File size: 15,157 Bytes
c59c099
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
import random
import torch
from pathlib import Path
from torch.utils import data as data

from basicsr.data.transforms import augment, paired_random_crop
from basicsr.utils import FileClient, get_root_logger, imfrombytes, img2tensor
from basicsr.utils.flow_util import dequantize_flow
from basicsr.utils.registry import DATASET_REGISTRY


@DATASET_REGISTRY.register()
class REDSDataset(data.Dataset):
    """REDS dataset for training.

    The keys are generated from a meta info txt file.
    basicsr/data/meta_info/meta_info_REDS_GT.txt

    Each line contains:
    1. subfolder (clip) name; 2. frame number; 3. image shape, separated by
    a white space.
    Examples:
    000 100 (720,1280,3)
    001 100 (720,1280,3)
    ...

    Key examples: "000/00000000"
    GT (gt): Ground-Truth;
    LQ (lq): Low-Quality, e.g., low-resolution/blurry/noisy/compressed frames.

    Args:
        opt (dict): Config for train dataset. It contains the following keys:
        dataroot_gt (str): Data root path for gt.
        dataroot_lq (str): Data root path for lq.
        dataroot_flow (str, optional): Data root path for flow.
        meta_info_file (str): Path for meta information file.
        val_partition (str): Validation partition types. 'REDS4' or 'official'.
        io_backend (dict): IO backend type and other kwarg.
        num_frame (int): Window size for input frames.
        gt_size (int): Cropped patched size for gt patches.
        interval_list (list): Interval list for temporal augmentation.
        random_reverse (bool): Random reverse input frames.
        use_hflip (bool): Use horizontal flips.
        use_rot (bool): Use rotation (use vertical flip and transposing h and w for implementation).
        scale (bool): Scale, which will be added automatically.
    """

    def __init__(self, opt):
        super(REDSDataset, self).__init__()
        self.opt = opt
        self.gt_root, self.lq_root = Path(opt['dataroot_gt']), Path(opt['dataroot_lq'])
        self.flow_root = Path(opt['dataroot_flow']) if opt['dataroot_flow'] is not None else None
        assert opt['num_frame'] % 2 == 1, (f'num_frame should be odd number, but got {opt["num_frame"]}')
        self.num_frame = opt['num_frame']
        self.num_half_frames = opt['num_frame'] // 2

        self.keys = []
        with open(opt['meta_info_file'], 'r') as fin:
            for line in fin:
                folder, frame_num, _ = line.split(' ')
                self.keys.extend([f'{folder}/{i:08d}' for i in range(int(frame_num))])

        # remove the video clips used in validation
        if opt['val_partition'] == 'REDS4':
            val_partition = ['000', '011', '015', '020']
        elif opt['val_partition'] == 'official':
            val_partition = [f'{v:03d}' for v in range(240, 270)]
        else:
            raise ValueError(f'Wrong validation partition {opt["val_partition"]}.'
                             f"Supported ones are ['official', 'REDS4'].")
        self.keys = [v for v in self.keys if v.split('/')[0] not in val_partition]

        # file client (io backend)
        self.file_client = None
        self.io_backend_opt = opt['io_backend']
        self.is_lmdb = False
        if self.io_backend_opt['type'] == 'lmdb':
            self.is_lmdb = True
            if self.flow_root is not None:
                self.io_backend_opt['db_paths'] = [self.lq_root, self.gt_root, self.flow_root]
                self.io_backend_opt['client_keys'] = ['lq', 'gt', 'flow']
            else:
                self.io_backend_opt['db_paths'] = [self.lq_root, self.gt_root]
                self.io_backend_opt['client_keys'] = ['lq', 'gt']

        # temporal augmentation configs
        self.interval_list = opt['interval_list']
        self.random_reverse = opt['random_reverse']
        interval_str = ','.join(str(x) for x in opt['interval_list'])
        logger = get_root_logger()
        logger.info(f'Temporal augmentation interval list: [{interval_str}]; '
                    f'random reverse is {self.random_reverse}.')

    def __getitem__(self, index):
        if self.file_client is None:
            self.file_client = FileClient(self.io_backend_opt.pop('type'), **self.io_backend_opt)

        scale = self.opt['scale']
        gt_size = self.opt['gt_size']
        key = self.keys[index]
        clip_name, frame_name = key.split('/')  # key example: 000/00000000
        center_frame_idx = int(frame_name)

        # determine the neighboring frames
        interval = random.choice(self.interval_list)

        # ensure not exceeding the borders
        start_frame_idx = center_frame_idx - self.num_half_frames * interval
        end_frame_idx = center_frame_idx + self.num_half_frames * interval
        # each clip has 100 frames starting from 0 to 99
        while (start_frame_idx < 0) or (end_frame_idx > 99):
            center_frame_idx = random.randint(0, 99)
            start_frame_idx = (center_frame_idx - self.num_half_frames * interval)
            end_frame_idx = center_frame_idx + self.num_half_frames * interval
        frame_name = f'{center_frame_idx:08d}'
        neighbor_list = list(range(start_frame_idx, end_frame_idx + 1, interval))
        # random reverse
        if self.random_reverse and random.random() < 0.5:
            neighbor_list.reverse()

        assert len(neighbor_list) == self.num_frame, (f'Wrong length of neighbor list: {len(neighbor_list)}')

        # get the GT frame (as the center frame)
        if self.is_lmdb:
            img_gt_path = f'{clip_name}/{frame_name}'
        else:
            img_gt_path = self.gt_root / clip_name / f'{frame_name}.png'
        img_bytes = self.file_client.get(img_gt_path, 'gt')
        img_gt = imfrombytes(img_bytes, float32=True)

        # get the neighboring LQ frames
        img_lqs = []
        for neighbor in neighbor_list:
            if self.is_lmdb:
                img_lq_path = f'{clip_name}/{neighbor:08d}'
            else:
                img_lq_path = self.lq_root / clip_name / f'{neighbor:08d}.png'
            img_bytes = self.file_client.get(img_lq_path, 'lq')
            img_lq = imfrombytes(img_bytes, float32=True)
            img_lqs.append(img_lq)

        # get flows
        if self.flow_root is not None:
            img_flows = []
            # read previous flows
            for i in range(self.num_half_frames, 0, -1):
                if self.is_lmdb:
                    flow_path = f'{clip_name}/{frame_name}_p{i}'
                else:
                    flow_path = (self.flow_root / clip_name / f'{frame_name}_p{i}.png')
                img_bytes = self.file_client.get(flow_path, 'flow')
                cat_flow = imfrombytes(img_bytes, flag='grayscale', float32=False)  # uint8, [0, 255]
                dx, dy = np.split(cat_flow, 2, axis=0)
                flow = dequantize_flow(dx, dy, max_val=20, denorm=False)  # we use max_val 20 here.
                img_flows.append(flow)
            # read next flows
            for i in range(1, self.num_half_frames + 1):
                if self.is_lmdb:
                    flow_path = f'{clip_name}/{frame_name}_n{i}'
                else:
                    flow_path = (self.flow_root / clip_name / f'{frame_name}_n{i}.png')
                img_bytes = self.file_client.get(flow_path, 'flow')
                cat_flow = imfrombytes(img_bytes, flag='grayscale', float32=False)  # uint8, [0, 255]
                dx, dy = np.split(cat_flow, 2, axis=0)
                flow = dequantize_flow(dx, dy, max_val=20, denorm=False)  # we use max_val 20 here.
                img_flows.append(flow)

            # for random crop, here, img_flows and img_lqs have the same
            # spatial size
            img_lqs.extend(img_flows)

        # randomly crop
        img_gt, img_lqs = paired_random_crop(img_gt, img_lqs, gt_size, scale, img_gt_path)
        if self.flow_root is not None:
            img_lqs, img_flows = img_lqs[:self.num_frame], img_lqs[self.num_frame:]

        # augmentation - flip, rotate
        img_lqs.append(img_gt)
        if self.flow_root is not None:
            img_results, img_flows = augment(img_lqs, self.opt['use_hflip'], self.opt['use_rot'], img_flows)
        else:
            img_results = augment(img_lqs, self.opt['use_hflip'], self.opt['use_rot'])

        img_results = img2tensor(img_results)
        img_lqs = torch.stack(img_results[0:-1], dim=0)
        img_gt = img_results[-1]

        if self.flow_root is not None:
            img_flows = img2tensor(img_flows)
            # add the zero center flow
            img_flows.insert(self.num_half_frames, torch.zeros_like(img_flows[0]))
            img_flows = torch.stack(img_flows, dim=0)

        # img_lqs: (t, c, h, w)
        # img_flows: (t, 2, h, w)
        # img_gt: (c, h, w)
        # key: str
        if self.flow_root is not None:
            return {'lq': img_lqs, 'flow': img_flows, 'gt': img_gt, 'key': key}
        else:
            return {'lq': img_lqs, 'gt': img_gt, 'key': key}

    def __len__(self):
        return len(self.keys)


@DATASET_REGISTRY.register()
class REDSRecurrentDataset(data.Dataset):
    """REDS dataset for training recurrent networks.

    The keys are generated from a meta info txt file.
    basicsr/data/meta_info/meta_info_REDS_GT.txt

    Each line contains:
    1. subfolder (clip) name; 2. frame number; 3. image shape, separated by
    a white space.
    Examples:
    000 100 (720,1280,3)
    001 100 (720,1280,3)
    ...

    Key examples: "000/00000000"
    GT (gt): Ground-Truth;
    LQ (lq): Low-Quality, e.g., low-resolution/blurry/noisy/compressed frames.

    Args:
        opt (dict): Config for train dataset. It contains the following keys:
        dataroot_gt (str): Data root path for gt.
        dataroot_lq (str): Data root path for lq.
        dataroot_flow (str, optional): Data root path for flow.
        meta_info_file (str): Path for meta information file.
        val_partition (str): Validation partition types. 'REDS4' or 'official'.
        io_backend (dict): IO backend type and other kwarg.
        num_frame (int): Window size for input frames.
        gt_size (int): Cropped patched size for gt patches.
        interval_list (list): Interval list for temporal augmentation.
        random_reverse (bool): Random reverse input frames.
        use_hflip (bool): Use horizontal flips.
        use_rot (bool): Use rotation (use vertical flip and transposing h and w for implementation).
        scale (bool): Scale, which will be added automatically.
    """

    def __init__(self, opt):
        super(REDSRecurrentDataset, self).__init__()
        self.opt = opt
        self.gt_root, self.lq_root = Path(opt['dataroot_gt']), Path(opt['dataroot_lq'])
        self.num_frame = opt['num_frame']

        self.keys = []
        with open(opt['meta_info_file'], 'r') as fin:
            for line in fin:
                folder, frame_num, _ = line.split(' ')
                self.keys.extend([f'{folder}/{i:08d}' for i in range(int(frame_num))])

        # remove the video clips used in validation
        if opt['val_partition'] == 'REDS4':
            val_partition = ['000', '011', '015', '020']
        elif opt['val_partition'] == 'official':
            val_partition = [f'{v:03d}' for v in range(240, 270)]
        else:
            raise ValueError(f'Wrong validation partition {opt["val_partition"]}.'
                             f"Supported ones are ['official', 'REDS4'].")
        if opt['test_mode']:
            self.keys = [v for v in self.keys if v.split('/')[0] in val_partition]
        else:
            self.keys = [v for v in self.keys if v.split('/')[0] not in val_partition]

        # file client (io backend)
        self.file_client = None
        self.io_backend_opt = opt['io_backend']
        self.is_lmdb = False
        if self.io_backend_opt['type'] == 'lmdb':
            self.is_lmdb = True
            if hasattr(self, 'flow_root') and self.flow_root is not None:
                self.io_backend_opt['db_paths'] = [self.lq_root, self.gt_root, self.flow_root]
                self.io_backend_opt['client_keys'] = ['lq', 'gt', 'flow']
            else:
                self.io_backend_opt['db_paths'] = [self.lq_root, self.gt_root]
                self.io_backend_opt['client_keys'] = ['lq', 'gt']

        # temporal augmentation configs
        self.interval_list = opt.get('interval_list', [1])
        self.random_reverse = opt.get('random_reverse', False)
        interval_str = ','.join(str(x) for x in self.interval_list)
        logger = get_root_logger()
        logger.info(f'Temporal augmentation interval list: [{interval_str}]; '
                    f'random reverse is {self.random_reverse}.')

    def __getitem__(self, index):
        if self.file_client is None:
            self.file_client = FileClient(self.io_backend_opt.pop('type'), **self.io_backend_opt)

        scale = self.opt['scale']
        gt_size = self.opt['gt_size']
        key = self.keys[index]
        clip_name, frame_name = key.split('/')  # key example: 000/00000000

        # determine the neighboring frames
        interval = random.choice(self.interval_list)

        # ensure not exceeding the borders
        start_frame_idx = int(frame_name)
        if start_frame_idx > 100 - self.num_frame * interval:
            start_frame_idx = random.randint(0, 100 - self.num_frame * interval)
        end_frame_idx = start_frame_idx + self.num_frame * interval

        neighbor_list = list(range(start_frame_idx, end_frame_idx, interval))

        # random reverse
        if self.random_reverse and random.random() < 0.5:
            neighbor_list.reverse()

        # get the neighboring LQ and GT frames
        img_lqs = []
        img_gts = []
        for neighbor in neighbor_list:
            if self.is_lmdb:
                img_lq_path = f'{clip_name}/{neighbor:08d}'
                img_gt_path = f'{clip_name}/{neighbor:08d}'
            else:
                img_lq_path = self.lq_root / clip_name / f'{neighbor:08d}.png'
                img_gt_path = self.gt_root / clip_name / f'{neighbor:08d}.png'

            # get LQ
            img_bytes = self.file_client.get(img_lq_path, 'lq')
            img_lq = imfrombytes(img_bytes, float32=True)
            img_lqs.append(img_lq)

            # get GT
            img_bytes = self.file_client.get(img_gt_path, 'gt')
            img_gt = imfrombytes(img_bytes, float32=True)
            img_gts.append(img_gt)

        # randomly crop
        img_gts, img_lqs = paired_random_crop(img_gts, img_lqs, gt_size, scale, img_gt_path)

        # augmentation - flip, rotate
        img_lqs.extend(img_gts)
        img_results = augment(img_lqs, self.opt['use_hflip'], self.opt['use_rot'])

        img_results = img2tensor(img_results)
        img_gts = torch.stack(img_results[len(img_lqs) // 2:], dim=0)
        img_lqs = torch.stack(img_results[:len(img_lqs) // 2], dim=0)

        # img_lqs: (t, c, h, w)
        # img_gts: (t, c, h, w)
        # key: str
        return {'lq': img_lqs, 'gt': img_gts, 'key': key}

    def __len__(self):
        return len(self.keys)