File size: 15,677 Bytes
0035a82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import random
import numbers
from torchvision.transforms import RandomCrop, RandomResizedCrop
from PIL import Image

def _is_tensor_video_clip(clip):
    if not torch.is_tensor(clip):
        raise TypeError("clip should be Tensor. Got %s" % type(clip))

    if not clip.ndimension() == 4:
        raise ValueError("clip should be 4D. Got %dD" % clip.dim())

    return True


def center_crop_arr(pil_image, image_size):
    """
    Center cropping implementation from ADM.
    https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diffusion/image_datasets.py#L126
    """
    while min(*pil_image.size) >= 2 * image_size:
        pil_image = pil_image.resize(
            tuple(x // 2 for x in pil_image.size), resample=Image.BOX
        )

    scale = image_size / min(*pil_image.size)
    pil_image = pil_image.resize(
        tuple(round(x * scale) for x in pil_image.size), resample=Image.BICUBIC
    )

    arr = np.array(pil_image)
    crop_y = (arr.shape[0] - image_size) // 2
    crop_x = (arr.shape[1] - image_size) // 2
    return Image.fromarray(arr[crop_y: crop_y + image_size, crop_x: crop_x + image_size])


def crop(clip, i, j, h, w):
    """
    Args:
        clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
    """
    if len(clip.size()) != 4:
        raise ValueError("clip should be a 4D tensor")
    return clip[..., i : i + h, j : j + w]


def resize(clip, target_size, interpolation_mode):
    if len(target_size) != 2:
        raise ValueError(f"target size should be tuple (height, width), instead got {target_size}")
    return torch.nn.functional.interpolate(clip, size=target_size, mode=interpolation_mode, align_corners=False)

def resize_scale(clip, target_size, interpolation_mode):
    if len(target_size) != 2:
        raise ValueError(f"target size should be tuple (height, width), instead got {target_size}")
    H, W = clip.size(-2), clip.size(-1)
    scale_ = target_size[0] / min(H, W)
    return torch.nn.functional.interpolate(clip, scale_factor=scale_, mode=interpolation_mode, align_corners=False)

def resize_with_scale_factor(clip, scale_factor, interpolation_mode):
    return torch.nn.functional.interpolate(clip, scale_factor=scale_factor, mode=interpolation_mode, align_corners=False)

def resize_scale_with_height(clip, target_size, interpolation_mode):
    H, W = clip.size(-2), clip.size(-1)
    scale_ = target_size / H
    return torch.nn.functional.interpolate(clip, scale_factor=scale_, mode=interpolation_mode, align_corners=False)

def resize_scale_with_weight(clip, target_size, interpolation_mode):
    H, W = clip.size(-2), clip.size(-1)
    scale_ = target_size / W
    return torch.nn.functional.interpolate(clip, scale_factor=scale_, mode=interpolation_mode, align_corners=False)


def resized_crop(clip, i, j, h, w, size, interpolation_mode="bilinear"):
    """
    Do spatial cropping and resizing to the video clip
    Args:
        clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        i (int): i in (i,j) i.e coordinates of the upper left corner.
        j (int): j in (i,j) i.e coordinates of the upper left corner.
        h (int): Height of the cropped region.
        w (int): Width of the cropped region.
        size (tuple(int, int)): height and width of resized clip
    Returns:
        clip (torch.tensor): Resized and cropped clip. Size is (T, C, H, W)
    """
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    clip = crop(clip, i, j, h, w)
    clip = resize(clip, size, interpolation_mode)
    return clip


def center_crop(clip, crop_size):
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    h, w = clip.size(-2), clip.size(-1)
    # print(clip.shape)
    th, tw = crop_size
    if h < th or w < tw:
        # print(h, w)
        raise ValueError("height {} and width {} must be no smaller than crop_size".format(h, w))

    i = int(round((h - th) / 2.0))
    j = int(round((w - tw) / 2.0))
    return crop(clip, i, j, th, tw)


def center_crop_using_short_edge(clip):
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    h, w = clip.size(-2), clip.size(-1)
    if h < w:
        th, tw = h, h
        i = 0
        j = int(round((w - tw) / 2.0))
    else:
        th, tw = w, w
        i = int(round((h - th) / 2.0))
        j = 0
    return crop(clip, i, j, th, tw)


def random_shift_crop(clip):
    '''
    Slide along the long edge, with the short edge as crop size
    '''
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    h, w = clip.size(-2), clip.size(-1)
    
    if h <= w:
        long_edge = w
        short_edge = h
    else:
        long_edge = h
        short_edge =w

    th, tw = short_edge, short_edge

    i = torch.randint(0, h - th + 1, size=(1,)).item()
    j = torch.randint(0, w - tw + 1, size=(1,)).item()
    return crop(clip, i, j, th, tw)


def to_tensor(clip):
    """
    Convert tensor data type from uint8 to float, divide value by 255.0 and
    permute the dimensions of clip tensor
    Args:
        clip (torch.tensor, dtype=torch.uint8): Size is (T, C, H, W)
    Return:
        clip (torch.tensor, dtype=torch.float): Size is (T, C, H, W)
    """
    _is_tensor_video_clip(clip)
    if not clip.dtype == torch.uint8:
        raise TypeError("clip tensor should have data type uint8. Got %s" % str(clip.dtype))
    # return clip.float().permute(3, 0, 1, 2) / 255.0
    return clip.float() / 255.0


def normalize(clip, mean, std, inplace=False):
    """
    Args:
        clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W)
        mean (tuple): pixel RGB mean. Size is (3)
        std (tuple): pixel standard deviation. Size is (3)
    Returns:
        normalized clip (torch.tensor): Size is (T, C, H, W)
    """
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    if not inplace:
        clip = clip.clone()
    mean = torch.as_tensor(mean, dtype=clip.dtype, device=clip.device)
    # print(mean)
    std = torch.as_tensor(std, dtype=clip.dtype, device=clip.device)
    clip.sub_(mean[:, None, None, None]).div_(std[:, None, None, None])
    return clip


def hflip(clip):
    """
    Args:
        clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W)
    Returns:
        flipped clip (torch.tensor): Size is (T, C, H, W)
    """
    if not _is_tensor_video_clip(clip):
        raise ValueError("clip should be a 4D torch.tensor")
    return clip.flip(-1)


class RandomCropVideo:
    def __init__(self, size):
        if isinstance(size, numbers.Number):
            self.size = (int(size), int(size))
        else:
            self.size = size

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: randomly cropped video clip.
                size is (T, C, OH, OW)
        """
        i, j, h, w = self.get_params(clip)
        return crop(clip, i, j, h, w)
    
    def get_params(self, clip):
        h, w = clip.shape[-2:]
        th, tw = self.size

        if h < th or w < tw:
            raise ValueError(f"Required crop size {(th, tw)} is larger than input image size {(h, w)}")

        if w == tw and h == th:
            return 0, 0, h, w

        i = torch.randint(0, h - th + 1, size=(1,)).item()
        j = torch.randint(0, w - tw + 1, size=(1,)).item()

        return i, j, th, tw

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size})"
    
class CenterCropResizeVideo:
    '''
    First use the short side for cropping length, 
    center crop video, then resize to the specified size
    '''
    def __init__(
        self,
        size,
        interpolation_mode="bilinear",
    ):
        if isinstance(size, tuple):
            if len(size) != 2:
                raise ValueError(f"size should be tuple (height, width), instead got {size}")
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
       

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: scale resized / center cropped video clip.
                size is (T, C, crop_size, crop_size)
        """
        # print(clip.shape)
        clip_center_crop = center_crop_using_short_edge(clip)
        # print(clip_center_crop.shape) 320 512
        clip_center_crop_resize = resize(clip_center_crop, target_size=self.size, interpolation_mode=self.interpolation_mode)
        return clip_center_crop_resize

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size}, interpolation_mode={self.interpolation_mode}"
    
class WebVideo320512:
    def __init__(
        self,
        size,
        interpolation_mode="bilinear",
    ):
        if isinstance(size, tuple):
            if len(size) != 2:
                raise ValueError(f"size should be tuple (height, width), instead got {size}")
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
       

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: scale resized / center cropped video clip.
                size is (T, C, crop_size, crop_size)
        """
        # add aditional one pixel for avoiding error in center crop 
        h, w = clip.size(-2), clip.size(-1)
        # print('before resize', clip.shape)
        if h < 320:
            clip = resize_scale_with_height(clip=clip, target_size=321, interpolation_mode=self.interpolation_mode)
            # print('after h resize', clip.shape)
        if w < 512:
            clip = resize_scale_with_weight(clip=clip, target_size=513, interpolation_mode=self.interpolation_mode)
            # print('after w resize', clip.shape)
        clip_center_crop = center_crop(clip, self.size)
        # print(clip_center_crop.shape)
        return clip_center_crop

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size}, interpolation_mode={self.interpolation_mode}"

class UCFCenterCropVideo:
    '''
    First scale to the specified size in equal proportion to the short edge, 
    then center cropping
    '''
    def __init__(
        self,
        size,
        interpolation_mode="bilinear",
    ):
        if isinstance(size, tuple):
            if len(size) != 2:
                raise ValueError(f"size should be tuple (height, width), instead got {size}")
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
       

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: scale resized / center cropped video clip.
                size is (T, C, crop_size, crop_size)
        """
        clip_resize = resize_scale(clip=clip, target_size=self.size, interpolation_mode=self.interpolation_mode)
        clip_center_crop = center_crop(clip_resize, self.size)
        return clip_center_crop

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size}, interpolation_mode={self.interpolation_mode}"
   

class CenterCropVideo:
    def __init__(
        self,
        size,
        interpolation_mode="bilinear",
    ):
        if isinstance(size, tuple):
            if len(size) != 2:
                raise ValueError(f"size should be tuple (height, width), instead got {size}")
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
       

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: center cropped video clip.
                size is (T, C, crop_size, crop_size)
        """
        clip_center_crop = center_crop(clip, self.size)
        return clip_center_crop

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size}, interpolation_mode={self.interpolation_mode}"
    

class NormalizeVideo:
    """
    Normalize the video clip by mean subtraction and division by standard deviation
    Args:
        mean (3-tuple): pixel RGB mean
        std (3-tuple): pixel RGB standard deviation
        inplace (boolean): whether do in-place normalization
    """

    def __init__(self, mean, std, inplace=False):
        self.mean = mean
        self.std = std
        self.inplace = inplace

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): video clip must be normalized. Size is (C, T, H, W)
        """
        return normalize(clip, self.mean, self.std, self.inplace)

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(mean={self.mean}, std={self.std}, inplace={self.inplace})"


class ToTensorVideo:
    """
    Convert tensor data type from uint8 to float, divide value by 255.0 and
    permute the dimensions of clip tensor
    """

    def __init__(self):
        pass

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor, dtype=torch.uint8): Size is (T, C, H, W)
        Return:
            clip (torch.tensor, dtype=torch.float): Size is (T, C, H, W)
        """
        return to_tensor(clip)

    def __repr__(self) -> str:
        return self.__class__.__name__


class ResizeVideo():
    '''
    First use the short side for cropping length, 
    center crop video, then resize to the specified size
    '''
    def __init__(
        self,
        size,
        interpolation_mode="bilinear",
    ):
        if isinstance(size, tuple):
            if len(size) != 2:
                raise ValueError(f"size should be tuple (height, width), instead got {size}")
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
       

    def __call__(self, clip):
        """
        Args:
            clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)
        Returns:
            torch.tensor: scale resized / center cropped video clip.
                size is (T, C, crop_size, crop_size)
        """
        clip_resize = resize(clip, target_size=self.size, interpolation_mode=self.interpolation_mode)
        return clip_resize

    def __repr__(self) -> str:
        return f"{self.__class__.__name__}(size={self.size}, interpolation_mode={self.interpolation_mode}"
    
#  ------------------------------------------------------------
#  ---------------------  Sampling  ---------------------------
#  ------------------------------------------------------------
class TemporalRandomCrop(object):
	"""Temporally crop the given frame indices at a random location.

	Args:
		size (int): Desired length of frames will be seen in the model.
	"""

	def __init__(self, size):
		self.size = size

	def __call__(self, total_frames):
		rand_end = max(0, total_frames - self.size - 1)
		begin_index = random.randint(0, rand_end)
		end_index = min(begin_index + self.size, total_frames)
		return begin_index, end_index