supervision-0.13.0

[SkalskiP]

🚀 Added

• Support for mean average precision (mAP) for object detection models with sv.MeanAveragePrecision. (#236)

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

>>> dataset = sv.DetectionDataset.from_yolo(...)

>>> model = YOLO(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
...     result = model(image)[0]
...     return sv.Detections.from_yolov8(result)

>>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
...     dataset = dataset,
...     callback = callback
... )

>>> mean_average_precision.map50_95
0.433

• Support for ByteTrack for object tracking with sv.ByteTrack. (#256)

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

>>> model = YOLO(...)
>>> byte_tracker = sv.ByteTrack()
>>> annotator = sv.BoxAnnotator()

>>> def callback(frame: np.ndarray, index: int) -> np.ndarray:
...     results = model(frame)[0]
...     detections = sv.Detections.from_yolov8(results)
...     detections = byte_tracker.update_from_detections(detections=detections)
...     labels = [
...         f"#{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
...         for _, _, confidence, class_id, tracker_id
...         in detections
...     ]
...     return annotator.annotate(scene=frame.copy(), detections=detections, labels=labels)

>>> sv.process_video(
...     source_path='...',
...     target_path='...',
...     callback=callback
... )

byte_track_result_small.mp4

• sv.Detections.from_ultralytics to enable seamless integration with Ultralytics framework. This will enable you to use supervision with all models that Ultralytics supports. (#222)

  Warning
  sv.Detections.from_yolov8 is now deprecated and will be removed with supervision-0.15.0 release.

• sv.Detections.from_paddledet to enable seamless integration with PaddleDetection framework. (#191)

• Support for loading PASCAL VOC segmentation datasets with sv.DetectionDataset.. (#245)

🏆 Contributors

@hardikdava (Hardik Dava), @kirilllzaitsev (Kirill Zaitsev), @onuralpszr (Onuralp SEZER), @dbroboflow (Dervis Basbabasi), @mayankagarwals (Mayank Agarwal), @danigarciaoca (Daniel M. García-Ocaña), @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

---

This discussion was created from the release supervision-0.13.0.

[maddust]

@SkalskiP there is a typo in the documentation detections = byte_tracker.update_ from_detections(detections=detections) -------> detections = byte_tracker.update_with _detections(detections=detections)

BTW great work guys. you have been killing it !

[SkalskiP]

Hi, @maddust 👋🏻! Thanks for pointing that out. 🙏🏻 I just updated the docs: https://roboflow.github.io/supervision/tracker/core/#supervision.tracker.byte_tracker.core.ByteTrack.update_with_detections

[epochDVKHN]

@SkalskiP is the redesigned annotators with the trail annotations out in this release?

Yeah I agree, supervision is simply amazing 🤩

[hardikdava]

Hi @ElNoSabe322 :wave, thanks for taking an interest in the feature. We are already working on redesigning annotators. The feature will be available in next releases.

[SkalskiP]

Hi, @ElNoSabe322 👋🏻! As @hardikdava said, the work on new annotators is in the advanced stage, but we were not ready for supervision-0.13.0. I hope we will be ready to release it with supervision-0.14.0. Stay tuned.

[anshulsdeshpande]

I am getting followin error. Can anyone please help:
IndexError: boolean index did not match indexed array along dimension 0; dimension is 93 but corresponding boolean dimension is 94

[anshulsdeshpande]

Hi @LinasKo
I am running following code for object detection and counting. however, I am running into the mentioned error.
https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-track-and-count-vehicles-with-yolov8.ipynb

[LinasKo]

I see, the notebook uses a very old supervision version.

I'll see if I can make it compatible with the more recent developments.

[anshulsdeshpande]

@LinasKo updated supervision ( version =0.21.0rc3) worked. Thanks a lot :)

[SkalskiP]

@anshulsdeshpande also here is updated version of that notebook: https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-track-and-count-vehicles-with-yolov8-and-supervison.ipynb

[LinasKo]

@anshulsdeshpande, one final remark: I think it'd be best to use supervision.
That'll guarantee you future updates. I initially assumed that one was failing 🙂