File size: 10,546 Bytes
e8f2571
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) OpenMMLab. All rights reserved.
from typing import Optional, Tuple, Union

import mmcv
import numpy as np
import pycocotools.mask as maskUtils
import torch
from mmcv.transforms import BaseTransform
from mmcv.transforms import LoadAnnotations as MMCV_LoadAnnotations
from mmcv.transforms import LoadImageFromFile
from mmengine.fileio import get
from mmengine.structures import BaseDataElement

from mmdet.registry import TRANSFORMS
from mmdet.structures.bbox import get_box_type
from mmdet.structures.bbox.box_type import autocast_box_type
from mmdet.structures.mask import BitmapMasks, PolygonMasks


@TRANSFORMS.register_module()
class LoadAnnotations(MMCV_LoadAnnotations):
    """Load and process the ``instances`` and ``seg_map`` annotation provided
    by dataset.

    The annotation format is as the following:

    .. code-block:: python

        {
            'instances':
            [
                {
                # List of 4 numbers representing the bounding box of the
                # instance, in (x1, y1, x2, y2) order.
                'bbox': [x1, y1, x2, y2],

                # Label of image classification.
                'bbox_label': 1,

                # Used in instance/panoptic segmentation. The segmentation mask
                # of the instance or the information of segments.
                # 1. If list[list[float]], it represents a list of polygons,
                # one for each connected component of the object. Each
                # list[float] is one simple polygon in the format of
                # [x1, y1, ..., xn, yn] (n≥3). The Xs and Ys are absolute
                # coordinates in unit of pixels.
                # 2. If dict, it represents the per-pixel segmentation mask in
                # COCO’s compressed RLE format. The dict should have keys
                # “size” and “counts”.  Can be loaded by pycocotools
                'mask': list[list[float]] or dict,

                }
            ]
            # Filename of semantic or panoptic segmentation ground truth file.
            'seg_map_path': 'a/b/c'
        }

    After this module, the annotation has been changed to the format below:

    .. code-block:: python

        {
            # In (x1, y1, x2, y2) order, float type. N is the number of bboxes
            # in an image
            'gt_bboxes': BaseBoxes(N, 4)
             # In int type.
            'gt_bboxes_labels': np.ndarray(N, )
             # In built-in class
            'gt_masks': PolygonMasks (H, W) or BitmapMasks (H, W)
             # In uint8 type.
            'gt_seg_map': np.ndarray (H, W)
             # in (x, y, v) order, float type.
        }

    Required Keys:

    - height
    - width
    - instances

      - bbox (optional)
      - bbox_label
      - mask (optional)
      - ignore_flag

    - seg_map_path (optional)

    Added Keys:

    - gt_bboxes (BaseBoxes[torch.float32])
    - gt_bboxes_labels (np.int64)
    - gt_masks (BitmapMasks | PolygonMasks)
    - gt_seg_map (np.uint8)
    - gt_ignore_flags (bool)

    Args:
        with_bbox (bool): Whether to parse and load the bbox annotation.
            Defaults to True.
        with_label (bool): Whether to parse and load the label annotation.
            Defaults to True.
        with_mask (bool): Whether to parse and load the mask annotation.
             Default: False.
        with_seg (bool): Whether to parse and load the semantic segmentation
            annotation. Defaults to False.
        poly2mask (bool): Whether to convert mask to bitmap. Default: True.
        box_type (str): The box type used to wrap the bboxes. If ``box_type``
            is None, gt_bboxes will keep being np.ndarray. Defaults to 'hbox'.
        imdecode_backend (str): The image decoding backend type. The backend
            argument for :func:``mmcv.imfrombytes``.
            See :fun:``mmcv.imfrombytes`` for details.
            Defaults to 'cv2'.
        backend_args (dict, optional): Arguments to instantiate the
            corresponding backend. Defaults to None.
    """

    def __init__(self,
                 with_mask: bool = False,
                 poly2mask: bool = True,
                 box_type: str = 'hbox',
                 **kwargs) -> None:
        super(LoadAnnotations, self).__init__(**kwargs)
        self.with_mask = with_mask
        self.poly2mask = poly2mask
        self.box_type = box_type

    def _load_bboxes(self, results: dict) -> None:
        """Private function to load bounding box annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.
        Returns:
            dict: The dict contains loaded bounding box annotations.
        """
        gt_bboxes = []
        gt_ignore_flags = []
        for instance in results.get('instances', []):
            gt_bboxes.append(instance['bbox'])
            gt_ignore_flags.append(instance['ignore_flag'])
        if self.box_type is None:
            results['gt_bboxes'] = np.array(
                gt_bboxes, dtype=np.float32).reshape((-1, 4))
        else:
            _, box_type_cls = get_box_type(self.box_type)
            results['gt_bboxes'] = box_type_cls(gt_bboxes, dtype=torch.float32)
        results['gt_ignore_flags'] = np.array(gt_ignore_flags, dtype=bool)

    def _load_labels(self, results: dict) -> None:
        """Private function to load label annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            dict: The dict contains loaded label annotations.
        """
        gt_bboxes_labels = []
        for instance in results.get('instances', []):
            gt_bboxes_labels.append(instance['bbox_label'])
        # TODO: Inconsistent with mmcv, consider how to deal with it later.
        results['gt_bboxes_labels'] = np.array(
            gt_bboxes_labels, dtype=np.int64)

    def _poly2mask(self, mask_ann: Union[list, dict], img_h: int,
                   img_w: int) -> np.ndarray:
        """Private function to convert masks represented with polygon to
        bitmaps.

        Args:
            mask_ann (list | dict): Polygon mask annotation input.
            img_h (int): The height of output mask.
            img_w (int): The width of output mask.

        Returns:
            np.ndarray: The decode bitmap mask of shape (img_h, img_w).
        """

        if isinstance(mask_ann, list):
            # polygon -- a single object might consist of multiple parts
            # we merge all parts into one mask rle code
            rles = maskUtils.frPyObjects(mask_ann, img_h, img_w)
            rle = maskUtils.merge(rles)
        elif isinstance(mask_ann['counts'], list):
            # uncompressed RLE
            rle = maskUtils.frPyObjects(mask_ann, img_h, img_w)
        else:
            # rle
            rle = mask_ann
        mask = maskUtils.decode(rle)
        return mask

    def _process_masks(self, results: dict) -> list:
        """Process gt_masks and filter invalid polygons.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            list: Processed gt_masks.
        """
        gt_masks = []
        gt_ignore_flags = []
        for instance in results.get('instances', []):
            gt_mask = instance['mask']
            # If the annotation of segmentation mask is invalid,
            # ignore the whole instance.
            if isinstance(gt_mask, list):
                gt_mask = [
                    np.array(polygon) for polygon in gt_mask
                    if len(polygon) % 2 == 0 and len(polygon) >= 6
                ]
                if len(gt_mask) == 0:
                    # ignore this instance and set gt_mask to a fake mask
                    instance['ignore_flag'] = 1
                    gt_mask = [np.zeros(6)]
            elif not self.poly2mask:
                # `PolygonMasks` requires a ploygon of format List[np.array],
                # other formats are invalid.
                instance['ignore_flag'] = 1
                gt_mask = [np.zeros(6)]
            elif isinstance(gt_mask, dict) and \
                    not (gt_mask.get('counts') is not None and
                         gt_mask.get('size') is not None and
                         isinstance(gt_mask['counts'], (list, str))):
                # if gt_mask is a dict, it should include `counts` and `size`,
                # so that `BitmapMasks` can uncompressed RLE
                instance['ignore_flag'] = 1
                gt_mask = [np.zeros(6)]
            gt_masks.append(gt_mask)
            # re-process gt_ignore_flags
            gt_ignore_flags.append(instance['ignore_flag'])
        results['gt_ignore_flags'] = np.array(gt_ignore_flags, dtype=bool)
        return gt_masks

    def _load_masks(self, results: dict) -> None:
        """Private function to load mask annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.
        """
        h, w = results['ori_shape']
        gt_masks = self._process_masks(results)
        if self.poly2mask:
            gt_masks = BitmapMasks(
                [self._poly2mask(mask, h, w) for mask in gt_masks], h, w)
        else:
            # fake polygon masks will be ignored in `PackDetInputs`
            gt_masks = PolygonMasks([mask for mask in gt_masks], h, w)
        results['gt_masks'] = gt_masks

    def transform(self, results: dict) -> dict:
        """Function to load multiple types annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            dict: The dict contains loaded bounding box, label and
            semantic segmentation.
        """

        if self.with_bbox:
            self._load_bboxes(results)
        if self.with_label:
            self._load_labels(results)
        if self.with_mask:
            self._load_masks(results)
        if self.with_seg:
            self._load_seg_map(results)
        return results

    def __repr__(self) -> str:
        repr_str = self.__class__.__name__
        repr_str += f'(with_bbox={self.with_bbox}, '
        repr_str += f'with_label={self.with_label}, '
        repr_str += f'with_mask={self.with_mask}, '
        repr_str += f'with_seg={self.with_seg}, '
        repr_str += f'poly2mask={self.poly2mask}, '
        repr_str += f"imdecode_backend='{self.imdecode_backend}', "
        repr_str += f'backend_args={self.backend_args})'
        return repr_str