Skip to content

Annotation

sahi.annotation

Classes

BoundingBox dataclass

BoundingBox represents a rectangular region in 2D space, typically used for object detection annotations.

Attributes:

Name Type Description
box Tuple[float, float, float, float]

The bounding box coordinates in the format (minx, miny, maxx, maxy). - minx (float): Minimum x-coordinate (left). - miny (float): Minimum y-coordinate (top). - maxx (float): Maximum x-coordinate (right). - maxy (float): Maximum y-coordinate (bottom).
shift_amount Tuple[int, int]

The amount to shift the bounding box in the x and y directions. Defaults to (0, 0).

BoundingBox Usage Example

bbox = BoundingBox((10.0, 20.0, 50.0, 80.0))
area = bbox.area
expanded_bbox = bbox.get_expanded_box(ratio=0.2)
shifted_bbox = bbox.get_shifted_box()
coco_format = bbox.to_coco_bbox()
Source code in sahi/annotation.py 
 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
@dataclass(frozen=True)
class BoundingBox:
    """
    BoundingBox represents a rectangular region in 2D space, typically used for object detection annotations.

    Attributes:
        box (Tuple[float, float, float, float]): The bounding box coordinates in the format (minx, miny, maxx, maxy).
            - minx (float): Minimum x-coordinate (left).
            - miny (float): Minimum y-coordinate (top).
            - maxx (float): Maximum x-coordinate (right).
            - maxy (float): Maximum y-coordinate (bottom).
        shift_amount (Tuple[int, int], optional): The amount to shift the bounding box in the x and y directions.
            Defaults to (0, 0).

    !!! example "BoundingBox Usage Example"
        ```python
        bbox = BoundingBox((10.0, 20.0, 50.0, 80.0))
        area = bbox.area
        expanded_bbox = bbox.get_expanded_box(ratio=0.2)
        shifted_bbox = bbox.get_shifted_box()
        coco_format = bbox.to_coco_bbox()
        ```

    """

    box: Union[Tuple[float, float, float, float], List[float]]
    shift_amount: Tuple[int, int] = (0, 0)

    def __post_init__(self):
        if len(self.box) != 4 or any(coord < 0 for coord in self.box):
            raise ValueError("box must be 4 non-negative floats: [minx, miny, maxx, maxy]")
        if len(self.shift_amount) != 2:
            raise ValueError("shift_amount must be 2 integers: [shift_x, shift_y]")

    @property
    def minx(self):
        return self.box[0]

    @property
    def miny(self):
        return self.box[1]

    @property
    def maxx(self):
        return self.box[2]

    @property
    def maxy(self):
        return self.box[3]

    @property
    def shift_x(self):
        return self.shift_amount[0]

    @property
    def shift_y(self):
        return self.shift_amount[1]

    @property
    def area(self):
        return (self.maxx - self.minx) * (self.maxy - self.miny)

    def get_expanded_box(self, ratio: float = 0.1, max_x: int = None, max_y: int = None):
        """
        Returns an expanded bounding box by increasing its size by a given ratio.
        The expansion is applied equally in all directions. Optionally, the expanded box
        can be clipped to maximum x and y boundaries.

        Args:
            ratio (float, optional): The proportion by which to expand the box size.
                Default is 0.1 (10%).
            max_x (int, optional): The maximum allowed x-coordinate for the expanded box.
                If None, no maximum is applied.
            max_y (int, optional): The maximum allowed y-coordinate for the expanded box.
                If None, no maximum is applied.

        Returns:
            BoundingBox: A new BoundingBox instance representing the expanded box.
        """

        w = self.maxx - self.minx
        h = self.maxy - self.miny
        y_mar = int(w * ratio)
        x_mar = int(h * ratio)
        maxx = min(max_x, self.maxx + x_mar) if max_x else self.maxx + x_mar
        minx = max(0, self.minx - x_mar)
        maxy = min(max_y, self.maxy + y_mar) if max_y else self.maxy + y_mar
        miny = max(0, self.miny - y_mar)
        box: list[float] = [minx, miny, maxx, maxy]
        return BoundingBox(box)

    def to_xywh(self):
        """
        Returns [xmin, ymin, width, height]

        Returns:
            List[float]: A list containing the bounding box in the format [xmin, ymin, width, height].
        """

        return [self.minx, self.miny, self.maxx - self.minx, self.maxy - self.miny]

    def to_coco_bbox(self):
        """
        Returns the bounding box in COCO format: [xmin, ymin, width, height]

        Returns:
            List[float]: A list containing the bounding box in COCO format.
        """
        return self.to_xywh()

    def to_xyxy(self):
        """
        Returns: [xmin, ymin, xmax, ymax]

        Returns:
            List[float]: A list containing the bounding box in the format [xmin, ymin, xmax, ymax].
        """
        return [self.minx, self.miny, self.maxx, self.maxy]

    def to_voc_bbox(self):
        """
        Returns the bounding box in VOC format: [xmin, ymin, xmax, ymax]

        Returns:
            List[float]: A list containing the bounding box in VOC format.
        """
        return self.to_xyxy()

    def get_shifted_box(self):
        """
        Returns shifted BoundingBox

        Returns:
            BoundingBox: A new BoundingBox instance representing the shifted box.
        """
        box = [
            self.minx + self.shift_x,
            self.miny + self.shift_y,
            self.maxx + self.shift_x,
            self.maxy + self.shift_y,
        ]
        return BoundingBox(box)

    def __repr__(self):
        return f"BoundingBox: <{(self.minx, self.miny, self.maxx, self.maxy)}, w: {self.maxx - self.minx}, h: {self.maxy - self.miny}>"
Functions
get_expanded_box(ratio=0.1, max_x=None, max_y=None)

Returns an expanded bounding box by increasing its size by a given ratio. The expansion is applied equally in all directions. Optionally, the expanded box can be clipped to maximum x and y boundaries.

Parameters:

Name Type Description Default
ratio float

The proportion by which to expand the box size. Default is 0.1 (10%).

 0.1
max_x int

The maximum allowed x-coordinate for the expanded box. If None, no maximum is applied.

 None
max_y int

The maximum allowed y-coordinate for the expanded box. If None, no maximum is applied.

 None

Returns:

Name Type Description
BoundingBox

A new BoundingBox instance representing the expanded box.
Source code in sahi/annotation.py 
 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
def get_expanded_box(self, ratio: float = 0.1, max_x: int = None, max_y: int = None):
    """
    Returns an expanded bounding box by increasing its size by a given ratio.
    The expansion is applied equally in all directions. Optionally, the expanded box
    can be clipped to maximum x and y boundaries.

    Args:
        ratio (float, optional): The proportion by which to expand the box size.
            Default is 0.1 (10%).
        max_x (int, optional): The maximum allowed x-coordinate for the expanded box.
            If None, no maximum is applied.
        max_y (int, optional): The maximum allowed y-coordinate for the expanded box.
            If None, no maximum is applied.

    Returns:
        BoundingBox: A new BoundingBox instance representing the expanded box.
    """

    w = self.maxx - self.minx
    h = self.maxy - self.miny
    y_mar = int(w * ratio)
    x_mar = int(h * ratio)
    maxx = min(max_x, self.maxx + x_mar) if max_x else self.maxx + x_mar
    minx = max(0, self.minx - x_mar)
    maxy = min(max_y, self.maxy + y_mar) if max_y else self.maxy + y_mar
    miny = max(0, self.miny - y_mar)
    box: list[float] = [minx, miny, maxx, maxy]
    return BoundingBox(box)
get_shifted_box()

Returns shifted BoundingBox

Returns:

Name Type Description
BoundingBox

A new BoundingBox instance representing the shifted box.
Source code in sahi/annotation.py 
150
151
152
153
154
155
156
157
158
159
160
161
162
163
def get_shifted_box(self):
    """
    Returns shifted BoundingBox

    Returns:
        BoundingBox: A new BoundingBox instance representing the shifted box.
    """
    box = [
        self.minx + self.shift_x,
        self.miny + self.shift_y,
        self.maxx + self.shift_x,
        self.maxy + self.shift_y,
    ]
    return BoundingBox(box)
to_coco_bbox()

Returns the bounding box in COCO format: [xmin, ymin, width, height]

Returns:

Type Description

List[float]: A list containing the bounding box in COCO format.
Source code in sahi/annotation.py 
123
124
125
126
127
128
129
130
def to_coco_bbox(self):
    """
    Returns the bounding box in COCO format: [xmin, ymin, width, height]

    Returns:
        List[float]: A list containing the bounding box in COCO format.
    """
    return self.to_xywh()
to_voc_bbox()

Returns the bounding box in VOC format: [xmin, ymin, xmax, ymax]

Returns:

Type Description

List[float]: A list containing the bounding box in VOC format.
Source code in sahi/annotation.py 
141
142
143
144
145
146
147
148
def to_voc_bbox(self):
    """
    Returns the bounding box in VOC format: [xmin, ymin, xmax, ymax]

    Returns:
        List[float]: A list containing the bounding box in VOC format.
    """
    return self.to_xyxy()
to_xywh()

Returns [xmin, ymin, width, height]

Returns:

Type Description

List[float]: A list containing the bounding box in the format [xmin, ymin, width, height].
Source code in sahi/annotation.py 
113
114
115
116
117
118
119
120
121
def to_xywh(self):
    """
    Returns [xmin, ymin, width, height]

    Returns:
        List[float]: A list containing the bounding box in the format [xmin, ymin, width, height].
    """

    return [self.minx, self.miny, self.maxx - self.minx, self.maxy - self.miny]
to_xyxy()

Returns: [xmin, ymin, xmax, ymax]

Returns:

Type Description

List[float]: A list containing the bounding box in the format [xmin, ymin, xmax, ymax].
Source code in sahi/annotation.py 
132
133
134
135
136
137
138
139
def to_xyxy(self):
    """
    Returns: [xmin, ymin, xmax, ymax]

    Returns:
        List[float]: A list containing the bounding box in the format [xmin, ymin, xmax, ymax].
    """
    return [self.minx, self.miny, self.maxx, self.maxy]

Category dataclass

Category of the annotation.

Attributes:

Name Type Description
id int

Unique identifier for the category.
name str

Name of the category.
Source code in sahi/annotation.py 
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
@dataclass(frozen=True)
class Category:
    """
    Category of the annotation.

    Attributes:
        id (int): Unique identifier for the category.
        name (str): Name of the category.

    """

    id: int
    name: str

    def __post_init__(self):
        if not isinstance(self.id, int):
            raise TypeError("id should be integer")
        if not isinstance(self.name, str):
            raise TypeError("name should be string")

    def __repr__(self):
        return f"Category: <id: {self.id}, name: {self.name}>"

Mask

Init Mask from coco segmentation representation.

Parameters:

Name Type Description Default
segmentation

List[List] [ [x1, y1, x2, y2, x3, y3, ...], [x1, y1, x2, y2, x3, y3, ...], ... ]

 required
full_shape
List[int]

List[int] Size of the full image, should be in the form of [height, width]

 required
shift_amount
list

List[int] To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
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
class Mask:
    """
    Init Mask from coco segmentation representation.

    Args:
        segmentation : List[List]
            [
                [x1, y1, x2, y2, x3, y3, ...],
                [x1, y1, x2, y2, x3, y3, ...],
                ...
            ]
        full_shape: List[int]
            Size of the full image, should be in the form of [height, width]
        shift_amount: List[int]
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """

    def __init__(
        self,
        segmentation: List[List[float]],
        full_shape: List[int],
        shift_amount: list = [0, 0],
    ):
        if full_shape is None:
            raise ValueError("full_shape must be provided")  # pyright: ignore[reportUnreachable]

        self.shift_x = shift_amount[0]
        self.shift_y = shift_amount[1]
        self.full_shape_height = full_shape[0]
        self.full_shape_width = full_shape[1]
        self.segmentation = segmentation

    @classmethod
    def from_float_mask(
        cls,
        mask: np.ndarray,
        full_shape: List[int],
        mask_threshold: float = 0.5,
        shift_amount: list = [0, 0],
    ):
        """
        Args:
            mask: np.ndarray of np.float elements
                Mask values between 0 and 1 (should have a shape of height*width)
            mask_threshold: float
                Value to threshold mask pixels between 0 and 1
            shift_amount: List
                To shift the box and mask predictions from sliced image
                to full sized image, should be in the form of [shift_x, shift_y]
            full_shape: List[int]
                Size of the full image after shifting, should be in the form of [height, width]
        """
        bool_mask = mask > mask_threshold
        return cls(
            segmentation=get_coco_segmentation_from_bool_mask(bool_mask),
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @classmethod
    def from_bool_mask(
        cls,
        bool_mask: np.ndarray,
        full_shape: List[int],
        shift_amount: list = [0, 0],
    ):
        """
        Args:
            bool_mask: np.ndarray with bool elements
                2D mask of object, should have a shape of height*width
            full_shape: List[int]
                Size of the full image, should be in the form of [height, width]
            shift_amount: List[int]
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        return cls(
            segmentation=get_coco_segmentation_from_bool_mask(bool_mask),
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @property
    def bool_mask(self) -> np.ndarray:
        return get_bool_mask_from_coco_segmentation(
            self.segmentation, width=self.full_shape[1], height=self.full_shape[0]
        )

    @property
    def shape(self) -> List[int]:
        """
        Returns mask shape as [height, width]
        """
        return [self.bool_mask.shape[0], self.bool_mask.shape[1]]

    @property
    def full_shape(self) -> List[int]:
        """
        Returns full mask shape after shifting as [height, width]
        """
        return [self.full_shape_height, self.full_shape_width]

    @property
    def shift_amount(self):
        """
        Returns the shift amount of the mask slice as [shift_x, shift_y]
        """
        return [self.shift_x, self.shift_y]

    def get_shifted_mask(self) -> "Mask":
        # Confirm full_shape is specified
        if (self.full_shape_height is None) or (self.full_shape_width is None):
            raise ValueError("full_shape is None")
        shifted_segmentation = []
        for s in self.segmentation:
            xs = [min(self.shift_x + s[i], self.full_shape_width) for i in range(0, len(s) - 1, 2)]
            ys = [min(self.shift_y + s[i], self.full_shape_height) for i in range(1, len(s), 2)]
            shifted_segmentation.append([j for i in zip(xs, ys) for j in i])
        return Mask(
            segmentation=shifted_segmentation,
            shift_amount=[0, 0],
            full_shape=self.full_shape,
        )
Attributes
full_shape property

Returns full mask shape after shifting as [height, width]

shape property

Returns mask shape as [height, width]

shift_amount property

Returns the shift amount of the mask slice as [shift_x, shift_y]

Functions
from_bool_mask(bool_mask, full_shape, shift_amount=[0, 0]) classmethod

Parameters:

Name Type Description Default
bool_mask ndarray

np.ndarray with bool elements 2D mask of object, should have a shape of height*width

 required
full_shape List[int]

List[int] Size of the full image, should be in the form of [height, width]

 required
shift_amount list

List[int] To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
@classmethod
def from_bool_mask(
    cls,
    bool_mask: np.ndarray,
    full_shape: List[int],
    shift_amount: list = [0, 0],
):
    """
    Args:
        bool_mask: np.ndarray with bool elements
            2D mask of object, should have a shape of height*width
        full_shape: List[int]
            Size of the full image, should be in the form of [height, width]
        shift_amount: List[int]
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    return cls(
        segmentation=get_coco_segmentation_from_bool_mask(bool_mask),
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
from_float_mask(mask, full_shape, mask_threshold=0.5, shift_amount=[0, 0]) classmethod

Parameters:

Name Type Description Default
mask ndarray

np.ndarray of np.float elements Mask values between 0 and 1 (should have a shape of height*width)

 required
mask_threshold float

float Value to threshold mask pixels between 0 and 1

 0.5
shift_amount list

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
full_shape List[int]

List[int] Size of the full image after shifting, should be in the form of [height, width]

 required
Source code in sahi/annotation.py 
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
@classmethod
def from_float_mask(
    cls,
    mask: np.ndarray,
    full_shape: List[int],
    mask_threshold: float = 0.5,
    shift_amount: list = [0, 0],
):
    """
    Args:
        mask: np.ndarray of np.float elements
            Mask values between 0 and 1 (should have a shape of height*width)
        mask_threshold: float
            Value to threshold mask pixels between 0 and 1
        shift_amount: List
            To shift the box and mask predictions from sliced image
            to full sized image, should be in the form of [shift_x, shift_y]
        full_shape: List[int]
            Size of the full image after shifting, should be in the form of [height, width]
    """
    bool_mask = mask > mask_threshold
    return cls(
        segmentation=get_coco_segmentation_from_bool_mask(bool_mask),
        shift_amount=shift_amount,
        full_shape=full_shape,
    )

ObjectAnnotation

All about an annotation such as Mask, Category, BoundingBox.

Source code in sahi/annotation.py 
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
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
class ObjectAnnotation:
    """
    All about an annotation such as Mask, Category, BoundingBox.
    """

    def __init__(
        self,
        bbox: Optional[List[int]] = None,
        segmentation: Optional[np.ndarray] = None,
        category_id: Optional[int] = None,
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
        full_shape: Optional[List[int]] = None,
    ):
        """
        Args:
            bbox: List
                [minx, miny, maxx, maxy]
            segmentation: List[List]
                [
                    [x1, y1, x2, y2, x3, y3, ...],
                    [x1, y1, x2, y2, x3, y3, ...],
                    ...
                ]
            category_id: int
                ID of the object category
            category_name: str
                Name of the object category
            shift_amount: List
                To shift the box and mask predictions from sliced image
                to full sized image, should be in the form of [shift_x, shift_y]
            full_shape: List
                Size of the full image after shifting, should be in
                the form of [height, width]
        """
        if not isinstance(category_id, int):
            raise ValueError("category_id must be an integer")
        if (bbox is None) and (segmentation is None):
            raise ValueError("you must provide a bbox or segmentation")

        self.mask: Mask | None = None
        if segmentation is not None:
            self.mask = Mask(
                segmentation=segmentation,
                shift_amount=shift_amount,
                full_shape=full_shape,
            )
            bbox_from_segmentation = get_bbox_from_coco_segmentation(segmentation)
            # https://github.com/obss/sahi/issues/235
            if bbox_from_segmentation is not None:
                bbox = bbox_from_segmentation
            else:
                raise ValueError("Invalid segmentation mask.")

        # if bbox is a numpy object, convert it to python List[float]
        if type(bbox).__module__ == "numpy":
            bbox = copy.deepcopy(bbox).tolist()

        # make sure bbox coords lie inside [0, image_size]
        xmin = max(bbox[0], 0)
        ymin = max(bbox[1], 0)
        if full_shape:
            xmax = min(bbox[2], full_shape[1])
            ymax = min(bbox[3], full_shape[0])
        else:
            xmax = bbox[2]
            ymax = bbox[3]
        bbox = [xmin, ymin, xmax, ymax]
        # set bbox
        self.bbox = BoundingBox(bbox, shift_amount)

        category_name = category_name if category_name else str(category_id)
        self.category = Category(
            id=category_id,
            name=category_name,
        )

        self.merged = None

    @classmethod
    def from_bool_mask(
        cls,
        bool_mask,
        category_id: Optional[int] = None,
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
        full_shape: Optional[List[int]] = None,
    ):
        """
        Creates ObjectAnnotation from bool_mask (2D np.ndarray)

        Args:
            bool_mask: np.ndarray with bool elements
                2D mask of object, should have a shape of height*width
            category_id: int
                ID of the object category
            category_name: str
                Name of the object category
            full_shape: List
                Size of the full image, should be in the form of [height, width]
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        segmentation = get_coco_segmentation_from_bool_mask(bool_mask)
        return cls(
            category_id=category_id,
            segmentation=segmentation,
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @classmethod
    def from_coco_segmentation(
        cls,
        segmentation,
        full_shape: List[int],
        category_id: Optional[int] = None,
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
    ):
        """
        Creates ObjectAnnotation from coco segmentation:
        [
            [x1, y1, x2, y2, x3, y3, ...],
            [x1, y1, x2, y2, x3, y3, ...],
            ...
        ]

        Args:
            segmentation: List[List]
                [
                    [x1, y1, x2, y2, x3, y3, ...],
                    [x1, y1, x2, y2, x3, y3, ...],
                    ...
                ]
            category_id: int
                ID of the object category
            category_name: str
                Name of the object category
            full_shape: List
                Size of the full image, should be in the form of [height, width]
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        return cls(
            category_id=category_id,
            segmentation=segmentation,
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @classmethod
    def from_coco_bbox(
        cls,
        bbox: List[int],
        category_id: Optional[int] = None,
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
        full_shape: Optional[List[int]] = None,
    ):
        """
        Creates ObjectAnnotation from coco bbox [minx, miny, width, height]

        Args:
            bbox: List
                [minx, miny, width, height]
            category_id: int
                ID of the object category
            category_name: str
                Name of the object category
            full_shape: List
                Size of the full image, should be in the form of [height, width]
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        xmin = bbox[0]
        ymin = bbox[1]
        xmax = bbox[0] + bbox[2]
        ymax = bbox[1] + bbox[3]
        bbox = [xmin, ymin, xmax, ymax]
        return cls(
            category_id=category_id,
            bbox=bbox,
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @classmethod
    def from_coco_annotation_dict(
        cls,
        annotation_dict: Dict,
        full_shape: List[int],
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
    ):
        """
        Creates ObjectAnnotation object from category name and COCO formatted
        annotation dict (with fields "bbox", "segmentation", "category_id").

        Args:
            annotation_dict: dict
                COCO formatted annotation dict (with fields "bbox", "segmentation", "category_id")
            category_name: str
                Category name of the annotation
            full_shape: List
                Size of the full image, should be in the form of [height, width]
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        if annotation_dict["segmentation"]:
            return cls.from_coco_segmentation(
                segmentation=annotation_dict["segmentation"],
                category_id=annotation_dict["category_id"],
                category_name=category_name,
                shift_amount=shift_amount,
                full_shape=full_shape,
            )
        else:
            return cls.from_coco_bbox(
                bbox=annotation_dict["bbox"],
                category_id=annotation_dict["category_id"],
                category_name=category_name,
                shift_amount=shift_amount,
                full_shape=full_shape,
            )

    @classmethod
    def from_shapely_annotation(
        cls,
        annotation: ShapelyAnnotation,
        full_shape: List[int],
        category_id: Optional[int] = None,
        category_name: Optional[str] = None,
        shift_amount: Optional[List[int]] = [0, 0],
    ):
        """
        Creates ObjectAnnotation from shapely_utils.ShapelyAnnotation

        Args:
            annotation: shapely_utils.ShapelyAnnotation
            category_id: int
                ID of the object category
            category_name: str
                Name of the object category
            full_shape: List
                Size of the full image, should be in the form of [height, width]
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
        """
        return cls(
            category_id=category_id,
            segmentation=annotation.to_coco_segmentation(),
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    @classmethod
    def from_imantics_annotation(
        cls,
        annotation,
        shift_amount: Optional[List[int]] = [0, 0],
        full_shape: Optional[List[int]] = None,
    ):
        """
        Creates ObjectAnnotation from imantics.annotation.Annotation

        Args:
            annotation: imantics.annotation.Annotation
            shift_amount: List
                To shift the box and mask predictions from sliced image to full
                sized image, should be in the form of [shift_x, shift_y]
            full_shape: List
                Size of the full image, should be in the form of [height, width]
        """
        return cls(
            category_id=annotation.category.id,
            bool_mask=annotation.mask.array,
            category_name=annotation.category.name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )

    def to_coco_annotation(self) -> CocoAnnotation:
        """
        Returns sahi.utils.coco.CocoAnnotation representation of ObjectAnnotation.
        """
        if self.mask:
            coco_annotation = CocoAnnotation.from_coco_segmentation(
                segmentation=self.mask.segmentation,
                category_id=self.category.id,
                category_name=self.category.name,
            )
        else:
            coco_annotation = CocoAnnotation.from_coco_bbox(
                bbox=self.bbox.to_xywh(),
                category_id=self.category.id,
                category_name=self.category.name,
            )
        return coco_annotation

    def to_coco_prediction(self) -> CocoPrediction:
        """
        Returns sahi.utils.coco.CocoPrediction representation of ObjectAnnotation.
        """
        if self.mask:
            coco_prediction = CocoPrediction.from_coco_segmentation(
                segmentation=self.mask.segmentation,
                category_id=self.category.id,
                category_name=self.category.name,
                score=1,
            )
        else:
            coco_prediction = CocoPrediction.from_coco_bbox(
                bbox=self.bbox.to_xywh(),
                category_id=self.category.id,
                category_name=self.category.name,
                score=1,
            )
        return coco_prediction

    def to_shapely_annotation(self) -> ShapelyAnnotation:
        """
        Returns sahi.utils.shapely.ShapelyAnnotation representation of ObjectAnnotation.
        """
        if self.mask:
            shapely_annotation = ShapelyAnnotation.from_coco_segmentation(
                segmentation=self.mask.segmentation,
            )
        else:
            shapely_annotation = ShapelyAnnotation.from_coco_bbox(
                bbox=self.bbox.to_xywh(),
            )
        return shapely_annotation

    def to_imantics_annotation(self):
        """
        Returns imantics.annotation.Annotation representation of ObjectAnnotation.
        """
        try:
            import imantics
        except ImportError:
            raise ImportError('Please run "pip install -U imantics" to install imantics first for imantics conversion.')

        imantics_category = imantics.Category(id=self.category.id, name=self.category.name)
        if self.mask is not None:
            imantics_mask = imantics.Mask.create(self.mask.bool_mask)
            imantics_annotation = imantics.annotation.Annotation.from_mask(
                mask=imantics_mask, category=imantics_category
            )
        else:
            imantics_bbox = imantics.BBox.create(self.bbox.to_xyxy())
            imantics_annotation = imantics.annotation.Annotation.from_bbox(
                bbox=imantics_bbox, category=imantics_category
            )
        return imantics_annotation

    def deepcopy(self):
        """
        Returns: deepcopy of current ObjectAnnotation instance
        """
        return copy.deepcopy(self)

    @classmethod
    def get_empty_mask(cls):
        return Mask(bool_mask=None)

    def get_shifted_object_annotation(self):
        if self.mask:
            shifted_mask = self.mask.get_shifted_mask()
            return ObjectAnnotation(
                bbox=self.bbox.get_shifted_box().to_xyxy(),
                category_id=self.category.id,
                segmentation=shifted_mask.segmentation,
                category_name=self.category.name,
                shift_amount=[0, 0],
                full_shape=shifted_mask.full_shape,
            )
        else:
            return ObjectAnnotation(
                bbox=self.bbox.get_shifted_box().to_xyxy(),
                category_id=self.category.id,
                bool_mask=None,
                category_name=self.category.name,
                shift_amount=[0, 0],
                full_shape=None,
            )

    def __repr__(self):
        return f"""ObjectAnnotation<
    bbox: {self.bbox},
    mask: {self.mask},
    category: {self.category}>"""
Functions
__init__(bbox=None, segmentation=None, category_id=None, category_name=None, shift_amount=[0, 0], full_shape=None)

Parameters:

Name Type Description Default
bbox Optional[List[int]]

List [minx, miny, maxx, maxy]

 None
segmentation Optional[ndarray]

List[List] [ [x1, y1, x2, y2, x3, y3, ...], [x1, y1, x2, y2, x3, y3, ...], ... ]

 None
category_id Optional[int]

int ID of the object category

 None
category_name Optional[str]

str Name of the object category

 None
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
full_shape Optional[List[int]]

List Size of the full image after shifting, should be in the form of [height, width]

 None
Source code in sahi/annotation.py 
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
def __init__(
    self,
    bbox: Optional[List[int]] = None,
    segmentation: Optional[np.ndarray] = None,
    category_id: Optional[int] = None,
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
    full_shape: Optional[List[int]] = None,
):
    """
    Args:
        bbox: List
            [minx, miny, maxx, maxy]
        segmentation: List[List]
            [
                [x1, y1, x2, y2, x3, y3, ...],
                [x1, y1, x2, y2, x3, y3, ...],
                ...
            ]
        category_id: int
            ID of the object category
        category_name: str
            Name of the object category
        shift_amount: List
            To shift the box and mask predictions from sliced image
            to full sized image, should be in the form of [shift_x, shift_y]
        full_shape: List
            Size of the full image after shifting, should be in
            the form of [height, width]
    """
    if not isinstance(category_id, int):
        raise ValueError("category_id must be an integer")
    if (bbox is None) and (segmentation is None):
        raise ValueError("you must provide a bbox or segmentation")

    self.mask: Mask | None = None
    if segmentation is not None:
        self.mask = Mask(
            segmentation=segmentation,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )
        bbox_from_segmentation = get_bbox_from_coco_segmentation(segmentation)
        # https://github.com/obss/sahi/issues/235
        if bbox_from_segmentation is not None:
            bbox = bbox_from_segmentation
        else:
            raise ValueError("Invalid segmentation mask.")

    # if bbox is a numpy object, convert it to python List[float]
    if type(bbox).__module__ == "numpy":
        bbox = copy.deepcopy(bbox).tolist()

    # make sure bbox coords lie inside [0, image_size]
    xmin = max(bbox[0], 0)
    ymin = max(bbox[1], 0)
    if full_shape:
        xmax = min(bbox[2], full_shape[1])
        ymax = min(bbox[3], full_shape[0])
    else:
        xmax = bbox[2]
        ymax = bbox[3]
    bbox = [xmin, ymin, xmax, ymax]
    # set bbox
    self.bbox = BoundingBox(bbox, shift_amount)

    category_name = category_name if category_name else str(category_id)
    self.category = Category(
        id=category_id,
        name=category_name,
    )

    self.merged = None
deepcopy()

Returns: deepcopy of current ObjectAnnotation instance

Source code in sahi/annotation.py 
684
685
686
687
688
def deepcopy(self):
    """
    Returns: deepcopy of current ObjectAnnotation instance
    """
    return copy.deepcopy(self)
from_bool_mask(bool_mask, category_id=None, category_name=None, shift_amount=[0, 0], full_shape=None) classmethod

Creates ObjectAnnotation from bool_mask (2D np.ndarray)

Parameters:

Name Type Description Default
bool_mask

np.ndarray with bool elements 2D mask of object, should have a shape of height*width

 required
category_id Optional[int]

int ID of the object category

 None
category_name Optional[str]

str Name of the object category

 None
full_shape Optional[List[int]]

List Size of the full image, should be in the form of [height, width]

 None
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
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
@classmethod
def from_bool_mask(
    cls,
    bool_mask,
    category_id: Optional[int] = None,
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
    full_shape: Optional[List[int]] = None,
):
    """
    Creates ObjectAnnotation from bool_mask (2D np.ndarray)

    Args:
        bool_mask: np.ndarray with bool elements
            2D mask of object, should have a shape of height*width
        category_id: int
            ID of the object category
        category_name: str
            Name of the object category
        full_shape: List
            Size of the full image, should be in the form of [height, width]
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    segmentation = get_coco_segmentation_from_bool_mask(bool_mask)
    return cls(
        category_id=category_id,
        segmentation=segmentation,
        category_name=category_name,
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
from_coco_annotation_dict(annotation_dict, full_shape, category_name=None, shift_amount=[0, 0]) classmethod

Creates ObjectAnnotation object from category name and COCO formatted annotation dict (with fields "bbox", "segmentation", "category_id").

Parameters:

Name Type Description Default
annotation_dict Dict

dict COCO formatted annotation dict (with fields "bbox", "segmentation", "category_id")

 required
category_name Optional[str]

str Category name of the annotation

 None
full_shape List[int]

List Size of the full image, should be in the form of [height, width]

 required
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
@classmethod
def from_coco_annotation_dict(
    cls,
    annotation_dict: Dict,
    full_shape: List[int],
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
):
    """
    Creates ObjectAnnotation object from category name and COCO formatted
    annotation dict (with fields "bbox", "segmentation", "category_id").

    Args:
        annotation_dict: dict
            COCO formatted annotation dict (with fields "bbox", "segmentation", "category_id")
        category_name: str
            Category name of the annotation
        full_shape: List
            Size of the full image, should be in the form of [height, width]
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    if annotation_dict["segmentation"]:
        return cls.from_coco_segmentation(
            segmentation=annotation_dict["segmentation"],
            category_id=annotation_dict["category_id"],
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )
    else:
        return cls.from_coco_bbox(
            bbox=annotation_dict["bbox"],
            category_id=annotation_dict["category_id"],
            category_name=category_name,
            shift_amount=shift_amount,
            full_shape=full_shape,
        )
from_coco_bbox(bbox, category_id=None, category_name=None, shift_amount=[0, 0], full_shape=None) classmethod

Creates ObjectAnnotation from coco bbox [minx, miny, width, height]

Parameters:

Name Type Description Default
bbox List[int]

List [minx, miny, width, height]

 required
category_id Optional[int]

int ID of the object category

 None
category_name Optional[str]

str Name of the object category

 None
full_shape Optional[List[int]]

List Size of the full image, should be in the form of [height, width]

 None
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
@classmethod
def from_coco_bbox(
    cls,
    bbox: List[int],
    category_id: Optional[int] = None,
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
    full_shape: Optional[List[int]] = None,
):
    """
    Creates ObjectAnnotation from coco bbox [minx, miny, width, height]

    Args:
        bbox: List
            [minx, miny, width, height]
        category_id: int
            ID of the object category
        category_name: str
            Name of the object category
        full_shape: List
            Size of the full image, should be in the form of [height, width]
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    xmin = bbox[0]
    ymin = bbox[1]
    xmax = bbox[0] + bbox[2]
    ymax = bbox[1] + bbox[3]
    bbox = [xmin, ymin, xmax, ymax]
    return cls(
        category_id=category_id,
        bbox=bbox,
        category_name=category_name,
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
from_coco_segmentation(segmentation, full_shape, category_id=None, category_name=None, shift_amount=[0, 0]) classmethod

Creates ObjectAnnotation from coco segmentation: [ [x1, y1, x2, y2, x3, y3, ...], [x1, y1, x2, y2, x3, y3, ...], ... ]

Parameters:

Name Type Description Default
segmentation

List[List] [ [x1, y1, x2, y2, x3, y3, ...], [x1, y1, x2, y2, x3, y3, ...], ... ]

 required
category_id Optional[int]

int ID of the object category

 None
category_name Optional[str]

str Name of the object category

 None
full_shape List[int]

List Size of the full image, should be in the form of [height, width]

 required
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
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
@classmethod
def from_coco_segmentation(
    cls,
    segmentation,
    full_shape: List[int],
    category_id: Optional[int] = None,
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
):
    """
    Creates ObjectAnnotation from coco segmentation:
    [
        [x1, y1, x2, y2, x3, y3, ...],
        [x1, y1, x2, y2, x3, y3, ...],
        ...
    ]

    Args:
        segmentation: List[List]
            [
                [x1, y1, x2, y2, x3, y3, ...],
                [x1, y1, x2, y2, x3, y3, ...],
                ...
            ]
        category_id: int
            ID of the object category
        category_name: str
            Name of the object category
        full_shape: List
            Size of the full image, should be in the form of [height, width]
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    return cls(
        category_id=category_id,
        segmentation=segmentation,
        category_name=category_name,
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
from_imantics_annotation(annotation, shift_amount=[0, 0], full_shape=None) classmethod

Creates ObjectAnnotation from imantics.annotation.Annotation

Parameters:

Name Type Description Default
annotation

imantics.annotation.Annotation

 required
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
full_shape Optional[List[int]]

List Size of the full image, should be in the form of [height, width]

 None
Source code in sahi/annotation.py 
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
@classmethod
def from_imantics_annotation(
    cls,
    annotation,
    shift_amount: Optional[List[int]] = [0, 0],
    full_shape: Optional[List[int]] = None,
):
    """
    Creates ObjectAnnotation from imantics.annotation.Annotation

    Args:
        annotation: imantics.annotation.Annotation
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
        full_shape: List
            Size of the full image, should be in the form of [height, width]
    """
    return cls(
        category_id=annotation.category.id,
        bool_mask=annotation.mask.array,
        category_name=annotation.category.name,
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
from_shapely_annotation(annotation, full_shape, category_id=None, category_name=None, shift_amount=[0, 0]) classmethod

Creates ObjectAnnotation from shapely_utils.ShapelyAnnotation

Parameters:

Name Type Description Default
annotation ShapelyAnnotation

shapely_utils.ShapelyAnnotation

 required
category_id Optional[int]

int ID of the object category

 None
category_name Optional[str]

str Name of the object category

 None
full_shape List[int]

List Size of the full image, should be in the form of [height, width]

 required
shift_amount Optional[List[int]]

List To shift the box and mask predictions from sliced image to full sized image, should be in the form of [shift_x, shift_y]

 [0, 0]
Source code in sahi/annotation.py 
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
@classmethod
def from_shapely_annotation(
    cls,
    annotation: ShapelyAnnotation,
    full_shape: List[int],
    category_id: Optional[int] = None,
    category_name: Optional[str] = None,
    shift_amount: Optional[List[int]] = [0, 0],
):
    """
    Creates ObjectAnnotation from shapely_utils.ShapelyAnnotation

    Args:
        annotation: shapely_utils.ShapelyAnnotation
        category_id: int
            ID of the object category
        category_name: str
            Name of the object category
        full_shape: List
            Size of the full image, should be in the form of [height, width]
        shift_amount: List
            To shift the box and mask predictions from sliced image to full
            sized image, should be in the form of [shift_x, shift_y]
    """
    return cls(
        category_id=category_id,
        segmentation=annotation.to_coco_segmentation(),
        category_name=category_name,
        shift_amount=shift_amount,
        full_shape=full_shape,
    )
to_coco_annotation()

Returns sahi.utils.coco.CocoAnnotation representation of ObjectAnnotation.

Source code in sahi/annotation.py 
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
def to_coco_annotation(self) -> CocoAnnotation:
    """
    Returns sahi.utils.coco.CocoAnnotation representation of ObjectAnnotation.
    """
    if self.mask:
        coco_annotation = CocoAnnotation.from_coco_segmentation(
            segmentation=self.mask.segmentation,
            category_id=self.category.id,
            category_name=self.category.name,
        )
    else:
        coco_annotation = CocoAnnotation.from_coco_bbox(
            bbox=self.bbox.to_xywh(),
            category_id=self.category.id,
            category_name=self.category.name,
        )
    return coco_annotation
to_coco_prediction()

Returns sahi.utils.coco.CocoPrediction representation of ObjectAnnotation.

Source code in sahi/annotation.py 
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
def to_coco_prediction(self) -> CocoPrediction:
    """
    Returns sahi.utils.coco.CocoPrediction representation of ObjectAnnotation.
    """
    if self.mask:
        coco_prediction = CocoPrediction.from_coco_segmentation(
            segmentation=self.mask.segmentation,
            category_id=self.category.id,
            category_name=self.category.name,
            score=1,
        )
    else:
        coco_prediction = CocoPrediction.from_coco_bbox(
            bbox=self.bbox.to_xywh(),
            category_id=self.category.id,
            category_name=self.category.name,
            score=1,
        )
    return coco_prediction
to_imantics_annotation()

Returns imantics.annotation.Annotation representation of ObjectAnnotation.

Source code in sahi/annotation.py 
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
def to_imantics_annotation(self):
    """
    Returns imantics.annotation.Annotation representation of ObjectAnnotation.
    """
    try:
        import imantics
    except ImportError:
        raise ImportError('Please run "pip install -U imantics" to install imantics first for imantics conversion.')

    imantics_category = imantics.Category(id=self.category.id, name=self.category.name)
    if self.mask is not None:
        imantics_mask = imantics.Mask.create(self.mask.bool_mask)
        imantics_annotation = imantics.annotation.Annotation.from_mask(
            mask=imantics_mask, category=imantics_category
        )
    else:
        imantics_bbox = imantics.BBox.create(self.bbox.to_xyxy())
        imantics_annotation = imantics.annotation.Annotation.from_bbox(
            bbox=imantics_bbox, category=imantics_category
        )
    return imantics_annotation
to_shapely_annotation()

Returns sahi.utils.shapely.ShapelyAnnotation representation of ObjectAnnotation.

Source code in sahi/annotation.py 
648
649
650
651
652
653
654
655
656
657
658
659
660
def to_shapely_annotation(self) -> ShapelyAnnotation:
    """
    Returns sahi.utils.shapely.ShapelyAnnotation representation of ObjectAnnotation.
    """
    if self.mask:
        shapely_annotation = ShapelyAnnotation.from_coco_segmentation(
            segmentation=self.mask.segmentation,
        )
    else:
        shapely_annotation = ShapelyAnnotation.from_coco_bbox(
            bbox=self.bbox.to_xywh(),
        )
    return shapely_annotation

Functions