-
Notifications
You must be signed in to change notification settings - Fork 2
/
transforms.py
337 lines (273 loc) · 10.5 KB
/
transforms.py
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
from __future__ import division
import torch
import math
import random
from PIL import Image, ImageOps
import numpy as np
import numbers
import types
import collections
class Compose(object):
"""Composes several transforms together.
Args:
transforms (List[Transform]): list of transforms to compose.
Example:
>>> transforms.Compose([
>>> transforms.CenterCrop(10),
>>> transforms.ToTensor(),
>>> ])
"""
def __init__(self, transforms):
self.transforms = transforms
def __call__(self, img):
for t in self.transforms:
img = t(img)
return img
class ToTensor(object):
"""Converts a PIL.Image or numpy.ndarray (H x W x C) in the range
[0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0].
"""
def __call__(self, pic):
if isinstance(pic, np.ndarray):
# handle numpy array
img = torch.from_numpy(pic.transpose((2, 0, 1)))
# backard compability
# return img.float().div(255)
return img.float()
# handle PIL Image
if pic.mode == 'I':
img = torch.from_numpy(np.array(pic, np.int32, copy=False))
elif pic.mode == 'I;16':
img = torch.from_numpy(np.array(pic, np.int16, copy=False))
else:
img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes()))
# PIL image mode: 1, L, P, I, F, RGB, YCbCr, RGBA, CMYK
if pic.mode == 'YCbCr':
nchannel = 3
elif pic.mode == 'I;16':
nchannel = 1
else:
nchannel = len(pic.mode)
img = img.view(pic.size[1], pic.size[0], nchannel)
# put it from HWC to CHW format
# yikes, this transpose takes 80% of the loading time/CPU
img = img.transpose(0, 1).transpose(0, 2).contiguous()
if isinstance(img, torch.ByteTensor):
# return img.float().div(255)
return img.float()
else:
return img
class ToTensor_BGR(object):
"""Converts a PIL.Image or numpy.ndarray (H x W x C) in the range
[0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0].
"""
def __call__(self, pic):
if isinstance(pic, np.ndarray):
# handle numpy array
img = torch.from_numpy(pic.transpose((2, 0, 1)))
# backard compability
# return img.float().div(255)
return img.float()
# handle PIL Image
if pic.mode == 'I':
img = torch.from_numpy(np.array(pic, np.int32, copy=False))
elif pic.mode == 'I;16':
img = torch.from_numpy(np.array(pic, np.int16, copy=False))
else:
img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes()))
# PIL image mode: 1, L, P, I, F, RGB, YCbCr, RGBA, CMYK
if pic.mode == 'YCbCr':
nchannel = 3
elif pic.mode == 'I;16':
nchannel = 1
else:
nchannel = len(pic.mode)
img = img.view(pic.size[1], pic.size[0], nchannel)
# put it from HWC to CHW format
# yikes, this transpose takes 80% of the loading time/CPU
img = img.transpose(0, 1).transpose(0, 2).contiguous()
if isinstance(img, torch.ByteTensor):
# return img.float().div(255)
img_bgr = img[[2, 1, 0], :, :]
return img_bgr.float()
else:
return img
class ToPILImage(object):
"""Converts a torch.*Tensor of shape C x H x W or a numpy ndarray of shape
H x W x C to a PIL.Image while preserving value range.
"""
def __call__(self, pic):
npimg = pic
mode = None
if isinstance(pic, torch.FloatTensor):
# pic = pic.mul(255).byte()
pic = pic.byte()
if torch.is_tensor(pic):
npimg = np.transpose(pic.numpy(), (1, 2, 0))
assert isinstance(npimg, np.ndarray), 'pic should be Tensor or ndarray'
if npimg.shape[2] == 1:
npimg = npimg[:, :, 0]
if npimg.dtype == np.uint8:
mode = 'L'
if npimg.dtype == np.int16:
mode = 'I;16'
if npimg.dtype == np.int32:
mode = 'I'
elif npimg.dtype == np.float32:
mode = 'F'
else:
if npimg.dtype == np.uint8:
mode = 'RGB'
assert mode is not None, '{} is not supported'.format(npimg.dtype)
return Image.fromarray(npimg, mode=mode)
class Normalize(object):
"""Given mean: (R, G, B) and std: (R, G, B),
will normalize each channel of the torch.*Tensor, i.e.
channel = (channel - mean) / std
"""
def __init__(self, mean, std):
self.mean = mean
self.std = std
def __call__(self, tensor):
# TODO: make efficient
for t, m, s in zip(tensor, self.mean, self.std):
t.sub_(m).div_(s)
return tensor
class Subtract(object):
"""Given mean: (R, G, B) and std: (R, G, B),
will normalize each channel of the torch.*Tensor, i.e.
channel = (channel - mean) / std
"""
def __init__(self, mean):
self.mean = mean
# self.std = std
def __call__(self, tensor):
# TODO: make efficient
for t, m in zip(tensor, self.mean):
t.sub_(m)
return tensor
class Scale(object):
"""Rescale the input PIL.Image to the given size.
Args:
size (sequence or int): Desired output size. If size is a sequence like
(w, h), output size will be matched to this. If size is an int,
smaller edge of the image will be matched to this number.
i.e, if height > width, then image will be rescaled to
(size * height / width, size)
interpolation (int, optional): Desired interpolation. Default is
``PIL.Image.BILINEAR``
"""
def __init__(self, size, interpolation=Image.BILINEAR):
assert isinstance(size, int) or (isinstance(size, collections.Iterable) and len(size) == 2)
self.size = size
self.interpolation = interpolation
def __call__(self, img):
"""
Args:
img (PIL.Image): Image to be scaled.
Returns:
PIL.Image: Rescaled image.
"""
if isinstance(self.size, int):
w, h = img.size
if (w <= h and w == self.size) or (h <= w and h == self.size):
return img
if w < h:
ow = self.size
oh = int(self.size * h / w)
return img.resize((ow, oh), self.interpolation)
else:
oh = self.size
ow = int(self.size * w / h)
return img.resize((ow, oh), self.interpolation)
else:
return img.resize(self.size, self.interpolation)
class CenterCrop(object):
"""Crops the given PIL.Image at the center to have a region of
the given size. size can be a tuple (target_height, target_width)
or an integer, in which case the target will be of a square shape (size, size)
"""
def __init__(self, size):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size
def __call__(self, img):
w, h = img.size
th, tw = self.size
x1 = int(round((w - tw) / 2.))
y1 = int(round((h - th) / 2.))
return img.crop((x1, y1, x1 + tw, y1 + th))
class Pad(object):
"""Pads the given PIL.Image on all sides with the given "pad" value"""
def __init__(self, padding, fill=0):
assert isinstance(padding, numbers.Number)
assert isinstance(fill, numbers.Number) or isinstance(fill, str) or isinstance(fill, tuple)
self.padding = padding
self.fill = fill
def __call__(self, img):
return ImageOps.expand(img, border=self.padding, fill=self.fill)
class Lambda(object):
"""Applies a lambda as a transform."""
def __init__(self, lambd):
assert isinstance(lambd, types.LambdaType)
self.lambd = lambd
def __call__(self, img):
return self.lambd(img)
class RandomCrop(object):
"""Crops the given PIL.Image at a random location to have a region of
the given size. size can be a tuple (target_height, target_width)
or an integer, in which case the target will be of a square shape (size, size)
"""
def __init__(self, size, padding=0):
if isinstance(size, numbers.Number):
self.size = (int(size), int(size))
else:
self.size = size
self.padding = padding
def __call__(self, img):
if self.padding > 0:
img = ImageOps.expand(img, border=self.padding, fill=0)
w, h = img.size
th, tw = self.size
if w == tw and h == th:
return img
x1 = random.randint(0, w - tw)
y1 = random.randint(0, h - th)
return img.crop((x1, y1, x1 + tw, y1 + th))
class RandomHorizontalFlip(object):
"""Randomly horizontally flips the given PIL.Image with a probability of 0.5
"""
def __call__(self, img):
if random.random() < 0.5:
return img.transpose(Image.FLIP_LEFT_RIGHT)
return img
class RandomSizedCrop(object):
"""Random crop the given PIL.Image to a random size of (0.08 to 1.0) of the original size
and and a random aspect ratio of 3/4 to 4/3 of the original aspect ratio
This is popularly used to train the Inception networks
size: size of the smaller edge
interpolation: Default: PIL.Image.BILINEAR
"""
def __init__(self, size, interpolation=Image.BILINEAR):
self.size = size
self.interpolation = interpolation
def __call__(self, img):
for attempt in range(10):
area = img.size[0] * img.size[1]
target_area = random.uniform(0.08, 1.0) * area
aspect_ratio = random.uniform(3. / 4, 4. / 3)
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))
assert(img.size == (w, h))
return img.resize((self.size, self.size), self.interpolation)
# Fallback
scale = Scale(self.size, interpolation=self.interpolation)
crop = CenterCrop(self.size)
return crop(scale(img))