Spaces:
Running
Running
File size: 15,220 Bytes
8a6df40 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 |
import torch
import math
import numbers
import random
import numpy as np
from PIL import Image, ImageOps
from torchvision import transforms
class RandomCrop(object):
def __init__(self, size, padding=0):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size # h, w
self.padding = padding
def __call__(self, sample):
img, mask = sample['image'], sample['label']
if self.padding > 0:
img = ImageOps.expand(img, border=self.padding, fill=0)
mask = ImageOps.expand(mask, border=self.padding, fill=0)
assert img.size == mask.size
w, h = img.size
th, tw = self.size # target size
if w == tw and h == th:
return {'image': img,
'label': mask}
if w < tw or h < th:
img = img.resize((tw, th), Image.BILINEAR)
mask = mask.resize((tw, th), Image.NEAREST)
return {'image': img,
'label': mask}
x1 = random.randint(0, w - tw)
y1 = random.randint(0, h - th)
img = img.crop((x1, y1, x1 + tw, y1 + th))
mask = mask.crop((x1, y1, x1 + tw, y1 + th))
return {'image': img,
'label': mask}
class RandomCrop_new(object):
def __init__(self, size, padding=0):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size # h, w
self.padding = padding
def __call__(self, sample):
img, mask = sample['image'], sample['label']
if self.padding > 0:
img = ImageOps.expand(img, border=self.padding, fill=0)
mask = ImageOps.expand(mask, border=self.padding, fill=0)
assert img.size == mask.size
w, h = img.size
th, tw = self.size # target size
if w == tw and h == th:
return {'image': img,
'label': mask}
new_img = Image.new('RGB',(tw,th),'black') # size is w x h; and 'white' is 255
new_mask = Image.new('L',(tw,th),'white') # same above
# if w > tw or h > th
x1 = y1 = 0
if w > tw:
x1 = random.randint(0,w - tw)
if h > th:
y1 = random.randint(0,h - th)
# crop
img = img.crop((x1,y1, x1 + tw, y1 + th))
mask = mask.crop((x1,y1, x1 + tw, y1 + th))
new_img.paste(img,(0,0))
new_mask.paste(mask,(0,0))
# x1 = random.randint(0, w - tw)
# y1 = random.randint(0, h - th)
# img = img.crop((x1, y1, x1 + tw, y1 + th))
# mask = mask.crop((x1, y1, x1 + tw, y1 + th))
return {'image': new_img,
'label': new_mask}
class Paste(object):
def __init__(self, size,):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size # h, w
def __call__(self, sample):
img, mask = sample['image'], sample['label']
assert img.size == mask.size
w, h = img.size
th, tw = self.size # target size
assert (w <=tw) and (h <= th)
if w == tw and h == th:
return {'image': img,
'label': mask}
new_img = Image.new('RGB',(tw,th),'black') # size is w x h; and 'white' is 255
new_mask = Image.new('L',(tw,th),'white') # same above
new_img.paste(img,(0,0))
new_mask.paste(mask,(0,0))
return {'image': new_img,
'label': new_mask}
class CenterCrop(object):
def __init__(self, size):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
w, h = img.size
th, tw = self.size
x1 = int(round((w - tw) / 2.))
y1 = int(round((h - th) / 2.))
img = img.crop((x1, y1, x1 + tw, y1 + th))
mask = mask.crop((x1, y1, x1 + tw, y1 + th))
return {'image': img,
'label': mask}
class RandomHorizontalFlip(object):
def __call__(self, sample):
img = sample['image']
mask = sample['label']
if random.random() < 0.5:
img = img.transpose(Image.FLIP_LEFT_RIGHT)
mask = mask.transpose(Image.FLIP_LEFT_RIGHT)
return {'image': img,
'label': mask}
class HorizontalFlip(object):
def __call__(self, sample):
img = sample['image']
mask = sample['label']
img = img.transpose(Image.FLIP_LEFT_RIGHT)
mask = mask.transpose(Image.FLIP_LEFT_RIGHT)
return {'image': img,
'label': mask}
class HorizontalFlip_only_img(object):
def __call__(self, sample):
img = sample['image']
mask = sample['label']
img = img.transpose(Image.FLIP_LEFT_RIGHT)
# mask = mask.transpose(Image.FLIP_LEFT_RIGHT)
return {'image': img,
'label': mask}
class RandomHorizontalFlip_cihp(object):
def __call__(self, sample):
img = sample['image']
mask = sample['label']
if random.random() < 0.5:
img = img.transpose(Image.FLIP_LEFT_RIGHT)
# mask = Image.open()
return {'image': img,
'label': mask}
class Normalize(object):
"""Normalize a tensor image with mean and standard deviation.
Args:
mean (tuple): means for each channel.
std (tuple): standard deviations for each channel.
"""
def __init__(self, mean=(0., 0., 0.), std=(1., 1., 1.)):
self.mean = mean
self.std = std
def __call__(self, sample):
img = np.array(sample['image']).astype(np.float32)
mask = np.array(sample['label']).astype(np.float32)
img /= 255.0
img -= self.mean
img /= self.std
return {'image': img,
'label': mask}
class Normalize_255(object):
"""Normalize a tensor image with mean and standard deviation. tf use 255.
Args:
mean (tuple): means for each channel.
std (tuple): standard deviations for each channel.
"""
def __init__(self, mean=(123.15, 115.90, 103.06), std=(1., 1., 1.)):
self.mean = mean
self.std = std
def __call__(self, sample):
img = np.array(sample['image']).astype(np.float32)
mask = np.array(sample['label']).astype(np.float32)
# img = 255.0
img -= self.mean
img /= self.std
img = img
img = img[[0,3,2,1],...]
return {'image': img,
'label': mask}
class Normalize_xception_tf(object):
# def __init__(self):
# self.rgb2bgr =
def __call__(self, sample):
img = np.array(sample['image']).astype(np.float32)
mask = np.array(sample['label']).astype(np.float32)
img = (img*2.0)/255.0 - 1
# print(img.shape)
# img = img[[0,3,2,1],...]
return {'image': img,
'label': mask}
class Normalize_xception_tf_only_img(object):
# def __init__(self):
# self.rgb2bgr =
def __call__(self, sample):
img = np.array(sample['image']).astype(np.float32)
# mask = np.array(sample['label']).astype(np.float32)
img = (img*2.0)/255.0 - 1
# print(img.shape)
# img = img[[0,3,2,1],...]
return {'image': img,
'label': sample['label']}
class Normalize_cityscapes(object):
"""Normalize a tensor image with mean and standard deviation.
Args:
mean (tuple): means for each channel.
std (tuple): standard deviations for each channel.
"""
def __init__(self, mean=(0., 0., 0.)):
self.mean = mean
def __call__(self, sample):
img = np.array(sample['image']).astype(np.float32)
mask = np.array(sample['label']).astype(np.float32)
img -= self.mean
img /= 255.0
return {'image': img,
'label': mask}
class ToTensor_(object):
"""Convert ndarrays in sample to Tensors."""
def __init__(self):
self.rgb2bgr = transforms.Lambda(lambda x:x[[2,1,0],...])
def __call__(self, sample):
# swap color axis because
# numpy image: H x W x C
# torch image: C X H X W
img = np.array(sample['image']).astype(np.float32).transpose((2, 0, 1))
mask = np.expand_dims(np.array(sample['label']).astype(np.float32), -1).transpose((2, 0, 1))
# mask[mask == 255] = 0
img = torch.from_numpy(img).float()
img = self.rgb2bgr(img)
mask = torch.from_numpy(mask).float()
return {'image': img,
'label': mask}
class ToTensor_only_img(object):
"""Convert ndarrays in sample to Tensors."""
def __init__(self):
self.rgb2bgr = transforms.Lambda(lambda x:x[[2,1,0],...])
def __call__(self, sample):
# swap color axis because
# numpy image: H x W x C
# torch image: C X H X W
img = np.array(sample['image']).astype(np.float32).transpose((2, 0, 1))
# mask = np.expand_dims(np.array(sample['label']).astype(np.float32), -1).transpose((2, 0, 1))
# mask[mask == 255] = 0
img = torch.from_numpy(img).float()
img = self.rgb2bgr(img)
# mask = torch.from_numpy(mask).float()
return {'image': img,
'label': sample['label']}
class FixedResize(object):
def __init__(self, size):
self.size = tuple(reversed(size)) # size: (h, w)
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
img = img.resize(self.size, Image.BILINEAR)
mask = mask.resize(self.size, Image.NEAREST)
return {'image': img,
'label': mask}
class Keep_origin_size_Resize(object):
def __init__(self, max_size, scale=1.0):
self.size = tuple(reversed(max_size)) # size: (h, w)
self.scale = scale
self.paste = Paste(int(max_size[0]*scale))
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
h, w = self.size
h = int(h*self.scale)
w = int(w*self.scale)
img = img.resize((h, w), Image.BILINEAR)
mask = mask.resize((h, w), Image.NEAREST)
return self.paste({'image': img,
'label': mask})
class Scale(object):
def __init__(self, size):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
w, h = img.size
if (w >= h and w == self.size[1]) or (h >= w and h == self.size[0]):
return {'image': img,
'label': mask}
oh, ow = self.size
img = img.resize((ow, oh), Image.BILINEAR)
mask = mask.resize((ow, oh), Image.NEAREST)
return {'image': img,
'label': mask}
class Scale_(object):
def __init__(self, scale):
self.scale = scale
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
w, h = img.size
ow = int(w*self.scale)
oh = int(h*self.scale)
img = img.resize((ow, oh), Image.BILINEAR)
mask = mask.resize((ow, oh), Image.NEAREST)
return {'image': img,
'label': mask}
class Scale_only_img(object):
def __init__(self, scale):
self.scale = scale
def __call__(self, sample):
img = sample['image']
mask = sample['label']
# assert img.size == mask.size
w, h = img.size
ow = int(w*self.scale)
oh = int(h*self.scale)
img = img.resize((ow, oh), Image.BILINEAR)
# mask = mask.resize((ow, oh), Image.NEAREST)
return {'image': img,
'label': mask}
class RandomSizedCrop(object):
def __init__(self, size):
self.size = size
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
for attempt in range(10):
area = img.size[0] * img.size[1]
target_area = random.uniform(0.45, 1.0) * area
aspect_ratio = random.uniform(0.5, 2)
w = int(round(math.sqrt(target_area * aspect_ratio)))
h = int(round(math.sqrt(target_area / aspect_ratio)))
if random.random() < 0.5:
w, h = h, w
if w <= img.size[0] and h <= img.size[1]:
x1 = random.randint(0, img.size[0] - w)
y1 = random.randint(0, img.size[1] - h)
img = img.crop((x1, y1, x1 + w, y1 + h))
mask = mask.crop((x1, y1, x1 + w, y1 + h))
assert (img.size == (w, h))
img = img.resize((self.size, self.size), Image.BILINEAR)
mask = mask.resize((self.size, self.size), Image.NEAREST)
return {'image': img,
'label': mask}
# Fallback
scale = Scale(self.size)
crop = CenterCrop(self.size)
sample = crop(scale(sample))
return sample
class RandomRotate(object):
def __init__(self, degree):
self.degree = degree
def __call__(self, sample):
img = sample['image']
mask = sample['label']
rotate_degree = random.random() * 2 * self.degree - self.degree
img = img.rotate(rotate_degree, Image.BILINEAR)
mask = mask.rotate(rotate_degree, Image.NEAREST)
return {'image': img,
'label': mask}
class RandomSized_new(object):
'''what we use is this class to aug'''
def __init__(self, size,scale1=0.5,scale2=2):
self.size = size
# self.scale = Scale(self.size)
self.crop = RandomCrop_new(self.size)
self.small_scale = scale1
self.big_scale = scale2
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
w = int(random.uniform(self.small_scale, self.big_scale) * img.size[0])
h = int(random.uniform(self.small_scale, self.big_scale) * img.size[1])
img, mask = img.resize((w, h), Image.BILINEAR), mask.resize((w, h), Image.NEAREST)
sample = {'image': img, 'label': mask}
# finish resize
return self.crop(sample)
# class Random
class RandomScale(object):
def __init__(self, limit):
self.limit = limit
def __call__(self, sample):
img = sample['image']
mask = sample['label']
assert img.size == mask.size
scale = random.uniform(self.limit[0], self.limit[1])
w = int(scale * img.size[0])
h = int(scale * img.size[1])
img, mask = img.resize((w, h), Image.BILINEAR), mask.resize((w, h), Image.NEAREST)
return {'image': img, 'label': mask} |