File size: 17,421 Bytes
3e06e1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) OpenMMLab. All rights reserved.
import warnings
from typing import Optional, Sequence, Union

import numpy as np
import torch
from torch import Tensor

from mmdet.registry import TASK_UTILS
from mmdet.structures.bbox import BaseBoxes, HorizontalBoxes, get_box_tensor
from .base_bbox_coder import BaseBBoxCoder


@TASK_UTILS.register_module()
class DeltaXYWHBBoxCoder(BaseBBoxCoder):
    """Delta XYWH BBox coder.

    Following the practice in `R-CNN <https://arxiv.org/abs/1311.2524>`_,
    this coder encodes bbox (x1, y1, x2, y2) into delta (dx, dy, dw, dh) and
    decodes delta (dx, dy, dw, dh) back to original bbox (x1, y1, x2, y2).

    Args:
        target_means (Sequence[float]): Denormalizing means of target for
            delta coordinates
        target_stds (Sequence[float]): Denormalizing standard deviation of
            target for delta coordinates
        clip_border (bool, optional): Whether clip the objects outside the
            border of the image. Defaults to True.
        add_ctr_clamp (bool): Whether to add center clamp, when added, the
            predicted box is clamped is its center is too far away from
            the original anchor's center. Only used by YOLOF. Default False.
        ctr_clamp (int): the maximum pixel shift to clamp. Only used by YOLOF.
            Default 32.
    """

    def __init__(self,
                 target_means: Sequence[float] = (0., 0., 0., 0.),
                 target_stds: Sequence[float] = (1., 1., 1., 1.),
                 clip_border: bool = True,
                 add_ctr_clamp: bool = False,
                 ctr_clamp: int = 32,
                 **kwargs) -> None:
        super().__init__(**kwargs)
        self.means = target_means
        self.stds = target_stds
        self.clip_border = clip_border
        self.add_ctr_clamp = add_ctr_clamp
        self.ctr_clamp = ctr_clamp

    def encode(self, bboxes: Union[Tensor, BaseBoxes],
               gt_bboxes: Union[Tensor, BaseBoxes]) -> Tensor:
        """Get box regression transformation deltas that can be used to
        transform the ``bboxes`` into the ``gt_bboxes``.

        Args:
            bboxes (torch.Tensor or :obj:`BaseBoxes`): Source boxes,
                e.g., object proposals.
            gt_bboxes (torch.Tensor or :obj:`BaseBoxes`): Target of the
                transformation, e.g., ground-truth boxes.

        Returns:
            torch.Tensor: Box transformation deltas
        """
        bboxes = get_box_tensor(bboxes)
        gt_bboxes = get_box_tensor(gt_bboxes)
        assert bboxes.size(0) == gt_bboxes.size(0)
        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
        encoded_bboxes = bbox2delta(bboxes, gt_bboxes, self.means, self.stds)
        return encoded_bboxes

    def decode(
        self,
        bboxes: Union[Tensor, BaseBoxes],
        pred_bboxes: Tensor,
        max_shape: Optional[Union[Sequence[int], Tensor,
                                  Sequence[Sequence[int]]]] = None,
        wh_ratio_clip: Optional[float] = 16 / 1000
    ) -> Union[Tensor, BaseBoxes]:
        """Apply transformation `pred_bboxes` to `boxes`.

        Args:
            bboxes (torch.Tensor or :obj:`BaseBoxes`): Basic boxes. Shape
                (B, N, 4) or (N, 4)
            pred_bboxes (Tensor): Encoded offsets with respect to each roi.
               Has shape (B, N, num_classes * 4) or (B, N, 4) or
               (N, num_classes * 4) or (N, 4). Note N = num_anchors * W * H
               when rois is a grid of anchors.Offset encoding follows [1]_.
            max_shape (Sequence[int] or torch.Tensor or Sequence[
               Sequence[int]],optional): Maximum bounds for boxes, specifies
               (H, W, C) or (H, W). If bboxes shape is (B, N, 4), then
               the max_shape should be a Sequence[Sequence[int]]
               and the length of max_shape should also be B.
            wh_ratio_clip (float, optional): The allowed ratio between
                width and height.

        Returns:
            Union[torch.Tensor, :obj:`BaseBoxes`]: Decoded boxes.
        """
        bboxes = get_box_tensor(bboxes)
        assert pred_bboxes.size(0) == bboxes.size(0)
        if pred_bboxes.ndim == 3:
            assert pred_bboxes.size(1) == bboxes.size(1)

        if pred_bboxes.ndim == 2 and not torch.onnx.is_in_onnx_export():
            # single image decode
            decoded_bboxes = delta2bbox(bboxes, pred_bboxes, self.means,
                                        self.stds, max_shape, wh_ratio_clip,
                                        self.clip_border, self.add_ctr_clamp,
                                        self.ctr_clamp)
        else:
            if pred_bboxes.ndim == 3 and not torch.onnx.is_in_onnx_export():
                warnings.warn(
                    'DeprecationWarning: onnx_delta2bbox is deprecated '
                    'in the case of batch decoding and non-ONNX, '
                    'please use “delta2bbox” instead. In order to improve '
                    'the decoding speed, the batch function will no '
                    'longer be supported. ')
            decoded_bboxes = onnx_delta2bbox(bboxes, pred_bboxes, self.means,
                                             self.stds, max_shape,
                                             wh_ratio_clip, self.clip_border,
                                             self.add_ctr_clamp,
                                             self.ctr_clamp)

        if self.use_box_type:
            assert decoded_bboxes.size(-1) == 4, \
                ('Cannot warp decoded boxes with box type when decoded boxes'
                 'have shape of (N, num_classes * 4)')
            decoded_bboxes = HorizontalBoxes(decoded_bboxes)
        return decoded_bboxes


def bbox2delta(
    proposals: Tensor,
    gt: Tensor,
    means: Sequence[float] = (0., 0., 0., 0.),
    stds: Sequence[float] = (1., 1., 1., 1.)
) -> Tensor:
    """Compute deltas of proposals w.r.t. gt.

    We usually compute the deltas of x, y, w, h of proposals w.r.t ground
    truth bboxes to get regression target.
    This is the inverse function of :func:`delta2bbox`.

    Args:
        proposals (Tensor): Boxes to be transformed, shape (N, ..., 4)
        gt (Tensor): Gt bboxes to be used as base, shape (N, ..., 4)
        means (Sequence[float]): Denormalizing means for delta coordinates
        stds (Sequence[float]): Denormalizing standard deviation for delta
            coordinates

    Returns:
        Tensor: deltas with shape (N, 4), where columns represent dx, dy,
            dw, dh.
    """
    assert proposals.size() == gt.size()

    proposals = proposals.float()
    gt = gt.float()
    px = (proposals[..., 0] + proposals[..., 2]) * 0.5
    py = (proposals[..., 1] + proposals[..., 3]) * 0.5
    pw = proposals[..., 2] - proposals[..., 0]
    ph = proposals[..., 3] - proposals[..., 1]

    gx = (gt[..., 0] + gt[..., 2]) * 0.5
    gy = (gt[..., 1] + gt[..., 3]) * 0.5
    gw = gt[..., 2] - gt[..., 0]
    gh = gt[..., 3] - gt[..., 1]

    dx = (gx - px) / pw
    dy = (gy - py) / ph
    dw = torch.log(gw / pw)
    dh = torch.log(gh / ph)
    deltas = torch.stack([dx, dy, dw, dh], dim=-1)

    means = deltas.new_tensor(means).unsqueeze(0)
    stds = deltas.new_tensor(stds).unsqueeze(0)
    deltas = deltas.sub_(means).div_(stds)

    return deltas


def delta2bbox(rois: Tensor,
               deltas: Tensor,
               means: Sequence[float] = (0., 0., 0., 0.),
               stds: Sequence[float] = (1., 1., 1., 1.),
               max_shape: Optional[Union[Sequence[int], Tensor,
                                         Sequence[Sequence[int]]]] = None,
               wh_ratio_clip: float = 16 / 1000,
               clip_border: bool = True,
               add_ctr_clamp: bool = False,
               ctr_clamp: int = 32) -> Tensor:
    """Apply deltas to shift/scale base boxes.

    Typically the rois are anchor or proposed bounding boxes and the deltas are
    network outputs used to shift/scale those boxes.
    This is the inverse function of :func:`bbox2delta`.

    Args:
        rois (Tensor): Boxes to be transformed. Has shape (N, 4).
        deltas (Tensor): Encoded offsets relative to each roi.
            Has shape (N, num_classes * 4) or (N, 4). Note
            N = num_base_anchors * W * H, when rois is a grid of
            anchors. Offset encoding follows [1]_.
        means (Sequence[float]): Denormalizing means for delta coordinates.
            Default (0., 0., 0., 0.).
        stds (Sequence[float]): Denormalizing standard deviation for delta
            coordinates. Default (1., 1., 1., 1.).
        max_shape (tuple[int, int]): Maximum bounds for boxes, specifies
           (H, W). Default None.
        wh_ratio_clip (float): Maximum aspect ratio for boxes. Default
            16 / 1000.
        clip_border (bool, optional): Whether clip the objects outside the
            border of the image. Default True.
        add_ctr_clamp (bool): Whether to add center clamp. When set to True,
            the center of the prediction bounding box will be clamped to
            avoid being too far away from the center of the anchor.
            Only used by YOLOF. Default False.
        ctr_clamp (int): the maximum pixel shift to clamp. Only used by YOLOF.
            Default 32.

    Returns:
        Tensor: Boxes with shape (N, num_classes * 4) or (N, 4), where 4
           represent tl_x, tl_y, br_x, br_y.

    References:
        .. [1] https://arxiv.org/abs/1311.2524

    Example:
        >>> rois = torch.Tensor([[ 0.,  0.,  1.,  1.],
        >>>                      [ 0.,  0.,  1.,  1.],
        >>>                      [ 0.,  0.,  1.,  1.],
        >>>                      [ 5.,  5.,  5.,  5.]])
        >>> deltas = torch.Tensor([[  0.,   0.,   0.,   0.],
        >>>                        [  1.,   1.,   1.,   1.],
        >>>                        [  0.,   0.,   2.,  -1.],
        >>>                        [ 0.7, -1.9, -0.5,  0.3]])
        >>> delta2bbox(rois, deltas, max_shape=(32, 32, 3))
        tensor([[0.0000, 0.0000, 1.0000, 1.0000],
                [0.1409, 0.1409, 2.8591, 2.8591],
                [0.0000, 0.3161, 4.1945, 0.6839],
                [5.0000, 5.0000, 5.0000, 5.0000]])
    """
    num_bboxes, num_classes = deltas.size(0), deltas.size(1) // 4
    if num_bboxes == 0:
        return deltas

    deltas = deltas.reshape(-1, 4)

    means = deltas.new_tensor(means).view(1, -1)
    stds = deltas.new_tensor(stds).view(1, -1)
    denorm_deltas = deltas * stds + means

    dxy = denorm_deltas[:, :2]
    dwh = denorm_deltas[:, 2:]

    # Compute width/height of each roi
    rois_ = rois.repeat(1, num_classes).reshape(-1, 4)
    pxy = ((rois_[:, :2] + rois_[:, 2:]) * 0.5)
    pwh = (rois_[:, 2:] - rois_[:, :2])

    dxy_wh = pwh * dxy

    max_ratio = np.abs(np.log(wh_ratio_clip))
    if add_ctr_clamp:
        dxy_wh = torch.clamp(dxy_wh, max=ctr_clamp, min=-ctr_clamp)
        dwh = torch.clamp(dwh, max=max_ratio)
    else:
        dwh = dwh.clamp(min=-max_ratio, max=max_ratio)

    gxy = pxy + dxy_wh
    gwh = pwh * dwh.exp()
    x1y1 = gxy - (gwh * 0.5)
    x2y2 = gxy + (gwh * 0.5)
    bboxes = torch.cat([x1y1, x2y2], dim=-1)
    if clip_border and max_shape is not None:
        bboxes[..., 0::2].clamp_(min=0, max=max_shape[1])
        bboxes[..., 1::2].clamp_(min=0, max=max_shape[0])
    bboxes = bboxes.reshape(num_bboxes, -1)
    return bboxes


def onnx_delta2bbox(rois: Tensor,
                    deltas: Tensor,
                    means: Sequence[float] = (0., 0., 0., 0.),
                    stds: Sequence[float] = (1., 1., 1., 1.),
                    max_shape: Optional[Union[Sequence[int], Tensor,
                                              Sequence[Sequence[int]]]] = None,
                    wh_ratio_clip: float = 16 / 1000,
                    clip_border: Optional[bool] = True,
                    add_ctr_clamp: bool = False,
                    ctr_clamp: int = 32) -> Tensor:
    """Apply deltas to shift/scale base boxes.

    Typically the rois are anchor or proposed bounding boxes and the deltas are
    network outputs used to shift/scale those boxes.
    This is the inverse function of :func:`bbox2delta`.

    Args:
        rois (Tensor): Boxes to be transformed. Has shape (N, 4) or (B, N, 4)
        deltas (Tensor): Encoded offsets with respect to each roi.
            Has shape (B, N, num_classes * 4) or (B, N, 4) or
            (N, num_classes * 4) or (N, 4). Note N = num_anchors * W * H
            when rois is a grid of anchors.Offset encoding follows [1]_.
        means (Sequence[float]): Denormalizing means for delta coordinates.
            Default (0., 0., 0., 0.).
        stds (Sequence[float]): Denormalizing standard deviation for delta
            coordinates. Default (1., 1., 1., 1.).
        max_shape (Sequence[int] or torch.Tensor or Sequence[
            Sequence[int]],optional): Maximum bounds for boxes, specifies
            (H, W, C) or (H, W). If rois shape is (B, N, 4), then
            the max_shape should be a Sequence[Sequence[int]]
            and the length of max_shape should also be B. Default None.
        wh_ratio_clip (float): Maximum aspect ratio for boxes.
            Default 16 / 1000.
        clip_border (bool, optional): Whether clip the objects outside the
            border of the image. Default True.
        add_ctr_clamp (bool): Whether to add center clamp, when added, the
            predicted box is clamped is its center is too far away from
            the original anchor's center. Only used by YOLOF. Default False.
        ctr_clamp (int): the maximum pixel shift to clamp. Only used by YOLOF.
            Default 32.

    Returns:
        Tensor: Boxes with shape (B, N, num_classes * 4) or (B, N, 4) or
           (N, num_classes * 4) or (N, 4), where 4 represent
           tl_x, tl_y, br_x, br_y.

    References:
        .. [1] https://arxiv.org/abs/1311.2524

    Example:
        >>> rois = torch.Tensor([[ 0.,  0.,  1.,  1.],
        >>>                      [ 0.,  0.,  1.,  1.],
        >>>                      [ 0.,  0.,  1.,  1.],
        >>>                      [ 5.,  5.,  5.,  5.]])
        >>> deltas = torch.Tensor([[  0.,   0.,   0.,   0.],
        >>>                        [  1.,   1.,   1.,   1.],
        >>>                        [  0.,   0.,   2.,  -1.],
        >>>                        [ 0.7, -1.9, -0.5,  0.3]])
        >>> delta2bbox(rois, deltas, max_shape=(32, 32, 3))
        tensor([[0.0000, 0.0000, 1.0000, 1.0000],
                [0.1409, 0.1409, 2.8591, 2.8591],
                [0.0000, 0.3161, 4.1945, 0.6839],
                [5.0000, 5.0000, 5.0000, 5.0000]])
    """
    means = deltas.new_tensor(means).view(1,
                                          -1).repeat(1,
                                                     deltas.size(-1) // 4)
    stds = deltas.new_tensor(stds).view(1, -1).repeat(1, deltas.size(-1) // 4)
    denorm_deltas = deltas * stds + means
    dx = denorm_deltas[..., 0::4]
    dy = denorm_deltas[..., 1::4]
    dw = denorm_deltas[..., 2::4]
    dh = denorm_deltas[..., 3::4]

    x1, y1 = rois[..., 0], rois[..., 1]
    x2, y2 = rois[..., 2], rois[..., 3]
    # Compute center of each roi
    px = ((x1 + x2) * 0.5).unsqueeze(-1).expand_as(dx)
    py = ((y1 + y2) * 0.5).unsqueeze(-1).expand_as(dy)
    # Compute width/height of each roi
    pw = (x2 - x1).unsqueeze(-1).expand_as(dw)
    ph = (y2 - y1).unsqueeze(-1).expand_as(dh)

    dx_width = pw * dx
    dy_height = ph * dy

    max_ratio = np.abs(np.log(wh_ratio_clip))
    if add_ctr_clamp:
        dx_width = torch.clamp(dx_width, max=ctr_clamp, min=-ctr_clamp)
        dy_height = torch.clamp(dy_height, max=ctr_clamp, min=-ctr_clamp)
        dw = torch.clamp(dw, max=max_ratio)
        dh = torch.clamp(dh, max=max_ratio)
    else:
        dw = dw.clamp(min=-max_ratio, max=max_ratio)
        dh = dh.clamp(min=-max_ratio, max=max_ratio)
    # Use exp(network energy) to enlarge/shrink each roi
    gw = pw * dw.exp()
    gh = ph * dh.exp()
    # Use network energy to shift the center of each roi
    gx = px + dx_width
    gy = py + dy_height
    # Convert center-xy/width/height to top-left, bottom-right
    x1 = gx - gw * 0.5
    y1 = gy - gh * 0.5
    x2 = gx + gw * 0.5
    y2 = gy + gh * 0.5

    bboxes = torch.stack([x1, y1, x2, y2], dim=-1).view(deltas.size())

    if clip_border and max_shape is not None:
        # clip bboxes with dynamic `min` and `max` for onnx
        if torch.onnx.is_in_onnx_export():
            from mmdet.core.export import dynamic_clip_for_onnx
            x1, y1, x2, y2 = dynamic_clip_for_onnx(x1, y1, x2, y2, max_shape)
            bboxes = torch.stack([x1, y1, x2, y2], dim=-1).view(deltas.size())
            return bboxes
        if not isinstance(max_shape, torch.Tensor):
            max_shape = x1.new_tensor(max_shape)
        max_shape = max_shape[..., :2].type_as(x1)
        if max_shape.ndim == 2:
            assert bboxes.ndim == 3
            assert max_shape.size(0) == bboxes.size(0)

        min_xy = x1.new_tensor(0)
        max_xy = torch.cat(
            [max_shape] * (deltas.size(-1) // 2),
            dim=-1).flip(-1).unsqueeze(-2)
        bboxes = torch.where(bboxes < min_xy, min_xy, bboxes)
        bboxes = torch.where(bboxes > max_xy, max_xy, bboxes)

    return bboxes