File size: 27,325 Bytes
938e515
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
# -*- coding: utf-8 -*-
# Copyright (c) Facebook, Inc. and its affiliates.
"""
Implement many useful :class:`Augmentation`.
"""
import numpy as np
import sys
from numpy import random
from typing import Tuple
import torch
from fvcore.transforms.transform import (
    BlendTransform,
    CropTransform,
    HFlipTransform,
    NoOpTransform,
    PadTransform,
    Transform,
    TransformList,
    VFlipTransform,
)
from PIL import Image

from detectron2.structures import Boxes, pairwise_iou

from .augmentation import Augmentation, _transform_to_aug
from .transform import ExtentTransform, ResizeTransform, RotationTransform

__all__ = [
    "FixedSizeCrop",
    "RandomApply",
    "RandomBrightness",
    "RandomContrast",
    "RandomCrop",
    "RandomExtent",
    "RandomFlip",
    "RandomSaturation",
    "RandomLighting",
    "RandomRotation",
    "Resize",
    "ResizeScale",
    "ResizeShortestEdge",
    "RandomCrop_CategoryAreaConstraint",
    "RandomResize",
    "MinIoURandomCrop",
]


class RandomApply(Augmentation):
    """
    Randomly apply an augmentation with a given probability.
    """

    def __init__(self, tfm_or_aug, prob=0.5):
        """
        Args:
            tfm_or_aug (Transform, Augmentation): the transform or augmentation
                to be applied. It can either be a `Transform` or `Augmentation`
                instance.
            prob (float): probability between 0.0 and 1.0 that
                the wrapper transformation is applied
        """
        super().__init__()
        self.aug = _transform_to_aug(tfm_or_aug)
        assert 0.0 <= prob <= 1.0, f"Probablity must be between 0.0 and 1.0 (given: {prob})"
        self.prob = prob

    def get_transform(self, *args):
        do = self._rand_range() < self.prob
        if do:
            return self.aug.get_transform(*args)
        else:
            return NoOpTransform()

    def __call__(self, aug_input):
        do = self._rand_range() < self.prob
        if do:
            return self.aug(aug_input)
        else:
            return NoOpTransform()


class RandomFlip(Augmentation):
    """
    Flip the image horizontally or vertically with the given probability.
    """

    def __init__(self, prob=0.5, *, horizontal=True, vertical=False):
        """
        Args:
            prob (float): probability of flip.
            horizontal (boolean): whether to apply horizontal flipping
            vertical (boolean): whether to apply vertical flipping
        """
        super().__init__()

        if horizontal and vertical:
            raise ValueError("Cannot do both horiz and vert. Please use two Flip instead.")
        if not horizontal and not vertical:
            raise ValueError("At least one of horiz or vert has to be True!")
        self._init(locals())

    def get_transform(self, image):
        h, w = image.shape[:2]
        do = self._rand_range() < self.prob
        if do:
            if self.horizontal:
                return HFlipTransform(w)
            elif self.vertical:
                return VFlipTransform(h)
        else:
            return NoOpTransform()


class Resize(Augmentation):
    """Resize image to a fixed target size"""

    def __init__(self, shape, interp=Image.BILINEAR):
        """
        Args:
            shape: (h, w) tuple or a int
            interp: PIL interpolation method
        """
        if isinstance(shape, int):
            shape = (shape, shape)
        shape = tuple(shape)
        self._init(locals())

    def get_transform(self, image):
        return ResizeTransform(
            image.shape[0], image.shape[1], self.shape[0], self.shape[1], self.interp
        )


class ResizeShortestEdge(Augmentation):
    """
    Resize the image while keeping the aspect ratio unchanged.
    It attempts to scale the shorter edge to the given `short_edge_length`,
    as long as the longer edge does not exceed `max_size`.
    If `max_size` is reached, then downscale so that the longer edge does not exceed max_size.
    """

    @torch.jit.unused
    def __init__(
        self, short_edge_length, max_size=sys.maxsize, sample_style="range", interp=Image.BILINEAR
    ):
        """
        Args:
            short_edge_length (list[int]): If ``sample_style=="range"``,
                a [min, max] interval from which to sample the shortest edge length.
                If ``sample_style=="choice"``, a list of shortest edge lengths to sample from.
            max_size (int): maximum allowed longest edge length.
            sample_style (str): either "range" or "choice".
        """
        super().__init__()
        assert sample_style in ["range", "choice"], sample_style

        self.is_range = sample_style == "range"
        if isinstance(short_edge_length, int):
            short_edge_length = (short_edge_length, short_edge_length)
        if self.is_range:
            assert len(short_edge_length) == 2, (
                "short_edge_length must be two values using 'range' sample style."
                f" Got {short_edge_length}!"
            )
        self._init(locals())

    @torch.jit.unused
    def get_transform(self, image):
        h, w = image.shape[:2]
        if self.is_range:
            size = np.random.randint(self.short_edge_length[0], self.short_edge_length[1] + 1)
        else:
            size = np.random.choice(self.short_edge_length)
        if size == 0:
            return NoOpTransform()

        newh, neww = ResizeShortestEdge.get_output_shape(h, w, size, self.max_size)
        return ResizeTransform(h, w, newh, neww, self.interp)

    @staticmethod
    def get_output_shape(
        oldh: int, oldw: int, short_edge_length: int, max_size: int
    ) -> Tuple[int, int]:
        """
        Compute the output size given input size and target short edge length.
        """
        h, w = oldh, oldw
        size = short_edge_length * 1.0
        scale = size / min(h, w)
        if h < w:
            newh, neww = size, scale * w
        else:
            newh, neww = scale * h, size
        if max(newh, neww) > max_size:
            scale = max_size * 1.0 / max(newh, neww)
            newh = newh * scale
            neww = neww * scale
        neww = int(neww + 0.5)
        newh = int(newh + 0.5)
        return (newh, neww)


class ResizeScale(Augmentation):
    """
    Takes target size as input and randomly scales the given target size between `min_scale`
    and `max_scale`. It then scales the input image such that it fits inside the scaled target
    box, keeping the aspect ratio constant.
    This implements the resize part of the Google's 'resize_and_crop' data augmentation:
    https://github.com/tensorflow/tpu/blob/master/models/official/detection/utils/input_utils.py#L127
    """

    def __init__(
        self,
        min_scale: float,
        max_scale: float,
        target_height: int,
        target_width: int,
        interp: int = Image.BILINEAR,
    ):
        """
        Args:
            min_scale: minimum image scale range.
            max_scale: maximum image scale range.
            target_height: target image height.
            target_width: target image width.
            interp: image interpolation method.
        """
        super().__init__()
        self._init(locals())

    def _get_resize(self, image: np.ndarray, scale: float) -> Transform:
        input_size = image.shape[:2]

        # Compute new target size given a scale.
        target_size = (self.target_height, self.target_width)
        target_scale_size = np.multiply(target_size, scale)

        # Compute actual rescaling applied to input image and output size.
        output_scale = np.minimum(
            target_scale_size[0] / input_size[0], target_scale_size[1] / input_size[1]
        )
        output_size = np.round(np.multiply(input_size, output_scale)).astype(int)

        return ResizeTransform(
            input_size[0], input_size[1], int(output_size[0]), int(output_size[1]), self.interp
        )

    def get_transform(self, image: np.ndarray) -> Transform:
        random_scale = np.random.uniform(self.min_scale, self.max_scale)
        return self._get_resize(image, random_scale)


class RandomRotation(Augmentation):
    """
    This method returns a copy of this image, rotated the given
    number of degrees counter clockwise around the given center.
    """

    def __init__(self, angle, expand=True, center=None, sample_style="range", interp=None):
        """
        Args:
            angle (list[float]): If ``sample_style=="range"``,
                a [min, max] interval from which to sample the angle (in degrees).
                If ``sample_style=="choice"``, a list of angles to sample from
            expand (bool): choose if the image should be resized to fit the whole
                rotated image (default), or simply cropped
            center (list[[float, float]]):  If ``sample_style=="range"``,
                a [[minx, miny], [maxx, maxy]] relative interval from which to sample the center,
                [0, 0] being the top left of the image and [1, 1] the bottom right.
                If ``sample_style=="choice"``, a list of centers to sample from
                Default: None, which means that the center of rotation is the center of the image
                center has no effect if expand=True because it only affects shifting
        """
        super().__init__()
        assert sample_style in ["range", "choice"], sample_style
        self.is_range = sample_style == "range"
        if isinstance(angle, (float, int)):
            angle = (angle, angle)
        if center is not None and isinstance(center[0], (float, int)):
            center = (center, center)
        self._init(locals())

    def get_transform(self, image):
        h, w = image.shape[:2]
        center = None
        if self.is_range:
            angle = np.random.uniform(self.angle[0], self.angle[1])
            if self.center is not None:
                center = (
                    np.random.uniform(self.center[0][0], self.center[1][0]),
                    np.random.uniform(self.center[0][1], self.center[1][1]),
                )
        else:
            angle = np.random.choice(self.angle)
            if self.center is not None:
                center = np.random.choice(self.center)

        if center is not None:
            center = (w * center[0], h * center[1])  # Convert to absolute coordinates

        if angle % 360 == 0:
            return NoOpTransform()

        return RotationTransform(h, w, angle, expand=self.expand, center=center, interp=self.interp)


class FixedSizeCrop(Augmentation):
    """
    If `crop_size` is smaller than the input image size, then it uses a random crop of
    the crop size. If `crop_size` is larger than the input image size, then it pads
    the right and the bottom of the image to the crop size if `pad` is True, otherwise
    it returns the smaller image.
    """

    def __init__(
        self,
        crop_size: Tuple[int],
        pad: bool = True,
        pad_value: float = 128.0,
        seg_pad_value: int = 255,
    ):
        """
        Args:
            crop_size: target image (height, width).
            pad: if True, will pad images smaller than `crop_size` up to `crop_size`
            pad_value: the padding value to the image.
            seg_pad_value: the padding value to the segmentation mask.
        """
        super().__init__()
        self._init(locals())

    def _get_crop(self, image: np.ndarray) -> Transform:
        # Compute the image scale and scaled size.
        input_size = image.shape[:2]
        output_size = self.crop_size

        # Add random crop if the image is scaled up.
        max_offset = np.subtract(input_size, output_size)
        max_offset = np.maximum(max_offset, 0)
        offset = np.multiply(max_offset, np.random.uniform(0.0, 1.0))
        offset = np.round(offset).astype(int)
        return CropTransform(
            offset[1], offset[0], output_size[1], output_size[0], input_size[1], input_size[0]
        )

    def _get_pad(self, image: np.ndarray) -> Transform:
        # Compute the image scale and scaled size.
        input_size = image.shape[:2]
        output_size = self.crop_size

        # Add padding if the image is scaled down.
        pad_size = np.subtract(output_size, input_size)
        pad_size = np.maximum(pad_size, 0)
        original_size = np.minimum(input_size, output_size)
        return PadTransform(
            0,
            0,
            pad_size[1],
            pad_size[0],
            original_size[1],
            original_size[0],
            self.pad_value,
            self.seg_pad_value,
        )

    def get_transform(self, image: np.ndarray) -> TransformList:
        transforms = [self._get_crop(image)]
        if self.pad:
            transforms.append(self._get_pad(image))
        return TransformList(transforms)


class RandomCrop(Augmentation):
    """
    Randomly crop a rectangle region out of an image.
    """

    def __init__(self, crop_type: str, crop_size):
        """
        Args:
            crop_type (str): one of "relative_range", "relative", "absolute", "absolute_range".
            crop_size (tuple[float, float]): two floats, explained below.

        - "relative": crop a (H * crop_size[0], W * crop_size[1]) region from an input image of
          size (H, W). crop size should be in (0, 1]
        - "relative_range": uniformly sample two values from [crop_size[0], 1]
          and [crop_size[1]], 1], and use them as in "relative" crop type.
        - "absolute" crop a (crop_size[0], crop_size[1]) region from input image.
          crop_size must be smaller than the input image size.
        - "absolute_range", for an input of size (H, W), uniformly sample H_crop in
          [crop_size[0], min(H, crop_size[1])] and W_crop in [crop_size[0], min(W, crop_size[1])].
          Then crop a region (H_crop, W_crop).
        """
        # TODO style of relative_range and absolute_range are not consistent:
        # one takes (h, w) but another takes (min, max)
        super().__init__()
        assert crop_type in ["relative_range", "relative", "absolute", "absolute_range"]
        self._init(locals())

    def get_transform(self, image):
        h, w = image.shape[:2]
        croph, cropw = self.get_crop_size((h, w))
        assert h >= croph and w >= cropw, "Shape computation in {} has bugs.".format(self)
        h0 = np.random.randint(h - croph + 1)
        w0 = np.random.randint(w - cropw + 1)
        return CropTransform(w0, h0, cropw, croph)

    def get_crop_size(self, image_size):
        """
        Args:
            image_size (tuple): height, width

        Returns:
            crop_size (tuple): height, width in absolute pixels
        """
        h, w = image_size
        if self.crop_type == "relative":
            ch, cw = self.crop_size
            return int(h * ch + 0.5), int(w * cw + 0.5)
        elif self.crop_type == "relative_range":
            crop_size = np.asarray(self.crop_size, dtype=np.float32)
            ch, cw = crop_size + np.random.rand(2) * (1 - crop_size)
            return int(h * ch + 0.5), int(w * cw + 0.5)
        elif self.crop_type == "absolute":
            return (min(self.crop_size[0], h), min(self.crop_size[1], w))
        elif self.crop_type == "absolute_range":
            assert self.crop_size[0] <= self.crop_size[1]
            ch = np.random.randint(min(h, self.crop_size[0]), min(h, self.crop_size[1]) + 1)
            cw = np.random.randint(min(w, self.crop_size[0]), min(w, self.crop_size[1]) + 1)
            return ch, cw
        else:
            raise NotImplementedError("Unknown crop type {}".format(self.crop_type))


class RandomCrop_CategoryAreaConstraint(Augmentation):
    """
    Similar to :class:`RandomCrop`, but find a cropping window such that no single category
    occupies a ratio of more than `single_category_max_area` in semantic segmentation ground
    truth, which can cause unstability in training. The function attempts to find such a valid
    cropping window for at most 10 times.
    """

    def __init__(
        self,
        crop_type: str,
        crop_size,
        single_category_max_area: float = 1.0,
        ignored_category: int = None,
    ):
        """
        Args:
            crop_type, crop_size: same as in :class:`RandomCrop`
            single_category_max_area: the maximum allowed area ratio of a
                category. Set to 1.0 to disable
            ignored_category: allow this category in the semantic segmentation
                ground truth to exceed the area ratio. Usually set to the category
                that's ignored in training.
        """
        self.crop_aug = RandomCrop(crop_type, crop_size)
        self._init(locals())

    def get_transform(self, image, sem_seg):
        if self.single_category_max_area >= 1.0:
            return self.crop_aug.get_transform(image)
        else:
            h, w = sem_seg.shape
            for _ in range(10):
                crop_size = self.crop_aug.get_crop_size((h, w))
                y0 = np.random.randint(h - crop_size[0] + 1)
                x0 = np.random.randint(w - crop_size[1] + 1)
                sem_seg_temp = sem_seg[y0 : y0 + crop_size[0], x0 : x0 + crop_size[1]]
                labels, cnt = np.unique(sem_seg_temp, return_counts=True)
                if self.ignored_category is not None:
                    cnt = cnt[labels != self.ignored_category]
                if len(cnt) > 1 and np.max(cnt) < np.sum(cnt) * self.single_category_max_area:
                    break
            crop_tfm = CropTransform(x0, y0, crop_size[1], crop_size[0])
            return crop_tfm


class RandomExtent(Augmentation):
    """
    Outputs an image by cropping a random "subrect" of the source image.

    The subrect can be parameterized to include pixels outside the source image,
    in which case they will be set to zeros (i.e. black). The size of the output
    image will vary with the size of the random subrect.
    """

    def __init__(self, scale_range, shift_range):
        """
        Args:
            output_size (h, w): Dimensions of output image
            scale_range (l, h): Range of input-to-output size scaling factor
            shift_range (x, y): Range of shifts of the cropped subrect. The rect
                is shifted by [w / 2 * Uniform(-x, x), h / 2 * Uniform(-y, y)],
                where (w, h) is the (width, height) of the input image. Set each
                component to zero to crop at the image's center.
        """
        super().__init__()
        self._init(locals())

    def get_transform(self, image):
        img_h, img_w = image.shape[:2]

        # Initialize src_rect to fit the input image.
        src_rect = np.array([-0.5 * img_w, -0.5 * img_h, 0.5 * img_w, 0.5 * img_h])

        # Apply a random scaling to the src_rect.
        src_rect *= np.random.uniform(self.scale_range[0], self.scale_range[1])

        # Apply a random shift to the coordinates origin.
        src_rect[0::2] += self.shift_range[0] * img_w * (np.random.rand() - 0.5)
        src_rect[1::2] += self.shift_range[1] * img_h * (np.random.rand() - 0.5)

        # Map src_rect coordinates into image coordinates (center at corner).
        src_rect[0::2] += 0.5 * img_w
        src_rect[1::2] += 0.5 * img_h

        return ExtentTransform(
            src_rect=(src_rect[0], src_rect[1], src_rect[2], src_rect[3]),
            output_size=(int(src_rect[3] - src_rect[1]), int(src_rect[2] - src_rect[0])),
        )


class RandomContrast(Augmentation):
    """
    Randomly transforms image contrast.

    Contrast intensity is uniformly sampled in (intensity_min, intensity_max).
    - intensity < 1 will reduce contrast
    - intensity = 1 will preserve the input image
    - intensity > 1 will increase contrast

    See: https://pillow.readthedocs.io/en/3.0.x/reference/ImageEnhance.html
    """

    def __init__(self, intensity_min, intensity_max):
        """
        Args:
            intensity_min (float): Minimum augmentation
            intensity_max (float): Maximum augmentation
        """
        super().__init__()
        self._init(locals())

    def get_transform(self, image):
        w = np.random.uniform(self.intensity_min, self.intensity_max)
        return BlendTransform(src_image=image.mean(), src_weight=1 - w, dst_weight=w)


class RandomBrightness(Augmentation):
    """
    Randomly transforms image brightness.

    Brightness intensity is uniformly sampled in (intensity_min, intensity_max).
    - intensity < 1 will reduce brightness
    - intensity = 1 will preserve the input image
    - intensity > 1 will increase brightness

    See: https://pillow.readthedocs.io/en/3.0.x/reference/ImageEnhance.html
    """

    def __init__(self, intensity_min, intensity_max):
        """
        Args:
            intensity_min (float): Minimum augmentation
            intensity_max (float): Maximum augmentation
        """
        super().__init__()
        self._init(locals())

    def get_transform(self, image):
        w = np.random.uniform(self.intensity_min, self.intensity_max)
        return BlendTransform(src_image=0, src_weight=1 - w, dst_weight=w)


class RandomSaturation(Augmentation):
    """
    Randomly transforms saturation of an RGB image.
    Input images are assumed to have 'RGB' channel order.

    Saturation intensity is uniformly sampled in (intensity_min, intensity_max).
    - intensity < 1 will reduce saturation (make the image more grayscale)
    - intensity = 1 will preserve the input image
    - intensity > 1 will increase saturation

    See: https://pillow.readthedocs.io/en/3.0.x/reference/ImageEnhance.html
    """

    def __init__(self, intensity_min, intensity_max):
        """
        Args:
            intensity_min (float): Minimum augmentation (1 preserves input).
            intensity_max (float): Maximum augmentation (1 preserves input).
        """
        super().__init__()
        self._init(locals())

    def get_transform(self, image):
        assert image.shape[-1] == 3, "RandomSaturation only works on RGB images"
        w = np.random.uniform(self.intensity_min, self.intensity_max)
        grayscale = image.dot([0.299, 0.587, 0.114])[:, :, np.newaxis]
        return BlendTransform(src_image=grayscale, src_weight=1 - w, dst_weight=w)


class RandomLighting(Augmentation):
    """
    The "lighting" augmentation described in AlexNet, using fixed PCA over ImageNet.
    Input images are assumed to have 'RGB' channel order.

    The degree of color jittering is randomly sampled via a normal distribution,
    with standard deviation given by the scale parameter.
    """

    def __init__(self, scale):
        """
        Args:
            scale (float): Standard deviation of principal component weighting.
        """
        super().__init__()
        self._init(locals())
        self.eigen_vecs = np.array(
            [[-0.5675, 0.7192, 0.4009], [-0.5808, -0.0045, -0.8140], [-0.5836, -0.6948, 0.4203]]
        )
        self.eigen_vals = np.array([0.2175, 0.0188, 0.0045])

    def get_transform(self, image):
        assert image.shape[-1] == 3, "RandomLighting only works on RGB images"
        weights = np.random.normal(scale=self.scale, size=3)
        return BlendTransform(
            src_image=self.eigen_vecs.dot(weights * self.eigen_vals), src_weight=1.0, dst_weight=1.0
        )


class RandomResize(Augmentation):
    """Randomly resize image to a target size in shape_list"""

    def __init__(self, shape_list, interp=Image.BILINEAR):
        """
        Args:
            shape_list: a list of shapes in (h, w)
            interp: PIL interpolation method
        """
        self.shape_list = shape_list
        self._init(locals())

    def get_transform(self, image):
        shape_idx = np.random.randint(low=0, high=len(self.shape_list))
        h, w = self.shape_list[shape_idx]
        return ResizeTransform(image.shape[0], image.shape[1], h, w, self.interp)


class MinIoURandomCrop(Augmentation):
    """Random crop the image & bboxes, the cropped patches have minimum IoU
    requirement with original image & bboxes, the IoU threshold is randomly
    selected from min_ious.

    Args:
        min_ious (tuple): minimum IoU threshold for all intersections with
        bounding boxes
        min_crop_size (float): minimum crop's size (i.e. h,w := a*h, a*w,
        where a >= min_crop_size)
        mode_trials: number of trials for sampling min_ious threshold
        crop_trials: number of trials for sampling crop_size after cropping
    """

    def __init__(
        self,
        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
        min_crop_size=0.3,
        mode_trials=1000,
        crop_trials=50,
    ):
        self.min_ious = min_ious
        self.sample_mode = (1, *min_ious, 0)
        self.min_crop_size = min_crop_size
        self.mode_trials = mode_trials
        self.crop_trials = crop_trials

    def get_transform(self, image, boxes):
        """Call function to crop images and bounding boxes with minimum IoU
        constraint.

        Args:
            boxes: ground truth boxes in (x1, y1, x2, y2) format
        """
        if boxes is None:
            return NoOpTransform()
        h, w, c = image.shape
        for _ in range(self.mode_trials):
            mode = random.choice(self.sample_mode)
            self.mode = mode
            if mode == 1:
                return NoOpTransform()

            min_iou = mode
            for _ in range(self.crop_trials):
                new_w = random.uniform(self.min_crop_size * w, w)
                new_h = random.uniform(self.min_crop_size * h, h)

                # h / w in [0.5, 2]
                if new_h / new_w < 0.5 or new_h / new_w > 2:
                    continue

                left = random.uniform(w - new_w)
                top = random.uniform(h - new_h)

                patch = np.array((int(left), int(top), int(left + new_w), int(top + new_h)))
                # Line or point crop is not allowed
                if patch[2] == patch[0] or patch[3] == patch[1]:
                    continue
                overlaps = pairwise_iou(
                    Boxes(patch.reshape(-1, 4)), Boxes(boxes.reshape(-1, 4))
                ).reshape(-1)
                if len(overlaps) > 0 and overlaps.min() < min_iou:
                    continue

                # center of boxes should inside the crop img
                # only adjust boxes and instance masks when the gt is not empty
                if len(overlaps) > 0:
                    # adjust boxes
                    def is_center_of_bboxes_in_patch(boxes, patch):
                        center = (boxes[:, :2] + boxes[:, 2:]) / 2
                        mask = (
                            (center[:, 0] > patch[0])
                            * (center[:, 1] > patch[1])
                            * (center[:, 0] < patch[2])
                            * (center[:, 1] < patch[3])
                        )
                        return mask

                    mask = is_center_of_bboxes_in_patch(boxes, patch)
                    if not mask.any():
                        continue
                return CropTransform(int(left), int(top), int(new_w), int(new_h))