generated from roboflow/template-python
-
Notifications
You must be signed in to change notification settings - Fork 1.2k
/
core.py
1412 lines (1162 loc) Β· 49.7 KB
/
core.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
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
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
from __future__ import annotations
from contextlib import suppress
from dataclasses import dataclass, field
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
import numpy as np
from supervision.config import CLASS_NAME_DATA_FIELD, ORIENTED_BOX_COORDINATES
from supervision.detection.lmm import LMM, from_paligemma, validate_lmm_and_kwargs
from supervision.detection.overlap_filter import (
box_non_max_merge,
box_non_max_suppression,
mask_non_max_suppression,
)
from supervision.detection.utils import (
box_iou_batch,
calculate_masks_centroids,
extract_ultralytics_masks,
get_data_item,
is_data_equal,
mask_to_xyxy,
merge_data,
process_roboflow_result,
xywh_to_xyxy,
)
from supervision.geometry.core import Position
from supervision.utils.internal import deprecated, get_instance_variables
from supervision.validators import validate_detections_fields
@dataclass
class Detections:
"""
The `sv.Detections` class in the Supervision library standardizes results from
various object detection and segmentation models into a consistent format. This
class simplifies data manipulation and filtering, providing a uniform API for
integration with Supervision [trackers](/trackers/), [annotators](/detection/annotators/), and [tools](/detection/tools/line_zone/).
=== "Inference"
Use [`sv.Detections.from_inference`](/detection/core/#supervision.detection.core.Detections.from_inference)
method, which accepts model results from both detection and segmentation models.
```python
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
```
=== "Ultralytics"
Use [`sv.Detections.from_ultralytics`](/detection/core/#supervision.detection.core.Detections.from_ultralytics)
method, which accepts model results from both detection and segmentation models.
```python
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
```
=== "Transformers"
Use [`sv.Detections.from_transformers`](/detection/core/#supervision.detection.core.Detections.from_transformers)
method, which accepts model results from both detection and segmentation models.
```python
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)
```
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.
data (Dict[str, Union[np.ndarray, List]]): A dictionary containing additional
data where each key is a string representing the data type, and the value
is either a NumPy array or a list of corresponding data.
""" # noqa: E501 // docs
xyxy: np.ndarray
mask: Optional[np.ndarray] = None
confidence: Optional[np.ndarray] = None
class_id: Optional[np.ndarray] = None
tracker_id: Optional[np.ndarray] = None
data: Dict[str, Union[np.ndarray, List]] = field(default_factory=dict)
def __post_init__(self):
validate_detections_fields(
xyxy=self.xyxy,
mask=self.mask,
confidence=self.confidence,
class_id=self.class_id,
tracker_id=self.tracker_id,
data=self.data,
)
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],
Dict[str, Union[np.ndarray, List]],
]
]:
"""
Iterates over the Detections object and yield a tuple of
`(xyxy, mask, confidence, class_id, tracker_id, data)` 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,
get_data_item(self.data, i),
)
def __eq__(self, other: Detections):
return all(
[
np.array_equal(self.xyxy, other.xyxy),
np.array_equal(self.mask, other.mask),
np.array_equal(self.class_id, other.class_id),
np.array_equal(self.confidence, other.confidence),
np.array_equal(self.tracker_id, other.tracker_id),
is_data_equal(self.data, other.data),
]
)
@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
def from_ultralytics(cls, ultralytics_results) -> Detections:
"""
Creates a `sv.Detections` instance from a
[YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
!!! Note
`from_ultralytics` is compatible with
[detection](https://docs.ultralytics.com/tasks/detect/),
[segmentation](https://docs.ultralytics.com/tasks/segment/), and
[OBB](https://docs.ultralytics.com/tasks/obb/) models.
Args:
ultralytics_results (ultralytics.yolo.engine.results.Results):
The output Results instance from Ultralytics
Returns:
Detections: A new Detections object.
Example:
```python
import cv2
import supervision as sv
from ultralytics import YOLO
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = YOLO('yolov8s.pt')
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
```
!!! tip
Class names values can be accessed using `detections["class_name"]`.
""" # noqa: E501 // docs
if hasattr(ultralytics_results, "obb") and ultralytics_results.obb is not None:
class_id = ultralytics_results.obb.cls.cpu().numpy().astype(int)
class_names = np.array([ultralytics_results.names[i] for i in class_id])
oriented_box_coordinates = ultralytics_results.obb.xyxyxyxy.cpu().numpy()
return cls(
xyxy=ultralytics_results.obb.xyxy.cpu().numpy(),
confidence=ultralytics_results.obb.conf.cpu().numpy(),
class_id=class_id,
tracker_id=ultralytics_results.obb.id.int().cpu().numpy()
if ultralytics_results.obb.id is not None
else None,
data={
ORIENTED_BOX_COORDINATES: oriented_box_coordinates,
CLASS_NAME_DATA_FIELD: class_names,
},
)
class_id = ultralytics_results.boxes.cls.cpu().numpy().astype(int)
class_names = np.array([ultralytics_results.names[i] for i in class_id])
return cls(
xyxy=ultralytics_results.boxes.xyxy.cpu().numpy(),
confidence=ultralytics_results.boxes.conf.cpu().numpy(),
class_id=class_id,
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,
data={CLASS_NAME_DATA_FIELD: class_names},
)
@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 (ImageDetectionPrediction):
The output Results instance from YOLO-NAS
ImageDetectionPrediction is coming from
'super_gradients.training.models.prediction_results'
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)
```
"""
if np.asarray(yolo_nas_results.prediction.bboxes_xyxy).shape[0] == 0:
return cls.empty()
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_tensorflow(
cls, tensorflow_results: dict, resolution_wh: tuple
) -> Detections:
"""
Creates a Detections instance from a
[Tensorflow Hub](https://www.tensorflow.org/hub/tutorials/tf2_object_detection)
inference result.
Args:
tensorflow_results (dict):
The output results from Tensorflow Hub.
Returns:
Detections: A new Detections object.
Example:
```python
import tensorflow as tf
import tensorflow_hub as hub
import numpy as np
import cv2
module_handle = "https://tfhub.dev/tensorflow/centernet/hourglass_512x512_kpts/1"
model = hub.load(module_handle)
img = np.array(cv2.imread(SOURCE_IMAGE_PATH))
result = model(img)
detections = sv.Detections.from_tensorflow(result)
```
""" # noqa: E501 // docs
boxes = tensorflow_results["detection_boxes"][0].numpy()
boxes[:, [0, 2]] *= resolution_wh[0]
boxes[:, [1, 3]] *= resolution_wh[1]
boxes = boxes[:, [1, 0, 3, 2]]
return cls(
xyxy=boxes,
confidence=tensorflow_results["detection_scores"][0].numpy(),
class_id=tensorflow_results["detection_classes"][0].numpy().astype(int),
)
@classmethod
def from_deepsparse(cls, deepsparse_results) -> Detections:
"""
Creates a Detections instance from a
[DeepSparse](https://github.com/neuralmagic/deepsparse)
inference result.
Args:
deepsparse_results (deepsparse.yolo.schemas.YOLOOutput):
The output Results instance from DeepSparse.
Returns:
Detections: A new Detections object.
Example:
```python
import supervision as sv
from deepsparse import Pipeline
yolo_pipeline = Pipeline.create(
task="yolo",
model_path = "zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned80_quant-none"
)
result = yolo_pipeline(<SOURCE IMAGE PATH>)
detections = sv.Detections.from_deepsparse(result)
```
""" # noqa: E501 // docs
if np.asarray(deepsparse_results.boxes[0]).shape[0] == 0:
return cls.empty()
return cls(
xyxy=np.array(deepsparse_results.boxes[0]),
confidence=np.array(deepsparse_results.scores[0]),
class_id=np.array(deepsparse_results.labels[0]).astype(float).astype(int),
)
@classmethod
def from_mmdetection(cls, mmdet_results) -> Detections:
"""
Creates a Detections instance from a
[mmdetection](https://github.com/open-mmlab/mmdetection) and
[mmyolo](https://github.com/open-mmlab/mmyolo) inference result.
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 init_detector, inference_detector
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = init_detector(<CONFIG_PATH>, <WEIGHTS_PATH>, device=<DEVICE>)
result = inference_detector(model, image)
detections = sv.Detections.from_mmdetection(result)
```
""" # noqa: E501 // docs
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),
mask=mmdet_results.pred_instances.masks.cpu().numpy()
if "masks" in mmdet_results.pred_instances
else None,
)
@classmethod
def from_transformers(
cls, transformers_results: dict, id2label: Optional[Dict[int, str]] = None
) -> Detections:
"""
Creates a Detections instance from object detection or segmentation
[Transformer](https://github.com/huggingface/transformers) inference result.
Args:
transformers_results (dict): The output of Transformers model inference. A
dictionary containing the `scores`, `labels`, `boxes` and `masks` keys.
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to
class names. If provided, the resulting Detections object will contain
`class_name` data field with the class names.
Returns:
Detections: A new Detections object.
Example:
```python
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label
)
```
!!! tip
Class names values can be accessed using `detections["class_name"]`.
""" # noqa: E501 // docs
class_ids = transformers_results["labels"].cpu().detach().numpy().astype(int)
data = {}
if id2label is not None:
class_names = np.array([id2label[class_id] for class_id in class_ids])
data[CLASS_NAME_DATA_FIELD] = class_names
if "boxes" in transformers_results:
return cls(
xyxy=transformers_results["boxes"].cpu().detach().numpy(),
confidence=transformers_results["scores"].cpu().detach().numpy(),
class_id=class_ids,
data=data,
)
elif "masks" in transformers_results:
masks = transformers_results["masks"].cpu().detach().numpy().astype(bool)
return cls(
xyxy=mask_to_xyxy(masks),
mask=masks,
confidence=transformers_results["scores"].cpu().detach().numpy(),
class_id=class_ids,
data=data,
)
else:
raise NotImplementedError(
"Only object detection and semantic segmentation results are supported."
)
@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
import supervision as sv
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
image = cv2.imread(<SOURCE_IMAGE_PATH>)
cfg = get_cfg()
cfg.merge_from_file(<CONFIG_PATH>)
cfg.MODEL.WEIGHTS = <WEIGHTS_PATH>
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_inference(cls, roboflow_result: Union[dict, Any]) -> Detections:
"""
Create a `sv.Detections` object from the [Roboflow](https://roboflow.com/)
API inference result or the [Inference](https://inference.roboflow.com/)
package results. This method extracts bounding boxes, class IDs,
confidences, and class names from the Roboflow API result and encapsulates
them into a Detections object.
Args:
roboflow_result (dict, any): The result from the
Roboflow API or Inference package containing predictions.
Returns:
(Detections): A Detections object containing the bounding boxes, class IDs,
and confidences of the predictions.
Example:
```python
import cv2
import supervision as sv
from inference import get_model
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = get_model(model_id="yolov8s-640")
result = model.infer(image)[0]
detections = sv.Detections.from_inference(result)
```
!!! tip
Class names values can be accessed using `detections["class_name"]`.
"""
with suppress(AttributeError):
roboflow_result = roboflow_result.dict(exclude_none=True, by_alias=True)
xyxy, confidence, class_id, masks, trackers, data = process_roboflow_result(
roboflow_result=roboflow_result
)
if np.asarray(xyxy).shape[0] == 0:
empty_detection = cls.empty()
empty_detection.data = {CLASS_NAME_DATA_FIELD: np.empty(0)}
return empty_detection
return cls(
xyxy=xyxy,
confidence=confidence,
class_id=class_id,
mask=masks,
tracker_id=trackers,
data=data,
)
@classmethod
@deprecated(
"`Detections.from_roboflow` is deprecated and will be removed in "
"`supervision-0.22.0`. Use `Detections.from_inference` instead."
)
def from_roboflow(cls, roboflow_result: Union[dict, Any]) -> Detections:
"""
!!! failure "Deprecated"
`Detections.from_roboflow` is deprecated and will be removed in
`supervision-0.22.0`. Use `Detections.from_inference` instead.
Create a Detections object from the [Roboflow](https://roboflow.com/)
API inference result or the [Inference](https://inference.roboflow.com/)
package results.
Args:
roboflow_result (dict): The result from the
Roboflow API containing predictions.
Returns:
(Detections): A Detections object containing the bounding boxes, class IDs,
and confidences of the predictions.
Example:
```python
import cv2
import supervision as sv
from inference import get_model
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = get_model(model_id="yolov8s-640")
result = model.infer(image)[0]
detections = sv.Detections.from_roboflow(result)
```
"""
return cls.from_inference(roboflow_result)
@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_model_reg = sam_model_registry[MODEL_TYPE]
sam = sam_model_reg(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])
if np.asarray(xywh).shape[0] == 0:
return cls.empty()
xyxy = xywh_to_xyxy(boxes_xywh=xywh)
return cls(xyxy=xyxy, mask=mask)
@classmethod
def from_azure_analyze_image(
cls, azure_result: dict, class_map: Optional[Dict[int, str]] = None
) -> Detections:
"""
Creates a Detections instance from [Azure Image Analysis 4.0](
https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/
concept-object-detection-40).
Args:
azure_result (dict): The result from Azure Image Analysis. It should
contain detected objects and their bounding box coordinates.
class_map (Optional[Dict[int, str]]): A mapping ofclass IDs (int) to class
names (str). If None, a new mapping is created dynamically.
Returns:
Detections: A new Detections object.
Example:
```python
import requests
import supervision as sv
image = open(input, "rb").read()
endpoint = "https://.cognitiveservices.azure.com/"
subscription_key = ""
headers = {
"Content-Type": "application/octet-stream",
"Ocp-Apim-Subscription-Key": subscription_key
}
response = requests.post(endpoint,
headers=self.headers,
data=image
).json()
detections = sv.Detections.from_azure_analyze_image(response)
```
"""
if "error" in azure_result:
raise ValueError(
f'Azure API returned an error {azure_result["error"]["message"]}'
)
xyxy, confidences, class_ids = [], [], []
is_dynamic_mapping = class_map is None
if is_dynamic_mapping:
class_map = {}
class_map = {value: key for key, value in class_map.items()}
for detection in azure_result["objectsResult"]["values"]:
bbox = detection["boundingBox"]
tags = detection["tags"]
x0 = bbox["x"]
y0 = bbox["y"]
x1 = x0 + bbox["w"]
y1 = y0 + bbox["h"]
for tag in tags:
confidence = tag["confidence"]
class_name = tag["name"]
class_id = class_map.get(class_name, None)
if is_dynamic_mapping and class_id is None:
class_id = len(class_map)
class_map[class_name] = class_id
if class_id is not None:
xyxy.append([x0, y0, x1, y1])
confidences.append(confidence)
class_ids.append(class_id)
if len(xyxy) == 0:
return Detections.empty()
return cls(
xyxy=np.array(xyxy),
class_id=np.array(class_ids),
confidence=np.array(confidences),
)
@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 PaddleDet
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)
```
"""
if np.asarray(paddledet_result["bbox"][:, 2:6]).shape[0] == 0:
return cls.empty()
return cls(
xyxy=paddledet_result["bbox"][:, 2:6],
confidence=paddledet_result["bbox"][:, 1],
class_id=paddledet_result["bbox"][:, 0].astype(int),
)
@classmethod
def from_lmm(cls, lmm: Union[LMM, str], result: str, **kwargs) -> Detections:
"""
Creates a Detections object from the given result string based on the specified
Large Multimodal Model (LMM).
Args:
lmm (Union[LMM, str]): The type of LMM (Large Multimodal Model) to use.
result (str): The result string containing the detection data.
**kwargs: Additional keyword arguments required by the specified LMM.
Returns:
Detections: A new Detections object.
Raises:
ValueError: If the LMM is invalid, required arguments are missing, or
disallowed arguments are provided.
ValueError: If the specified LMM is not supported.
Examples:
```python
import supervision as sv
paligemma_result = "<loc0256><loc0256><loc0768><loc0768> cat"
detections = sv.Detections.from_lmm(
sv.LMM.PALIGEMMA,
paligemma_result,
resolution_wh=(1000, 1000),
classes=['cat', 'dog']
)
detections.xyxy
# array([[250., 250., 750., 750.]])
detections.class_id
# array([0])
```
"""
lmm = validate_lmm_and_kwargs(lmm, kwargs)
if lmm == LMM.PALIGEMMA:
xyxy, class_id, class_name = from_paligemma(result, **kwargs)
data = {CLASS_NAME_DATA_FIELD: class_name}
return cls(xyxy=xyxy, class_id=class_id, data=data)
raise ValueError(f"Unsupported LMM: {lmm}")
@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),
)
def is_empty(self) -> bool:
"""
Returns `True` if the `Detections` object is considered empty.
"""
empty_detections = Detections.empty()
empty_detections.data = self.data
return self == empty_detections
@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.
For example, if merging Detections with 3 and 4 detected objects, this method
will return a Detections with 7 objects (7 entries in `xyxy`, `mask`, etc).
!!! Note
When merging, empty `Detections` objects are ignored.
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
import numpy as np
import supervision as sv
detections_1 = sv.Detections(
xyxy=np.array([[15, 15, 100, 100], [200, 200, 300, 300]]),
class_id=np.array([1, 2]),
data={'feature_vector': np.array([0.1, 0.2)])}
)
detections_2 = sv.Detections(
xyxy=np.array([[30, 30, 120, 120]]),
class_id=np.array([1]),
data={'feature_vector': [np.array([0.3])]}
)
merged_detections = Detections.merge([detections_1, detections_2])
merged_detections.xyxy
array([[ 15, 15, 100, 100],
[200, 200, 300, 300],
[ 30, 30, 120, 120]])
merged_detections.class_id
array([1, 2, 1])
merged_detections.data['feature_vector']
array([0.1, 0.2, 0.3])
```
"""
detections_list = [
detections for detections in detections_list if not detections.is_empty()
]
if len(detections_list) == 0:
return Detections.empty()
for detections in detections_list:
validate_detections_fields(
xyxy=detections.xyxy,
mask=detections.mask,
confidence=detections.confidence,
class_id=detections.class_id,
tracker_id=detections.tracker_id,
data=detections.data,
)
xyxy = np.vstack([d.xyxy for d in detections_list])
def stack_or_none(name: str):
if all(d.__getattribute__(name) is None for d in detections_list):
return None
if any(d.__getattribute__(name) is None for d in detections_list):
raise ValueError(f"All or none of the '{name}' fields must be None")
return (
np.vstack([d.__getattribute__(name) for d in detections_list])
if name == "mask"
else np.hstack([d.__getattribute__(name) for d in detections_list])
)
mask = stack_or_none("mask")
confidence = stack_or_none("confidence")
class_id = stack_or_none("class_id")
tracker_id = stack_or_none("tracker_id")
data = merge_data([d.data for d in detections_list])
return cls(
xyxy=xyxy,
mask=mask,
confidence=confidence,
class_id=class_id,
tracker_id=tracker_id,
data=data,
)
def get_anchors_coordinates(self, anchor: Position) -> np.ndarray:
"""
Calculates and returns the coordinates of a specific anchor point
within the bounding boxes defined by the `xyxy` attribute. The anchor
point can be any of the predefined positions in the `Position` enum,
such as `CENTER`, `CENTER_LEFT`, `BOTTOM_RIGHT`, etc.
Args:
anchor (Position): An enum specifying the position of the anchor point
within the bounding box. Supported positions are defined in the
`Position` enum.