Skip to content

Core

Detections

Data class containing information about the detections in a video frame. Attributes: xyxy (np.ndarray): An array of shape (n, 4) containing the bounding boxes coordinates in format [x1, y1, x2, y2] mask: (Optional[np.ndarray]): An array of shape (n, H, W) containing the segmentation masks. confidence (Optional[np.ndarray]): An array of shape (n,) containing the confidence scores of the detections. class_id (Optional[np.ndarray]): An array of shape (n,) containing the class ids of the detections. tracker_id (Optional[np.ndarray]): An array of shape (n,) containing the tracker ids of the detections.

Source code in supervision/detection/core.py
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
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
@dataclass
class Detections:
    """
    Data class containing information about the detections in a video frame.
    Attributes:
        xyxy (np.ndarray): An array of shape `(n, 4)` containing the bounding boxes coordinates in format `[x1, y1, x2, y2]`
        mask: (Optional[np.ndarray]): An array of shape `(n, H, W)` containing the segmentation masks.
        confidence (Optional[np.ndarray]): An array of shape `(n,)` containing the confidence scores of the detections.
        class_id (Optional[np.ndarray]): An array of shape `(n,)` containing the class ids of the detections.
        tracker_id (Optional[np.ndarray]): An array of shape `(n,)` containing the tracker ids of the detections.
    """

    xyxy: np.ndarray
    mask: np.Optional[np.ndarray] = None
    confidence: Optional[np.ndarray] = None
    class_id: Optional[np.ndarray] = None
    tracker_id: Optional[np.ndarray] = None

    def __post_init__(self):
        n = len(self.xyxy)
        _validate_xyxy(xyxy=self.xyxy, n=n)
        _validate_mask(mask=self.mask, n=n)
        _validate_class_id(class_id=self.class_id, n=n)
        _validate_confidence(confidence=self.confidence, n=n)
        _validate_tracker_id(tracker_id=self.tracker_id, n=n)

    def __len__(self):
        """
        Returns the number of detections in the Detections object.
        """
        return len(self.xyxy)

    def __iter__(
        self,
    ) -> Iterator[
        Tuple[
            np.ndarray,
            Optional[np.ndarray],
            Optional[float],
            Optional[int],
            Optional[int],
        ]
    ]:
        """
        Iterates over the Detections object and yield a tuple of `(xyxy, mask, confidence, class_id, tracker_id)` for each detection.
        """
        for i in range(len(self.xyxy)):
            yield (
                self.xyxy[i],
                self.mask[i] if self.mask is not None else None,
                self.confidence[i] if self.confidence is not None else None,
                self.class_id[i] if self.class_id is not None else None,
                self.tracker_id[i] if self.tracker_id is not None else None,
            )

    def __eq__(self, other: Detections):
        return all(
            [
                np.array_equal(self.xyxy, other.xyxy),
                any(
                    [
                        self.mask is None and other.mask is None,
                        np.array_equal(self.mask, other.mask),
                    ]
                ),
                any(
                    [
                        self.class_id is None and other.class_id is None,
                        np.array_equal(self.class_id, other.class_id),
                    ]
                ),
                any(
                    [
                        self.confidence is None and other.confidence is None,
                        np.array_equal(self.confidence, other.confidence),
                    ]
                ),
                any(
                    [
                        self.tracker_id is None and other.tracker_id is None,
                        np.array_equal(self.tracker_id, other.tracker_id),
                    ]
                ),
            ]
        )

    @classmethod
    def from_yolov5(cls, yolov5_results) -> Detections:
        """
        Creates a Detections instance from a [YOLOv5](https://github.com/ultralytics/yolov5) inference result.

        Args:
            yolov5_results (yolov5.models.common.Detections): The output Detections instance from YOLOv5

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import cv2
            >>> import torch
            >>> import supervision as sv

            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
            >>> model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
            >>> result = model(image)
            >>> detections = sv.Detections.from_yolov5(result)
            ```
        """
        yolov5_detections_predictions = yolov5_results.pred[0].cpu().cpu().numpy()
        return cls(
            xyxy=yolov5_detections_predictions[:, :4],
            confidence=yolov5_detections_predictions[:, 4],
            class_id=yolov5_detections_predictions[:, 5].astype(int),
        )

    @classmethod
    @deprecated(
        "This method is deprecated and removed in 0.15.0 release. Use sv.Detections.from_ultralytics() instead."
    )
    def from_yolov8(cls, yolov8_results) -> Detections:
        """
        Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.

        Args:
            yolov8_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import cv2
            >>> from ultralytics import YOLO
            >>> import supervision as sv

            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
            >>> model = YOLO('yolov8s.pt')
            >>> result = model(image)[0]
            >>> detections = sv.Detections.from_yolov8(result)
            ```
        """
        return cls(
            xyxy=yolov8_results.boxes.xyxy.cpu().numpy(),
            confidence=yolov8_results.boxes.conf.cpu().numpy(),
            class_id=yolov8_results.boxes.cls.cpu().numpy().astype(int),
            mask=extract_ultralytics_masks(yolov8_results),
        )

    @classmethod
    def from_ultralytics(cls, ultralytics_results) -> Detections:
        """
        Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.

        Args:
            ultralytics_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import cv2
            >>> from ultralytics import YOLO, FastSAM, SAM, RTDETR
            >>> import supervision as sv

            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
            >>> model = YOLO('yolov8s.pt')
            >>> model = SAM('sam_b.pt')
            >>> model = SAM('mobile_sam.pt')
            >>> model = FastSAM('FastSAM-s.pt')
            >>> model = RTDETR('rtdetr-l.pt')
            >>> # model inferences
            >>> result = model(image)[0]
            >>> # if tracker is enabled
            >>> result = model.track(image)[0]
            >>> detections = sv.Detections.from_ultralytics(result)
            ```
        """
        return cls(
            xyxy=ultralytics_results.boxes.xyxy.cpu().numpy(),
            confidence=ultralytics_results.boxes.conf.cpu().numpy(),
            class_id=ultralytics_results.boxes.cls.cpu().numpy().astype(int),
            mask=extract_ultralytics_masks(ultralytics_results),
            tracker_id=ultralytics_results.boxes.id.int().cpu().numpy()
            if ultralytics_results.boxes.id is not None
            else None,
        )

    @classmethod
    def from_yolo_nas(cls, yolo_nas_results) -> Detections:
        """
        Creates a Detections instance from a [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) inference result.

        Args:
            yolo_nas_results (super_gradients.training.models.prediction_results.ImageDetectionPrediction): The output Results instance from YOLO-NAS

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import cv2
            >>> from super_gradients.training import models
            >>> import supervision as sv

            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
            >>> model = models.get('yolo_nas_l', pretrained_weights="coco")
            >>> result = list(model.predict(image, conf=0.35))[0]
            >>> detections = sv.Detections.from_yolo_nas(result)
            ```
        """
        return cls(
            xyxy=yolo_nas_results.prediction.bboxes_xyxy,
            confidence=yolo_nas_results.prediction.confidence,
            class_id=yolo_nas_results.prediction.labels.astype(int),
        )

    @classmethod
    def from_mmdetection(cls, mmdet_results) -> Detections:
        """
        Creates a Detections instance from a [mmdetection](https://github.com/open-mmlab/mmdetection) inference result.
        Also supported for [mmyolo](https://github.com/open-mmlab/mmyolo)

        Args:
            mmdet_results (mmdet.structures.DetDataSample): The output Results instance from MMDetection

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import cv2
            >>> import supervision as sv
            >>> from mmdet.apis import DetInferencer

            >>> inferencer = DetInferencer(model_name, checkpoint, device)
            >>> mmdet_result = inferencer(SOURCE_IMAGE_PATH, out_dir='./output', return_datasample=True)["predictions"][0]
            >>> detections = sv.Detections.from_mmdet(mmdet_result)
            ```
        """
        return cls(
            xyxy=mmdet_results.pred_instances.bboxes.cpu().numpy(),
            confidence=mmdet_results.pred_instances.scores.cpu().numpy(),
            class_id=mmdet_results.pred_instances.labels.cpu().numpy().astype(int),
        )

    @classmethod
    def from_transformers(cls, transformers_results: dict) -> Detections:
        """
        Creates a Detections instance from object detection [transformer](https://github.com/huggingface/transformers) inference result.

        Returns:
            Detections: A new Detections object.
        """
        return cls(
            xyxy=transformers_results["boxes"].cpu().numpy(),
            confidence=transformers_results["scores"].cpu().numpy(),
            class_id=transformers_results["labels"].cpu().numpy().astype(int),
        )

    @classmethod
    def from_detectron2(cls, detectron2_results) -> Detections:
        """
        Create a Detections object from the [Detectron2](https://github.com/facebookresearch/detectron2) inference result.

        Args:
            detectron2_results: The output of a Detectron2 model containing instances with prediction data.

        Returns:
            (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

        Example:
            ```python
            >>> import cv2
            >>> from detectron2.engine import DefaultPredictor
            >>> from detectron2.config import get_cfg
            >>> import supervision as sv

            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
            >>> cfg = get_cfg()
            >>> cfg.merge_from_file("path/to/config.yaml")
            >>> cfg.MODEL.WEIGHTS = "path/to/model_weights.pth"
            >>> predictor = DefaultPredictor(cfg)
            >>> result = predictor(image)

            >>> detections = sv.Detections.from_detectron2(result)
            ```
        """
        return cls(
            xyxy=detectron2_results["instances"].pred_boxes.tensor.cpu().numpy(),
            confidence=detectron2_results["instances"].scores.cpu().numpy(),
            class_id=detectron2_results["instances"]
            .pred_classes.cpu()
            .numpy()
            .astype(int),
        )

    @classmethod
    def from_roboflow(cls, roboflow_result: dict, class_list: List[str]) -> Detections:
        """
        Create a Detections object from the [Roboflow](https://roboflow.com/) API inference result.

        Args:
            roboflow_result (dict): The result from the Roboflow API containing predictions.
            class_list (List[str]): A list of class names corresponding to the class IDs in the API result.

        Returns:
            (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

        Example:
            ```python
            >>> import supervision as sv

            >>> roboflow_result = {
            ...     "predictions": [
            ...         {
            ...             "x": 0.5,
            ...             "y": 0.5,
            ...             "width": 0.2,
            ...             "height": 0.3,
            ...             "class": "person",
            ...             "confidence": 0.9
            ...         },
            ...         # ... more predictions ...
            ...     ]
            ... }
            >>> class_list = ["person", "car", "dog"]

            >>> detections = sv.Detections.from_roboflow(roboflow_result, class_list)
            ```
        """
        xyxy, confidence, class_id, masks = process_roboflow_result(
            roboflow_result=roboflow_result, class_list=class_list
        )
        return Detections(
            xyxy=xyxy,
            confidence=confidence,
            class_id=class_id,
            mask=masks,
        )

    @classmethod
    def from_sam(cls, sam_result: List[dict]) -> Detections:
        """
        Creates a Detections instance from [Segment Anything Model](https://github.com/facebookresearch/segment-anything) inference result.

        Args:
            sam_result (List[dict]): The output Results instance from SAM

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import supervision as sv
            >>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator

            >>> sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
            >>> mask_generator = SamAutomaticMaskGenerator(sam)
            >>> sam_result = mask_generator.generate(IMAGE)
            >>> detections = sv.Detections.from_sam(sam_result=sam_result)
            ```
        """
        sorted_generated_masks = sorted(
            sam_result, key=lambda x: x["area"], reverse=True
        )

        xywh = np.array([mask["bbox"] for mask in sorted_generated_masks])
        mask = np.array([mask["segmentation"] for mask in sorted_generated_masks])

        return Detections(xyxy=xywh_to_xyxy(boxes_xywh=xywh), mask=mask)

    @classmethod
    def from_paddledet(cls, paddledet_result) -> Detections:
        """
        Creates a Detections instance from [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) inference result.

        Args:
            paddledet_result (List[dict]): The output Results instance from SAM

        Returns:
            Detections: A new Detections object.

        Example:
            ```python
            >>> import supervision as sv
            >>> import paddle
            >>> from ppdet.engine import Trainer
            >>> from ppdet.core.workspace import load_config

            >>> weights = (...)
            >>> config = (...)

            >>> cfg = load_config(config)
            >>> trainer = Trainer(cfg, mode='test')
            >>> trainer.load_weights(weights)

            >>> paddledet_result = trainer.predict([images])[0]

            >>> detections = sv.Detections.from_paddledet(paddledet_result=paddledet_result)
            ```
        """
        return cls(
            xyxy=paddledet_result["bbox"][:, 2:6],
            confidence=paddledet_result["bbox"][:, 1],
            class_id=paddledet_result["bbox"][:, 0].astype(int),
        )

    @classmethod
    def empty(cls) -> Detections:
        """
        Create an empty Detections object with no bounding boxes, confidences, or class IDs.

        Returns:
            (Detections): An empty Detections object.

        Example:
            ```python
            >>> from supervision import Detections

            >>> empty_detections = Detections.empty()
            ```
        """
        return cls(
            xyxy=np.empty((0, 4), dtype=np.float32),
            confidence=np.array([], dtype=np.float32),
            class_id=np.array([], dtype=int),
        )

    @classmethod
    def merge(cls, detections_list: List[Detections]) -> Detections:
        """
        Merge a list of Detections objects into a single Detections object.

        This method takes a list of Detections objects and combines their respective fields (`xyxy`, `mask`,
        `confidence`, `class_id`, and `tracker_id`) into a single Detections object. If all elements in a field are not
        `None`, the corresponding field will be stacked. Otherwise, the field will be set to `None`.

        Args:
            detections_list (List[Detections]): A list of Detections objects to merge.

        Returns:
            (Detections): A single Detections object containing the merged data from the input list.

        Example:
            ```python
            >>> from supervision import Detections

            >>> detections_1 = Detections(...)
            >>> detections_2 = Detections(...)

            >>> merged_detections = Detections.merge([detections_1, detections_2])
            ```
        """
        if len(detections_list) == 0:
            return Detections.empty()

        detections_tuples_list = [astuple(detection) for detection in detections_list]
        xyxy, mask, confidence, class_id, tracker_id = [
            list(field) for field in zip(*detections_tuples_list)
        ]

        all_not_none = lambda l: all(x is not None for x in l)

        xyxy = np.vstack(xyxy)
        mask = np.vstack(mask) if all_not_none(mask) else None
        confidence = np.hstack(confidence) if all_not_none(confidence) else None
        class_id = np.hstack(class_id) if all_not_none(class_id) else None
        tracker_id = np.hstack(tracker_id) if all_not_none(tracker_id) else None

        return cls(
            xyxy=xyxy,
            mask=mask,
            confidence=confidence,
            class_id=class_id,
            tracker_id=tracker_id,
        )

    def get_anchor_coordinates(self, anchor: Position) -> np.ndarray:
        """
        Returns the bounding box coordinates for a specific anchor.

        Args:
            anchor (Position): Position of bounding box anchor for which to return the coordinates.

        Returns:
            np.ndarray: An array of shape `(n, 2)` containing the bounding box anchor coordinates in format `[x, y]`.
        """
        if anchor == Position.CENTER:
            return np.array(
                [
                    (self.xyxy[:, 0] + self.xyxy[:, 2]) / 2,
                    (self.xyxy[:, 1] + self.xyxy[:, 3]) / 2,
                ]
            ).transpose()
        elif anchor == Position.BOTTOM_CENTER:
            return np.array(
                [(self.xyxy[:, 0] + self.xyxy[:, 2]) / 2, self.xyxy[:, 3]]
            ).transpose()

        raise ValueError(f"{anchor} is not supported.")

    def __getitem__(
        self, index: Union[int, slice, List[int], np.ndarray]
    ) -> Detections:
        """
        Get a subset of the Detections object.

        Args:
            index (Union[int, slice, List[int], np.ndarray]): The index or indices of the subset of the Detections

        Returns:
            (Detections): A subset of the Detections object.

        Example:
            ```python
            >>> import supervision as sv

            >>> detections = sv.Detections(...)

            >>> first_detection = detections[0]

            >>> first_10_detections = detections[0:10]

            >>> some_detections = detections[[0, 2, 4]]

            >>> class_0_detections = detections[detections.class_id == 0]

            >>> high_confidence_detections = detections[detections.confidence > 0.5]
            ```
        """
        if isinstance(index, int):
            index = [index]
        return Detections(
            xyxy=self.xyxy[index],
            mask=self.mask[index] if self.mask is not None else None,
            confidence=self.confidence[index] if self.confidence is not None else None,
            class_id=self.class_id[index] if self.class_id is not None else None,
            tracker_id=self.tracker_id[index] if self.tracker_id is not None else None,
        )

    @property
    def area(self) -> np.ndarray:
        """
        Calculate the area of each detection in the set of object detections. If masks field is defined property
        returns are of each mask. If only box is given property return area of each box.

        Returns:
          np.ndarray: An array of floats containing the area of each detection in the format of `(area_1, area_2, ..., area_n)`, where n is the number of detections.
        """
        if self.mask is not None:
            return np.array([np.sum(mask) for mask in self.mask])
        else:
            return self.box_area

    @property
    def box_area(self) -> np.ndarray:
        """
        Calculate the area of each bounding box in the set of object detections.

        Returns:
            np.ndarray: An array of floats containing the area of each bounding box in the format of `(area_1, area_2, ..., area_n)`, where n is the number of detections.
        """
        return (self.xyxy[:, 3] - self.xyxy[:, 1]) * (self.xyxy[:, 2] - self.xyxy[:, 0])

    def with_nms(
        self, threshold: float = 0.5, class_agnostic: bool = False
    ) -> Detections:
        """
        Perform non-maximum suppression on the current set of object detections.

        Args:
            threshold (float, optional): The intersection-over-union threshold to use for non-maximum suppression. Defaults to 0.5.
            class_agnostic (bool, optional): Whether to perform class-agnostic non-maximum suppression. If True, the class_id of each detection will be ignored. Defaults to False.

        Returns:
            Detections: A new Detections object containing the subset of detections after non-maximum suppression.

        Raises:
            AssertionError: If `confidence` is None and class_agnostic is False. If `class_id` is None and class_agnostic is False.
        """
        if len(self) == 0:
            return self

        assert (
            self.confidence is not None
        ), f"Detections confidence must be given for NMS to be executed."

        if class_agnostic:
            predictions = np.hstack((self.xyxy, self.confidence.reshape(-1, 1)))
            indices = non_max_suppression(
                predictions=predictions, iou_threshold=threshold
            )
            return self[indices]

        assert self.class_id is not None, (
            f"Detections class_id must be given for NMS to be executed. If you intended to perform class agnostic "
            f"NMS set class_agnostic=True."
        )

        predictions = np.hstack(
            (self.xyxy, self.confidence.reshape(-1, 1), self.class_id.reshape(-1, 1))
        )
        indices = non_max_suppression(predictions=predictions, iou_threshold=threshold)
        return self[indices]

area: np.ndarray property

Calculate the area of each detection in the set of object detections. If masks field is defined property returns are of each mask. If only box is given property return area of each box.

Returns:

Type Description
ndarray

np.ndarray: An array of floats containing the area of each detection in the format of (area_1, area_2, ..., area_n), where n is the number of detections.

box_area: np.ndarray property

Calculate the area of each bounding box in the set of object detections.

Returns:

Type Description
ndarray

np.ndarray: An array of floats containing the area of each bounding box in the format of (area_1, area_2, ..., area_n), where n is the number of detections.

__getitem__(index)

Get a subset of the Detections object.

Parameters:

Name Type Description Default
index Union[int, slice, List[int], ndarray]

The index or indices of the subset of the Detections

required

Returns:

Type Description
Detections

A subset of the Detections object.

Example
>>> import supervision as sv

>>> detections = sv.Detections(...)

>>> first_detection = detections[0]

>>> first_10_detections = detections[0:10]

>>> some_detections = detections[[0, 2, 4]]

>>> class_0_detections = detections[detections.class_id == 0]

>>> high_confidence_detections = detections[detections.confidence > 0.5]
Source code in supervision/detection/core.py
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
def __getitem__(
    self, index: Union[int, slice, List[int], np.ndarray]
) -> Detections:
    """
    Get a subset of the Detections object.

    Args:
        index (Union[int, slice, List[int], np.ndarray]): The index or indices of the subset of the Detections

    Returns:
        (Detections): A subset of the Detections object.

    Example:
        ```python
        >>> import supervision as sv

        >>> detections = sv.Detections(...)

        >>> first_detection = detections[0]

        >>> first_10_detections = detections[0:10]

        >>> some_detections = detections[[0, 2, 4]]

        >>> class_0_detections = detections[detections.class_id == 0]

        >>> high_confidence_detections = detections[detections.confidence > 0.5]
        ```
    """
    if isinstance(index, int):
        index = [index]
    return Detections(
        xyxy=self.xyxy[index],
        mask=self.mask[index] if self.mask is not None else None,
        confidence=self.confidence[index] if self.confidence is not None else None,
        class_id=self.class_id[index] if self.class_id is not None else None,
        tracker_id=self.tracker_id[index] if self.tracker_id is not None else None,
    )

__iter__()

Iterates over the Detections object and yield a tuple of (xyxy, mask, confidence, class_id, tracker_id) for each detection.

Source code in supervision/detection/core.py
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
def __iter__(
    self,
) -> Iterator[
    Tuple[
        np.ndarray,
        Optional[np.ndarray],
        Optional[float],
        Optional[int],
        Optional[int],
    ]
]:
    """
    Iterates over the Detections object and yield a tuple of `(xyxy, mask, confidence, class_id, tracker_id)` for each detection.
    """
    for i in range(len(self.xyxy)):
        yield (
            self.xyxy[i],
            self.mask[i] if self.mask is not None else None,
            self.confidence[i] if self.confidence is not None else None,
            self.class_id[i] if self.class_id is not None else None,
            self.tracker_id[i] if self.tracker_id is not None else None,
        )

__len__()

Returns the number of detections in the Detections object.

Source code in supervision/detection/core.py
83
84
85
86
87
def __len__(self):
    """
    Returns the number of detections in the Detections object.
    """
    return len(self.xyxy)

empty() classmethod

Create an empty Detections object with no bounding boxes, confidences, or class IDs.

Returns:

Type Description
Detections

An empty Detections object.

Example
>>> from supervision import Detections

>>> empty_detections = Detections.empty()
Source code in supervision/detection/core.py
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
@classmethod
def empty(cls) -> Detections:
    """
    Create an empty Detections object with no bounding boxes, confidences, or class IDs.

    Returns:
        (Detections): An empty Detections object.

    Example:
        ```python
        >>> from supervision import Detections

        >>> empty_detections = Detections.empty()
        ```
    """
    return cls(
        xyxy=np.empty((0, 4), dtype=np.float32),
        confidence=np.array([], dtype=np.float32),
        class_id=np.array([], dtype=int),
    )

from_detectron2(detectron2_results) classmethod

Create a Detections object from the Detectron2 inference result.

Parameters:

Name Type Description Default
detectron2_results

The output of a Detectron2 model containing instances with prediction data.

required

Returns:

Type Description
Detections

A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

Example
>>> import cv2
>>> from detectron2.engine import DefaultPredictor
>>> from detectron2.config import get_cfg
>>> import supervision as sv

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> cfg = get_cfg()
>>> cfg.merge_from_file("path/to/config.yaml")
>>> cfg.MODEL.WEIGHTS = "path/to/model_weights.pth"
>>> predictor = DefaultPredictor(cfg)
>>> result = predictor(image)

>>> detections = sv.Detections.from_detectron2(result)
Source code in supervision/detection/core.py
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
@classmethod
def from_detectron2(cls, detectron2_results) -> Detections:
    """
    Create a Detections object from the [Detectron2](https://github.com/facebookresearch/detectron2) inference result.

    Args:
        detectron2_results: The output of a Detectron2 model containing instances with prediction data.

    Returns:
        (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

    Example:
        ```python
        >>> import cv2
        >>> from detectron2.engine import DefaultPredictor
        >>> from detectron2.config import get_cfg
        >>> import supervision as sv

        >>> image = cv2.imread(SOURCE_IMAGE_PATH)
        >>> cfg = get_cfg()
        >>> cfg.merge_from_file("path/to/config.yaml")
        >>> cfg.MODEL.WEIGHTS = "path/to/model_weights.pth"
        >>> predictor = DefaultPredictor(cfg)
        >>> result = predictor(image)

        >>> detections = sv.Detections.from_detectron2(result)
        ```
    """
    return cls(
        xyxy=detectron2_results["instances"].pred_boxes.tensor.cpu().numpy(),
        confidence=detectron2_results["instances"].scores.cpu().numpy(),
        class_id=detectron2_results["instances"]
        .pred_classes.cpu()
        .numpy()
        .astype(int),
    )

from_mmdetection(mmdet_results) classmethod

Creates a Detections instance from a mmdetection inference result. Also supported for mmyolo

Parameters:

Name Type Description Default
mmdet_results DetDataSample

The output Results instance from MMDetection

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import cv2
>>> import supervision as sv
>>> from mmdet.apis import DetInferencer

>>> inferencer = DetInferencer(model_name, checkpoint, device)
>>> mmdet_result = inferencer(SOURCE_IMAGE_PATH, out_dir='./output', return_datasample=True)["predictions"][0]
>>> detections = sv.Detections.from_mmdet(mmdet_result)
Source code in supervision/detection/core.py
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
@classmethod
def from_mmdetection(cls, mmdet_results) -> Detections:
    """
    Creates a Detections instance from a [mmdetection](https://github.com/open-mmlab/mmdetection) inference result.
    Also supported for [mmyolo](https://github.com/open-mmlab/mmyolo)

    Args:
        mmdet_results (mmdet.structures.DetDataSample): The output Results instance from MMDetection

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import cv2
        >>> import supervision as sv
        >>> from mmdet.apis import DetInferencer

        >>> inferencer = DetInferencer(model_name, checkpoint, device)
        >>> mmdet_result = inferencer(SOURCE_IMAGE_PATH, out_dir='./output', return_datasample=True)["predictions"][0]
        >>> detections = sv.Detections.from_mmdet(mmdet_result)
        ```
    """
    return cls(
        xyxy=mmdet_results.pred_instances.bboxes.cpu().numpy(),
        confidence=mmdet_results.pred_instances.scores.cpu().numpy(),
        class_id=mmdet_results.pred_instances.labels.cpu().numpy().astype(int),
    )

from_paddledet(paddledet_result) classmethod

Creates a Detections instance from PaddleDetection inference result.

Parameters:

Name Type Description Default
paddledet_result List[dict]

The output Results instance from SAM

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import supervision as sv
>>> import paddle
>>> from ppdet.engine import Trainer
>>> from ppdet.core.workspace import load_config

>>> weights = (...)
>>> config = (...)

>>> cfg = load_config(config)
>>> trainer = Trainer(cfg, mode='test')
>>> trainer.load_weights(weights)

>>> paddledet_result = trainer.predict([images])[0]

>>> detections = sv.Detections.from_paddledet(paddledet_result=paddledet_result)
Source code in supervision/detection/core.py
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
@classmethod
def from_paddledet(cls, paddledet_result) -> Detections:
    """
    Creates a Detections instance from [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) inference result.

    Args:
        paddledet_result (List[dict]): The output Results instance from SAM

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import supervision as sv
        >>> import paddle
        >>> from ppdet.engine import Trainer
        >>> from ppdet.core.workspace import load_config

        >>> weights = (...)
        >>> config = (...)

        >>> cfg = load_config(config)
        >>> trainer = Trainer(cfg, mode='test')
        >>> trainer.load_weights(weights)

        >>> paddledet_result = trainer.predict([images])[0]

        >>> detections = sv.Detections.from_paddledet(paddledet_result=paddledet_result)
        ```
    """
    return cls(
        xyxy=paddledet_result["bbox"][:, 2:6],
        confidence=paddledet_result["bbox"][:, 1],
        class_id=paddledet_result["bbox"][:, 0].astype(int),
    )

from_roboflow(roboflow_result, class_list) classmethod

Create a Detections object from the Roboflow API inference result.

Parameters:

Name Type Description Default
roboflow_result dict

The result from the Roboflow API containing predictions.

required
class_list List[str]

A list of class names corresponding to the class IDs in the API result.

required

Returns:

Type Description
Detections

A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

Example
>>> import supervision as sv

>>> roboflow_result = {
...     "predictions": [
...         {
...             "x": 0.5,
...             "y": 0.5,
...             "width": 0.2,
...             "height": 0.3,
...             "class": "person",
...             "confidence": 0.9
...         },
...         # ... more predictions ...
...     ]
... }
>>> class_list = ["person", "car", "dog"]

>>> detections = sv.Detections.from_roboflow(roboflow_result, class_list)
Source code in supervision/detection/core.py
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
@classmethod
def from_roboflow(cls, roboflow_result: dict, class_list: List[str]) -> Detections:
    """
    Create a Detections object from the [Roboflow](https://roboflow.com/) API inference result.

    Args:
        roboflow_result (dict): The result from the Roboflow API containing predictions.
        class_list (List[str]): A list of class names corresponding to the class IDs in the API result.

    Returns:
        (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.

    Example:
        ```python
        >>> import supervision as sv

        >>> roboflow_result = {
        ...     "predictions": [
        ...         {
        ...             "x": 0.5,
        ...             "y": 0.5,
        ...             "width": 0.2,
        ...             "height": 0.3,
        ...             "class": "person",
        ...             "confidence": 0.9
        ...         },
        ...         # ... more predictions ...
        ...     ]
        ... }
        >>> class_list = ["person", "car", "dog"]

        >>> detections = sv.Detections.from_roboflow(roboflow_result, class_list)
        ```
    """
    xyxy, confidence, class_id, masks = process_roboflow_result(
        roboflow_result=roboflow_result, class_list=class_list
    )
    return Detections(
        xyxy=xyxy,
        confidence=confidence,
        class_id=class_id,
        mask=masks,
    )

from_sam(sam_result) classmethod

Creates a Detections instance from Segment Anything Model inference result.

Parameters:

Name Type Description Default
sam_result List[dict]

The output Results instance from SAM

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import supervision as sv
>>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator

>>> sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
>>> mask_generator = SamAutomaticMaskGenerator(sam)
>>> sam_result = mask_generator.generate(IMAGE)
>>> detections = sv.Detections.from_sam(sam_result=sam_result)
Source code in supervision/detection/core.py
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
@classmethod
def from_sam(cls, sam_result: List[dict]) -> Detections:
    """
    Creates a Detections instance from [Segment Anything Model](https://github.com/facebookresearch/segment-anything) inference result.

    Args:
        sam_result (List[dict]): The output Results instance from SAM

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import supervision as sv
        >>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator

        >>> sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
        >>> mask_generator = SamAutomaticMaskGenerator(sam)
        >>> sam_result = mask_generator.generate(IMAGE)
        >>> detections = sv.Detections.from_sam(sam_result=sam_result)
        ```
    """
    sorted_generated_masks = sorted(
        sam_result, key=lambda x: x["area"], reverse=True
    )

    xywh = np.array([mask["bbox"] for mask in sorted_generated_masks])
    mask = np.array([mask["segmentation"] for mask in sorted_generated_masks])

    return Detections(xyxy=xywh_to_xyxy(boxes_xywh=xywh), mask=mask)

from_transformers(transformers_results) classmethod

Creates a Detections instance from object detection transformer inference result.

Returns:

Name Type Description
Detections Detections

A new Detections object.

Source code in supervision/detection/core.py
304
305
306
307
308
309
310
311
312
313
314
315
316
@classmethod
def from_transformers(cls, transformers_results: dict) -> Detections:
    """
    Creates a Detections instance from object detection [transformer](https://github.com/huggingface/transformers) inference result.

    Returns:
        Detections: A new Detections object.
    """
    return cls(
        xyxy=transformers_results["boxes"].cpu().numpy(),
        confidence=transformers_results["scores"].cpu().numpy(),
        class_id=transformers_results["labels"].cpu().numpy().astype(int),
    )

from_ultralytics(ultralytics_results) classmethod

Creates a Detections instance from a YOLOv8 inference result.

Parameters:

Name Type Description Default
ultralytics_results Results

The output Results instance from YOLOv8

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import cv2
>>> from ultralytics import YOLO, FastSAM, SAM, RTDETR
>>> import supervision as sv

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> model = YOLO('yolov8s.pt')
>>> model = SAM('sam_b.pt')
>>> model = SAM('mobile_sam.pt')
>>> model = FastSAM('FastSAM-s.pt')
>>> model = RTDETR('rtdetr-l.pt')
>>> # model inferences
>>> result = model(image)[0]
>>> # if tracker is enabled
>>> result = model.track(image)[0]
>>> detections = sv.Detections.from_ultralytics(result)
Source code in supervision/detection/core.py
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
@classmethod
def from_ultralytics(cls, ultralytics_results) -> Detections:
    """
    Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.

    Args:
        ultralytics_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import cv2
        >>> from ultralytics import YOLO, FastSAM, SAM, RTDETR
        >>> import supervision as sv

        >>> image = cv2.imread(SOURCE_IMAGE_PATH)
        >>> model = YOLO('yolov8s.pt')
        >>> model = SAM('sam_b.pt')
        >>> model = SAM('mobile_sam.pt')
        >>> model = FastSAM('FastSAM-s.pt')
        >>> model = RTDETR('rtdetr-l.pt')
        >>> # model inferences
        >>> result = model(image)[0]
        >>> # if tracker is enabled
        >>> result = model.track(image)[0]
        >>> detections = sv.Detections.from_ultralytics(result)
        ```
    """
    return cls(
        xyxy=ultralytics_results.boxes.xyxy.cpu().numpy(),
        confidence=ultralytics_results.boxes.conf.cpu().numpy(),
        class_id=ultralytics_results.boxes.cls.cpu().numpy().astype(int),
        mask=extract_ultralytics_masks(ultralytics_results),
        tracker_id=ultralytics_results.boxes.id.int().cpu().numpy()
        if ultralytics_results.boxes.id is not None
        else None,
    )

from_yolo_nas(yolo_nas_results) classmethod

Creates a Detections instance from a YOLO-NAS inference result.

Parameters:

Name Type Description Default
yolo_nas_results ImageDetectionPrediction

The output Results instance from YOLO-NAS

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import cv2
>>> from super_gradients.training import models
>>> import supervision as sv

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> model = models.get('yolo_nas_l', pretrained_weights="coco")
>>> result = list(model.predict(image, conf=0.35))[0]
>>> detections = sv.Detections.from_yolo_nas(result)
Source code in supervision/detection/core.py
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
@classmethod
def from_yolo_nas(cls, yolo_nas_results) -> Detections:
    """
    Creates a Detections instance from a [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) inference result.

    Args:
        yolo_nas_results (super_gradients.training.models.prediction_results.ImageDetectionPrediction): The output Results instance from YOLO-NAS

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import cv2
        >>> from super_gradients.training import models
        >>> import supervision as sv

        >>> image = cv2.imread(SOURCE_IMAGE_PATH)
        >>> model = models.get('yolo_nas_l', pretrained_weights="coco")
        >>> result = list(model.predict(image, conf=0.35))[0]
        >>> detections = sv.Detections.from_yolo_nas(result)
        ```
    """
    return cls(
        xyxy=yolo_nas_results.prediction.bboxes_xyxy,
        confidence=yolo_nas_results.prediction.confidence,
        class_id=yolo_nas_results.prediction.labels.astype(int),
    )

from_yolov5(yolov5_results) classmethod

Creates a Detections instance from a YOLOv5 inference result.

Parameters:

Name Type Description Default
yolov5_results Detections

The output Detections instance from YOLOv5

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import cv2
>>> import torch
>>> import supervision as sv

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
>>> result = model(image)
>>> detections = sv.Detections.from_yolov5(result)
Source code in supervision/detection/core.py
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
@classmethod
def from_yolov5(cls, yolov5_results) -> Detections:
    """
    Creates a Detections instance from a [YOLOv5](https://github.com/ultralytics/yolov5) inference result.

    Args:
        yolov5_results (yolov5.models.common.Detections): The output Detections instance from YOLOv5

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import cv2
        >>> import torch
        >>> import supervision as sv

        >>> image = cv2.imread(SOURCE_IMAGE_PATH)
        >>> model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
        >>> result = model(image)
        >>> detections = sv.Detections.from_yolov5(result)
        ```
    """
    yolov5_detections_predictions = yolov5_results.pred[0].cpu().cpu().numpy()
    return cls(
        xyxy=yolov5_detections_predictions[:, :4],
        confidence=yolov5_detections_predictions[:, 4],
        class_id=yolov5_detections_predictions[:, 5].astype(int),
    )

from_yolov8(yolov8_results) classmethod

Creates a Detections instance from a YOLOv8 inference result.

Parameters:

Name Type Description Default
yolov8_results Results

The output Results instance from YOLOv8

required

Returns:

Name Type Description
Detections Detections

A new Detections object.

Example
>>> import cv2
>>> from ultralytics import YOLO
>>> import supervision as sv

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> model = YOLO('yolov8s.pt')
>>> result = model(image)[0]
>>> detections = sv.Detections.from_yolov8(result)
Source code in supervision/detection/core.py
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
@classmethod
@deprecated(
    "This method is deprecated and removed in 0.15.0 release. Use sv.Detections.from_ultralytics() instead."
)
def from_yolov8(cls, yolov8_results) -> Detections:
    """
    Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.

    Args:
        yolov8_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8

    Returns:
        Detections: A new Detections object.

    Example:
        ```python
        >>> import cv2
        >>> from ultralytics import YOLO
        >>> import supervision as sv

        >>> image = cv2.imread(SOURCE_IMAGE_PATH)
        >>> model = YOLO('yolov8s.pt')
        >>> result = model(image)[0]
        >>> detections = sv.Detections.from_yolov8(result)
        ```
    """
    return cls(
        xyxy=yolov8_results.boxes.xyxy.cpu().numpy(),
        confidence=yolov8_results.boxes.conf.cpu().numpy(),
        class_id=yolov8_results.boxes.cls.cpu().numpy().astype(int),
        mask=extract_ultralytics_masks(yolov8_results),
    )

get_anchor_coordinates(anchor)

Returns the bounding box coordinates for a specific anchor.

Parameters:

Name Type Description Default
anchor Position

Position of bounding box anchor for which to return the coordinates.

required

Returns:

Type Description
ndarray

np.ndarray: An array of shape (n, 2) containing the bounding box anchor coordinates in format [x, y].

Source code in supervision/detection/core.py
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
def get_anchor_coordinates(self, anchor: Position) -> np.ndarray:
    """
    Returns the bounding box coordinates for a specific anchor.

    Args:
        anchor (Position): Position of bounding box anchor for which to return the coordinates.

    Returns:
        np.ndarray: An array of shape `(n, 2)` containing the bounding box anchor coordinates in format `[x, y]`.
    """
    if anchor == Position.CENTER:
        return np.array(
            [
                (self.xyxy[:, 0] + self.xyxy[:, 2]) / 2,
                (self.xyxy[:, 1] + self.xyxy[:, 3]) / 2,
            ]
        ).transpose()
    elif anchor == Position.BOTTOM_CENTER:
        return np.array(
            [(self.xyxy[:, 0] + self.xyxy[:, 2]) / 2, self.xyxy[:, 3]]
        ).transpose()

    raise ValueError(f"{anchor} is not supported.")

merge(detections_list) classmethod

Merge a list of Detections objects into a single Detections object.

This method takes a list of Detections objects and combines their respective fields (xyxy, mask, confidence, class_id, and tracker_id) into a single Detections object. If all elements in a field are not None, the corresponding field will be stacked. Otherwise, the field will be set to None.

Parameters:

Name Type Description Default
detections_list List[Detections]

A list of Detections objects to merge.

required

Returns:

Type Description
Detections

A single Detections object containing the merged data from the input list.

Example
>>> from supervision import Detections

>>> detections_1 = Detections(...)
>>> detections_2 = Detections(...)

>>> merged_detections = Detections.merge([detections_1, detections_2])
Source code in supervision/detection/core.py
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
@classmethod
def merge(cls, detections_list: List[Detections]) -> Detections:
    """
    Merge a list of Detections objects into a single Detections object.

    This method takes a list of Detections objects and combines their respective fields (`xyxy`, `mask`,
    `confidence`, `class_id`, and `tracker_id`) into a single Detections object. If all elements in a field are not
    `None`, the corresponding field will be stacked. Otherwise, the field will be set to `None`.

    Args:
        detections_list (List[Detections]): A list of Detections objects to merge.

    Returns:
        (Detections): A single Detections object containing the merged data from the input list.

    Example:
        ```python
        >>> from supervision import Detections

        >>> detections_1 = Detections(...)
        >>> detections_2 = Detections(...)

        >>> merged_detections = Detections.merge([detections_1, detections_2])
        ```
    """
    if len(detections_list) == 0:
        return Detections.empty()

    detections_tuples_list = [astuple(detection) for detection in detections_list]
    xyxy, mask, confidence, class_id, tracker_id = [
        list(field) for field in zip(*detections_tuples_list)
    ]

    all_not_none = lambda l: all(x is not None for x in l)

    xyxy = np.vstack(xyxy)
    mask = np.vstack(mask) if all_not_none(mask) else None
    confidence = np.hstack(confidence) if all_not_none(confidence) else None
    class_id = np.hstack(class_id) if all_not_none(class_id) else None
    tracker_id = np.hstack(tracker_id) if all_not_none(tracker_id) else None

    return cls(
        xyxy=xyxy,
        mask=mask,
        confidence=confidence,
        class_id=class_id,
        tracker_id=tracker_id,
    )

with_nms(threshold=0.5, class_agnostic=False)

Perform non-maximum suppression on the current set of object detections.

Parameters:

Name Type Description Default
threshold float

The intersection-over-union threshold to use for non-maximum suppression. Defaults to 0.5.

0.5
class_agnostic bool

Whether to perform class-agnostic non-maximum suppression. If True, the class_id of each detection will be ignored. Defaults to False.

False

Returns:

Name Type Description
Detections Detections

A new Detections object containing the subset of detections after non-maximum suppression.

Raises:

Type Description
AssertionError

If confidence is None and class_agnostic is False. If class_id is None and class_agnostic is False.

Source code in supervision/detection/core.py
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
def with_nms(
    self, threshold: float = 0.5, class_agnostic: bool = False
) -> Detections:
    """
    Perform non-maximum suppression on the current set of object detections.

    Args:
        threshold (float, optional): The intersection-over-union threshold to use for non-maximum suppression. Defaults to 0.5.
        class_agnostic (bool, optional): Whether to perform class-agnostic non-maximum suppression. If True, the class_id of each detection will be ignored. Defaults to False.

    Returns:
        Detections: A new Detections object containing the subset of detections after non-maximum suppression.

    Raises:
        AssertionError: If `confidence` is None and class_agnostic is False. If `class_id` is None and class_agnostic is False.
    """
    if len(self) == 0:
        return self

    assert (
        self.confidence is not None
    ), f"Detections confidence must be given for NMS to be executed."

    if class_agnostic:
        predictions = np.hstack((self.xyxy, self.confidence.reshape(-1, 1)))
        indices = non_max_suppression(
            predictions=predictions, iou_threshold=threshold
        )
        return self[indices]

    assert self.class_id is not None, (
        f"Detections class_id must be given for NMS to be executed. If you intended to perform class agnostic "
        f"NMS set class_agnostic=True."
    )

    predictions = np.hstack(
        (self.xyxy, self.confidence.reshape(-1, 1), self.class_id.reshape(-1, 1))
    )
    indices = non_max_suppression(predictions=predictions, iou_threshold=threshold)
    return self[indices]