File size: 24,338 Bytes
7a919c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#
#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.
#

import sys
import six
import cv2
import numpy as np
import math
from PIL import Image


class DecodeImage(object):
    """ decode image """

    def __init__(self,

                 img_mode='RGB',

                 channel_first=False,

                 ignore_orientation=False,

                 **kwargs):
        self.img_mode = img_mode
        self.channel_first = channel_first
        self.ignore_orientation = ignore_orientation

    def __call__(self, data):
        img = data['image']
        if six.PY2:
            assert isinstance(img, str) and len(
                img) > 0, "invalid input 'img' in DecodeImage"
        else:
            assert isinstance(img, bytes) and len(
                img) > 0, "invalid input 'img' in DecodeImage"
        img = np.frombuffer(img, dtype='uint8')
        if self.ignore_orientation:
            img = cv2.imdecode(img, cv2.IMREAD_IGNORE_ORIENTATION |
                               cv2.IMREAD_COLOR)
        else:
            img = cv2.imdecode(img, 1)
        if img is None:
            return None
        if self.img_mode == 'GRAY':
            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
        elif self.img_mode == 'RGB':
            assert img.shape[2] == 3, 'invalid shape of image[%s]' % (
                img.shape)
            img = img[:, :, ::-1]

        if self.channel_first:
            img = img.transpose((2, 0, 1))

        data['image'] = img
        return data


class StandardizeImage(object):
    """normalize image

    Args:

        mean (list): im - mean

        std (list): im / std

        is_scale (bool): whether need im / 255

        norm_type (str): type in ['mean_std', 'none']

    """

    def __init__(self, mean, std, is_scale=True, norm_type='mean_std'):
        self.mean = mean
        self.std = std
        self.is_scale = is_scale
        self.norm_type = norm_type

    def __call__(self, im, im_info):
        """

        Args:

            im (np.ndarray): image (np.ndarray)

            im_info (dict): info of image

        Returns:

            im (np.ndarray):  processed image (np.ndarray)

            im_info (dict): info of processed image

        """
        im = im.astype(np.float32, copy=False)
        if self.is_scale:
            scale = 1.0 / 255.0
            im *= scale

        if self.norm_type == 'mean_std':
            mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
            std = np.array(self.std)[np.newaxis, np.newaxis, :]
            im -= mean
            im /= std
        return im, im_info


class NormalizeImage(object):
    """ normalize image such as substract mean, divide std

    """

    def __init__(self, scale=None, mean=None, std=None, order='chw', **kwargs):
        if isinstance(scale, str):
            scale = eval(scale)
        self.scale = np.float32(scale if scale is not None else 1.0 / 255.0)
        mean = mean if mean is not None else [0.485, 0.456, 0.406]
        std = std if std is not None else [0.229, 0.224, 0.225]

        shape = (3, 1, 1) if order == 'chw' else (1, 1, 3)
        self.mean = np.array(mean).reshape(shape).astype('float32')
        self.std = np.array(std).reshape(shape).astype('float32')

    def __call__(self, data):
        img = data['image']
        from PIL import Image
        if isinstance(img, Image.Image):
            img = np.array(img)
        assert isinstance(img,
                          np.ndarray), "invalid input 'img' in NormalizeImage"
        data['image'] = (
            img.astype('float32') * self.scale - self.mean) / self.std
        return data


class ToCHWImage(object):
    """ convert hwc image to chw image

    """

    def __init__(self, **kwargs):
        pass

    def __call__(self, data):
        img = data['image']
        from PIL import Image
        if isinstance(img, Image.Image):
            img = np.array(img)
        data['image'] = img.transpose((2, 0, 1))
        return data


class Fasttext(object):
    def __init__(self, path="None", **kwargs):
        import fasttext
        self.fast_model = fasttext.load_model(path)

    def __call__(self, data):
        label = data['label']
        fast_label = self.fast_model[label]
        data['fast_label'] = fast_label
        return data


class KeepKeys(object):
    def __init__(self, keep_keys, **kwargs):
        self.keep_keys = keep_keys

    def __call__(self, data):
        data_list = []
        for key in self.keep_keys:
            data_list.append(data[key])
        return data_list


class Pad(object):
    def __init__(self, size=None, size_div=32, **kwargs):
        if size is not None and not isinstance(size, (int, list, tuple)):
            raise TypeError("Type of target_size is invalid. Now is {}".format(
                type(size)))
        if isinstance(size, int):
            size = [size, size]
        self.size = size
        self.size_div = size_div

    def __call__(self, data):

        img = data['image']
        img_h, img_w = img.shape[0], img.shape[1]
        if self.size:
            resize_h2, resize_w2 = self.size
            assert (
                img_h < resize_h2 and img_w < resize_w2
            ), '(h, w) of target size should be greater than (img_h, img_w)'
        else:
            resize_h2 = max(
                int(math.ceil(img.shape[0] / self.size_div) * self.size_div),
                self.size_div)
            resize_w2 = max(
                int(math.ceil(img.shape[1] / self.size_div) * self.size_div),
                self.size_div)
        img = cv2.copyMakeBorder(
            img,
            0,
            resize_h2 - img_h,
            0,
            resize_w2 - img_w,
            cv2.BORDER_CONSTANT,
            value=0)
        data['image'] = img
        return data


class LinearResize(object):
    """resize image by target_size and max_size

    Args:

        target_size (int): the target size of image

        keep_ratio (bool): whether keep_ratio or not, default true

        interp (int): method of resize

    """

    def __init__(self, target_size, keep_ratio=True, interp=cv2.INTER_LINEAR):
        if isinstance(target_size, int):
            target_size = [target_size, target_size]
        self.target_size = target_size
        self.keep_ratio = keep_ratio
        self.interp = interp

    def __call__(self, im, im_info):
        """

        Args:

            im (np.ndarray): image (np.ndarray)

            im_info (dict): info of image

        Returns:

            im (np.ndarray):  processed image (np.ndarray)

            im_info (dict): info of processed image

        """
        assert len(self.target_size) == 2
        assert self.target_size[0] > 0 and self.target_size[1] > 0
        im_channel = im.shape[2]
        im_scale_y, im_scale_x = self.generate_scale(im)
        im = cv2.resize(
            im,
            None,
            None,
            fx=im_scale_x,
            fy=im_scale_y,
            interpolation=self.interp)
        im_info['im_shape'] = np.array(im.shape[:2]).astype('float32')
        im_info['scale_factor'] = np.array(
            [im_scale_y, im_scale_x]).astype('float32')
        return im, im_info

    def generate_scale(self, im):
        """

        Args:

            im (np.ndarray): image (np.ndarray)

        Returns:

            im_scale_x: the resize ratio of X

            im_scale_y: the resize ratio of Y

        """
        origin_shape = im.shape[:2]
        im_c = im.shape[2]
        if self.keep_ratio:
            im_size_min = np.min(origin_shape)
            im_size_max = np.max(origin_shape)
            target_size_min = np.min(self.target_size)
            target_size_max = np.max(self.target_size)
            im_scale = float(target_size_min) / float(im_size_min)
            if np.round(im_scale * im_size_max) > target_size_max:
                im_scale = float(target_size_max) / float(im_size_max)
            im_scale_x = im_scale
            im_scale_y = im_scale
        else:
            resize_h, resize_w = self.target_size
            im_scale_y = resize_h / float(origin_shape[0])
            im_scale_x = resize_w / float(origin_shape[1])
        return im_scale_y, im_scale_x


class Resize(object):
    def __init__(self, size=(640, 640), **kwargs):
        self.size = size

    def resize_image(self, img):
        resize_h, resize_w = self.size
        ori_h, ori_w = img.shape[:2]  # (h, w, c)
        ratio_h = float(resize_h) / ori_h
        ratio_w = float(resize_w) / ori_w
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        return img, [ratio_h, ratio_w]

    def __call__(self, data):
        img = data['image']
        if 'polys' in data:
            text_polys = data['polys']

        img_resize, [ratio_h, ratio_w] = self.resize_image(img)
        if 'polys' in data:
            new_boxes = []
            for box in text_polys:
                new_box = []
                for cord in box:
                    new_box.append([cord[0] * ratio_w, cord[1] * ratio_h])
                new_boxes.append(new_box)
            data['polys'] = np.array(new_boxes, dtype=np.float32)
        data['image'] = img_resize
        return data


class DetResizeForTest(object):
    def __init__(self, **kwargs):
        super(DetResizeForTest, self).__init__()
        self.resize_type = 0
        self.keep_ratio = False
        if 'image_shape' in kwargs:
            self.image_shape = kwargs['image_shape']
            self.resize_type = 1
            if 'keep_ratio' in kwargs:
                self.keep_ratio = kwargs['keep_ratio']
        elif 'limit_side_len' in kwargs:
            self.limit_side_len = kwargs['limit_side_len']
            self.limit_type = kwargs.get('limit_type', 'min')
        elif 'resize_long' in kwargs:
            self.resize_type = 2
            self.resize_long = kwargs.get('resize_long', 960)
        else:
            self.limit_side_len = 736
            self.limit_type = 'min'

    def __call__(self, data):
        img = data['image']
        src_h, src_w, _ = img.shape
        if sum([src_h, src_w]) < 64:
            img = self.image_padding(img)

        if self.resize_type == 0:
            # img, shape = self.resize_image_type0(img)
            img, [ratio_h, ratio_w] = self.resize_image_type0(img)
        elif self.resize_type == 2:
            img, [ratio_h, ratio_w] = self.resize_image_type2(img)
        else:
            # img, shape = self.resize_image_type1(img)
            img, [ratio_h, ratio_w] = self.resize_image_type1(img)
        data['image'] = img
        data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
        return data

    def image_padding(self, im, value=0):
        h, w, c = im.shape
        im_pad = np.zeros((max(32, h), max(32, w), c), np.uint8) + value
        im_pad[:h, :w, :] = im
        return im_pad

    def resize_image_type1(self, img):
        resize_h, resize_w = self.image_shape
        ori_h, ori_w = img.shape[:2]  # (h, w, c)
        if self.keep_ratio is True:
            resize_w = ori_w * resize_h / ori_h
            N = math.ceil(resize_w / 32)
            resize_w = N * 32
        ratio_h = float(resize_h) / ori_h
        ratio_w = float(resize_w) / ori_w
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        # return img, np.array([ori_h, ori_w])
        return img, [ratio_h, ratio_w]

    def resize_image_type0(self, img):
        """

        resize image to a size multiple of 32 which is required by the network

        args:

            img(array): array with shape [h, w, c]

        return(tuple):

            img, (ratio_h, ratio_w)

        """
        limit_side_len = self.limit_side_len
        h, w, c = img.shape

        # limit the max side
        if self.limit_type == 'max':
            if max(h, w) > limit_side_len:
                if h > w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.
        elif self.limit_type == 'min':
            if min(h, w) < limit_side_len:
                if h < w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.
        elif self.limit_type == 'resize_long':
            ratio = float(limit_side_len) / max(h, w)
        else:
            raise Exception('not support limit type, image ')
        resize_h = int(h * ratio)
        resize_w = int(w * ratio)

        resize_h = max(int(round(resize_h / 32) * 32), 32)
        resize_w = max(int(round(resize_w / 32) * 32), 32)

        try:
            if int(resize_w) <= 0 or int(resize_h) <= 0:
                return None, (None, None)
            img = cv2.resize(img, (int(resize_w), int(resize_h)))
        except BaseException:
            print(img.shape, resize_w, resize_h)
            sys.exit(0)
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)
        return img, [ratio_h, ratio_w]

    def resize_image_type2(self, img):
        h, w, _ = img.shape

        resize_w = w
        resize_h = h

        if resize_h > resize_w:
            ratio = float(self.resize_long) / resize_h
        else:
            ratio = float(self.resize_long) / resize_w

        resize_h = int(resize_h * ratio)
        resize_w = int(resize_w * ratio)

        max_stride = 128
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)

        return img, [ratio_h, ratio_w]


class E2EResizeForTest(object):
    def __init__(self, **kwargs):
        super(E2EResizeForTest, self).__init__()
        self.max_side_len = kwargs['max_side_len']
        self.valid_set = kwargs['valid_set']

    def __call__(self, data):
        img = data['image']
        src_h, src_w, _ = img.shape
        if self.valid_set == 'totaltext':
            im_resized, [ratio_h, ratio_w] = self.resize_image_for_totaltext(
                img, max_side_len=self.max_side_len)
        else:
            im_resized, (ratio_h, ratio_w) = self.resize_image(
                img, max_side_len=self.max_side_len)
        data['image'] = im_resized
        data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
        return data

    def resize_image_for_totaltext(self, im, max_side_len=512):

        h, w, _ = im.shape
        resize_w = w
        resize_h = h
        ratio = 1.25
        if h * ratio > max_side_len:
            ratio = float(max_side_len) / resize_h
        resize_h = int(resize_h * ratio)
        resize_w = int(resize_w * ratio)

        max_stride = 128
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        im = cv2.resize(im, (int(resize_w), int(resize_h)))
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)
        return im, (ratio_h, ratio_w)

    def resize_image(self, im, max_side_len=512):
        """

        resize image to a size multiple of max_stride which is required by the network

        :param im: the resized image

        :param max_side_len: limit of max image size to avoid out of memory in gpu

        :return: the resized image and the resize ratio

        """
        h, w, _ = im.shape

        resize_w = w
        resize_h = h

        # Fix the longer side
        if resize_h > resize_w:
            ratio = float(max_side_len) / resize_h
        else:
            ratio = float(max_side_len) / resize_w

        resize_h = int(resize_h * ratio)
        resize_w = int(resize_w * ratio)

        max_stride = 128
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        im = cv2.resize(im, (int(resize_w), int(resize_h)))
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)

        return im, (ratio_h, ratio_w)


class KieResize(object):
    def __init__(self, **kwargs):
        super(KieResize, self).__init__()
        self.max_side, self.min_side = kwargs['img_scale'][0], kwargs[
            'img_scale'][1]

    def __call__(self, data):
        img = data['image']
        points = data['points']
        src_h, src_w, _ = img.shape
        im_resized, scale_factor, [ratio_h, ratio_w
                                   ], [new_h, new_w] = self.resize_image(img)
        resize_points = self.resize_boxes(img, points, scale_factor)
        data['ori_image'] = img
        data['ori_boxes'] = points
        data['points'] = resize_points
        data['image'] = im_resized
        data['shape'] = np.array([new_h, new_w])
        return data

    def resize_image(self, img):
        norm_img = np.zeros([1024, 1024, 3], dtype='float32')
        scale = [512, 1024]
        h, w = img.shape[:2]
        max_long_edge = max(scale)
        max_short_edge = min(scale)
        scale_factor = min(max_long_edge / max(h, w),
                           max_short_edge / min(h, w))
        resize_w, resize_h = int(w * float(scale_factor) + 0.5), int(h * float(
            scale_factor) + 0.5)
        max_stride = 32
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        im = cv2.resize(img, (resize_w, resize_h))
        new_h, new_w = im.shape[:2]
        w_scale = new_w / w
        h_scale = new_h / h
        scale_factor = np.array(
            [w_scale, h_scale, w_scale, h_scale], dtype=np.float32)
        norm_img[:new_h, :new_w, :] = im
        return norm_img, scale_factor, [h_scale, w_scale], [new_h, new_w]

    def resize_boxes(self, im, points, scale_factor):
        points = points * scale_factor
        img_shape = im.shape[:2]
        points[:, 0::2] = np.clip(points[:, 0::2], 0, img_shape[1])
        points[:, 1::2] = np.clip(points[:, 1::2], 0, img_shape[0])
        return points


class SRResize(object):
    def __init__(self,

                 imgH=32,

                 imgW=128,

                 down_sample_scale=4,

                 keep_ratio=False,

                 min_ratio=1,

                 mask=False,

                 infer_mode=False,

                 **kwargs):
        self.imgH = imgH
        self.imgW = imgW
        self.keep_ratio = keep_ratio
        self.min_ratio = min_ratio
        self.down_sample_scale = down_sample_scale
        self.mask = mask
        self.infer_mode = infer_mode

    def __call__(self, data):
        imgH = self.imgH
        imgW = self.imgW
        images_lr = data["image_lr"]
        transform2 = ResizeNormalize(
            (imgW // self.down_sample_scale, imgH // self.down_sample_scale))
        images_lr = transform2(images_lr)
        data["img_lr"] = images_lr
        if self.infer_mode:
            return data

        images_HR = data["image_hr"]
        label_strs = data["label"]
        transform = ResizeNormalize((imgW, imgH))
        images_HR = transform(images_HR)
        data["img_hr"] = images_HR
        return data


class ResizeNormalize(object):
    def __init__(self, size, interpolation=Image.BICUBIC):
        self.size = size
        self.interpolation = interpolation

    def __call__(self, img):
        img = img.resize(self.size, self.interpolation)
        img_numpy = np.array(img).astype("float32")
        img_numpy = img_numpy.transpose((2, 0, 1)) / 255
        return img_numpy


class GrayImageChannelFormat(object):
    """

    format gray scale image's channel: (3,h,w) -> (1,h,w)

    Args:

        inverse: inverse gray image

    """

    def __init__(self, inverse=False, **kwargs):
        self.inverse = inverse

    def __call__(self, data):
        img = data['image']
        img_single_channel = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        img_expanded = np.expand_dims(img_single_channel, 0)

        if self.inverse:
            data['image'] = np.abs(img_expanded - 1)
        else:
            data['image'] = img_expanded

        data['src_image'] = img
        return data


class Permute(object):
    """permute image

    Args:

        to_bgr (bool): whether convert RGB to BGR

        channel_first (bool): whether convert HWC to CHW

    """

    def __init__(self, ):
        super(Permute, self).__init__()

    def __call__(self, im, im_info):
        """

        Args:

            im (np.ndarray): image (np.ndarray)

            im_info (dict): info of image

        Returns:

            im (np.ndarray):  processed image (np.ndarray)

            im_info (dict): info of processed image

        """
        im = im.transpose((2, 0, 1)).copy()
        return im, im_info


class PadStride(object):
    """ padding image for model with FPN, instead PadBatch(pad_to_stride) in original config

    Args:

        stride (bool): model with FPN need image shape % stride == 0

    """

    def __init__(self, stride=0):
        self.coarsest_stride = stride

    def __call__(self, im, im_info):
        """

        Args:

            im (np.ndarray): image (np.ndarray)

            im_info (dict): info of image

        Returns:

            im (np.ndarray):  processed image (np.ndarray)

            im_info (dict): info of processed image

        """
        coarsest_stride = self.coarsest_stride
        if coarsest_stride <= 0:
            return im, im_info
        im_c, im_h, im_w = im.shape
        pad_h = int(np.ceil(float(im_h) / coarsest_stride) * coarsest_stride)
        pad_w = int(np.ceil(float(im_w) / coarsest_stride) * coarsest_stride)
        padding_im = np.zeros((im_c, pad_h, pad_w), dtype=np.float32)
        padding_im[:, :im_h, :im_w] = im
        return padding_im, im_info


def decode_image(im_file, im_info):
    """read rgb image

    Args:

        im_file (str|np.ndarray): input can be image path or np.ndarray

        im_info (dict): info of image

    Returns:

        im (np.ndarray):  processed image (np.ndarray)

        im_info (dict): info of processed image

    """
    if isinstance(im_file, str):
        with open(im_file, 'rb') as f:
            im_read = f.read()
        data = np.frombuffer(im_read, dtype='uint8')
        im = cv2.imdecode(data, 1)  # BGR mode, but need RGB mode
        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
    else:
        im = im_file
    im_info['im_shape'] = np.array(im.shape[:2], dtype=np.float32)
    im_info['scale_factor'] = np.array([1., 1.], dtype=np.float32)
    return im, im_info


def preprocess(im, preprocess_ops):
    # process image by preprocess_ops
    im_info = {
        'scale_factor': np.array(
            [1., 1.], dtype=np.float32),
        'im_shape': None,
    }
    im, im_info = decode_image(im, im_info)
    for operator in preprocess_ops:
        im, im_info = operator(im, im_info)
    return im, im_info