio with random interpolation.
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, second_size=None, scale=(0.08, 1.0), ratio=(3. / 4., 4. / 3.),
interpolation='bilinear', second_interpolation='lanczos'):
if isinstance(size, tuple):
self.size = size
else:
self.size = (size, size)
if second_size is not None:
if isinstance(second_size, tuple):
self.second_size = second_size
else:
self.second_size = (second_size, second_size)
else:
self.second_size = None
if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
warnings.warn("range should be of kind (min, max)")
if interpolation == 'random':
self.interpolation = _RANDOM_INTERPOLATION
else:
self.interpolation = _pil_interp(interpolation)
self.second_interpolation = _pil_interp(second_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 = int(round(w / min(ratio)))
elif in_ratio > max(ratio):
h = img.size[1]
w = int(round(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, img):
"""
Args:
img (PIL Image): Image to be cropped and resized.
Returns:
PIL Image: Randomly cropped and resized image.
"""
i, j, h, w = self.get_params(img, self.scale, self.ratio)
if isinstance(self.interpolation, (tuple, list)):
interpolation = random.choice(self.interpolation)
else:
interpolation = self.interpolation
if self.second_size is None:
return F.resized_crop(img, i, j, h, w, self.size, interpolation)
else:
return F.resized_crop(img, i, j, h, w, self.size, interpolation), \
F.resized_crop(img, i, j, h, w, self.second_size, self.second_interpolation)
def __repr__(self):
if isinstance(self.interpolation, (tuple, list)):
interpolate_str = ' '.join([_pil_interpolation_to_str[x] for x in self.interpolation])
else:
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)
if self.second_size is not None:
format_string += ', second_size={0}'.format(self.second_size)
format_string += ', second_interpolation={0}'.format(_pil_interpolation_to_str[self.second_interpolation])
format_string += ')'
return format_string
|