File size: 12,037 Bytes
b334e29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from collections.abc import Sequence

import mmcv
import numpy as np
import torch
from mmcv.parallel import DataContainer as DC

from ..builder import PIPELINES


def to_tensor(data):
    """Convert objects of various python types to :obj:`torch.Tensor`.

    Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
    :class:`Sequence`, :class:`int` and :class:`float`.

    Args:
        data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
            be converted.
    """

    if isinstance(data, torch.Tensor):
        return data
    elif isinstance(data, np.ndarray):
        return torch.from_numpy(data)
    elif isinstance(data, Sequence) and not mmcv.is_str(data):
        return torch.tensor(data)
    elif isinstance(data, int):
        return torch.LongTensor([data])
    elif isinstance(data, float):
        return torch.FloatTensor([data])
    else:
        raise TypeError(f'type {type(data)} cannot be converted to tensor.')


@PIPELINES.register_module()
class ToTensor(object):
    """Convert some results to :obj:`torch.Tensor` by given keys.

    Args:
        keys (Sequence[str]): Keys that need to be converted to Tensor.
    """

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

    def __call__(self, results):
        """Call function to convert data in results to :obj:`torch.Tensor`.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            dict: The result dict contains the data converted
                to :obj:`torch.Tensor`.
        """
        for key in self.keys:
            results[key] = to_tensor(results[key])
        return results

    def __repr__(self):
        return self.__class__.__name__ + f'(keys={self.keys})'


@PIPELINES.register_module()
class ImageToTensor(object):
    """Convert image to :obj:`torch.Tensor` by given keys.

    The dimension order of input image is (H, W, C). The pipeline will convert
    it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
    (1, H, W).

    Args:
        keys (Sequence[str]): Key of images to be converted to Tensor.
    """

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

    def __call__(self, results):
        """Call function to convert image in results to :obj:`torch.Tensor` and
        transpose the channel order.

        Args:
            results (dict): Result dict contains the image data to convert.

        Returns:
            dict: The result dict contains the image converted
                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
        """
        for key in self.keys:
            img = results[key]
            if len(img.shape) < 3:
                img = np.expand_dims(img, -1)
            results[key] = to_tensor(img.transpose(2, 0, 1))
        return results

    def __repr__(self):
        return self.__class__.__name__ + f'(keys={self.keys})'


@PIPELINES.register_module()
class Transpose(object):
    """Transpose some results by given keys.

    Args:
        keys (Sequence[str]): Keys of results to be transposed.
        order (Sequence[int]): Order of transpose.
    """

    def __init__(self, keys, order):
        self.keys = keys
        self.order = order

    def __call__(self, results):
        """Call function to transpose the channel order of data in results.

        Args:
            results (dict): Result dict contains the data to transpose.

        Returns:
            dict: The result dict contains the data transposed to \
                ``self.order``.
        """
        for key in self.keys:
            results[key] = results[key].transpose(self.order)
        return results

    def __repr__(self):
        return self.__class__.__name__ + \
            f'(keys={self.keys}, order={self.order})'


@PIPELINES.register_module()
class ToDataContainer(object):
    """Convert results to :obj:`mmcv.DataContainer` by given fields.

    Args:
        fields (Sequence[dict]): Each field is a dict like
            ``dict(key='xxx', **kwargs)``. The ``key`` in result will
            be converted to :obj:`mmcv.DataContainer` with ``**kwargs``.
            Default: ``(dict(key='img', stack=True), dict(key='gt_bboxes'),
            dict(key='gt_labels'))``.
    """

    def __init__(self,
                 fields=(dict(key='img', stack=True), dict(key='gt_bboxes'),
                         dict(key='gt_labels'))):
        self.fields = fields

    def __call__(self, results):
        """Call function to convert data in results to
        :obj:`mmcv.DataContainer`.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            dict: The result dict contains the data converted to \
                :obj:`mmcv.DataContainer`.
        """

        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results

    def __repr__(self):
        return self.__class__.__name__ + f'(fields={self.fields})'


@PIPELINES.register_module()
class DefaultFormatBundle(object):
    """Default formatting bundle.

    It simplifies the pipeline of formatting common fields, including "img",
    "proposals", "gt_bboxes", "gt_labels", "gt_masks" and "gt_semantic_seg".
    These fields are formatted as follows.

    - img: (1)transpose, (2)to tensor, (3)to DataContainer (stack=True)
    - proposals: (1)to tensor, (2)to DataContainer
    - gt_bboxes: (1)to tensor, (2)to DataContainer
    - gt_bboxes_ignore: (1)to tensor, (2)to DataContainer
    - gt_labels: (1)to tensor, (2)to DataContainer
    - gt_masks: (1)to tensor, (2)to DataContainer (cpu_only=True)
    - gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor, \
                       (3)to DataContainer (stack=True)
    """

    def __call__(self, results):
        """Call function to transform and format common fields in results.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            dict: The result dict contains the data that is formatted with \
                default bundle.
        """

        if 'img' in results:
            img = results['img']
            # add default meta keys
            results = self._add_default_meta_keys(results)
            if len(img.shape) < 3:
                img = np.expand_dims(img, -1)
            img = np.ascontiguousarray(img.transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results

    def _add_default_meta_keys(self, results):
        """Add default meta keys.

        We set default meta keys including `pad_shape`, `scale_factor` and
        `img_norm_cfg` to avoid the case where no `Resize`, `Normalize` and
        `Pad` are implemented during the whole pipeline.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            results (dict): Updated result dict contains the data to convert.
        """
        img = results['img']
        results.setdefault('pad_shape', img.shape)
        results.setdefault('scale_factor', 1.0)
        num_channels = 1 if len(img.shape) < 3 else img.shape[2]
        results.setdefault(
            'img_norm_cfg',
            dict(
                mean=np.zeros(num_channels, dtype=np.float32),
                std=np.ones(num_channels, dtype=np.float32),
                to_rgb=False))
        return results

    def __repr__(self):
        return self.__class__.__name__


@PIPELINES.register_module()
class Collect(object):
    """Collect data from the loader relevant to the specific task.

    This is usually the last stage of the data loader pipeline. Typically keys
    is set to some subset of "img", "proposals", "gt_bboxes",
    "gt_bboxes_ignore", "gt_labels", and/or "gt_masks".

    The "img_meta" item is always populated.  The contents of the "img_meta"
    dictionary depends on "meta_keys". By default this includes:

        - "img_shape": shape of the image input to the network as a tuple \
            (h, w, c).  Note that images may be zero padded on the \
            bottom/right if the batch tensor is larger than this shape.

        - "scale_factor": a float indicating the preprocessing scale

        - "flip": a boolean indicating if image flip transform was used

        - "filename": path to the image file

        - "ori_shape": original shape of the image as a tuple (h, w, c)

        - "pad_shape": image shape after padding

        - "img_norm_cfg": a dict of normalization information:

            - mean - per channel mean subtraction
            - std - per channel std divisor
            - to_rgb - bool indicating if bgr was converted to rgb

    Args:
        keys (Sequence[str]): Keys of results to be collected in ``data``.
        meta_keys (Sequence[str], optional): Meta keys to be converted to
            ``mmcv.DataContainer`` and collected in ``data[img_metas]``.
            Default: ``('filename', 'ori_filename', 'ori_shape', 'img_shape',
            'pad_shape', 'scale_factor', 'flip', 'flip_direction',
            'img_norm_cfg')``
    """

    def __init__(self,
                 keys,
                 meta_keys=('filename', 'ori_filename', 'ori_shape',
                            'img_shape', 'pad_shape', 'scale_factor', 'flip',
                            'flip_direction', 'img_norm_cfg')):
        self.keys = keys
        self.meta_keys = meta_keys

    def __call__(self, results):
        """Call function to collect keys in results. The keys in ``meta_keys``
        will be converted to :obj:mmcv.DataContainer.

        Args:
            results (dict): Result dict contains the data to collect.

        Returns:
            dict: The result dict contains the following keys

                - keys in``self.keys``
                - ``img_metas``
        """

        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_metas'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data

    def __repr__(self):
        return self.__class__.__name__ + \
            f'(keys={self.keys}, meta_keys={self.meta_keys})'


@PIPELINES.register_module()
class WrapFieldsToLists(object):
    """Wrap fields of the data dictionary into lists for evaluation.

    This class can be used as a last step of a test or validation
    pipeline for single image evaluation or inference.

    Example:
        >>> test_pipeline = [
        >>>    dict(type='LoadImageFromFile'),
        >>>    dict(type='Normalize',
                    mean=[123.675, 116.28, 103.53],
                    std=[58.395, 57.12, 57.375],
                    to_rgb=True),
        >>>    dict(type='Pad', size_divisor=32),
        >>>    dict(type='ImageToTensor', keys=['img']),
        >>>    dict(type='Collect', keys=['img']),
        >>>    dict(type='WrapFieldsToLists')
        >>> ]
    """

    def __call__(self, results):
        """Call function to wrap fields into lists.

        Args:
            results (dict): Result dict contains the data to wrap.

        Returns:
            dict: The result dict where value of ``self.keys`` are wrapped \
                into list.
        """

        # Wrap dict fields into lists
        for key, val in results.items():
            results[key] = [val]
        return results

    def __repr__(self):
        return f'{self.__class__.__name__}()'