supervision-0.10.0

[SkalskiP]

🚀 Added

• Ability to load and save sv.ClassificationDataset in a folder structure format. (Add ClassificationDataset API #125)

>>> import supervision as sv

>>> cs = sv.ClassificationDataset.from_folder_structure(
...     root_directory_path='...'
... )

>>> cs.as_folder_structure(
...     root_directory_path='...'
... )

• Support for sv.ClassificationDataset.split allowing to divide sv.ClassificationDataset into two parts. (Add ClassificationDataset API #125)

>>> import supervision as sv

>>> cs = sv.ClassificationDataset(...)
>>> train_cs, test_cs = cs.split(split_ratio=0.7, random_state=42, shuffle=True)

>>> len(train_cs), len(test_cs)
(700, 300)

• Ability to extract masks from Roboflow API results using sv.Detections.from_roboflow. (Add semantic segmentation polygon loading from Roboflow #110)

• Supervision Quickstart notebook where you can learn more about Detection, Dataset and Video APIs.

🌱 Changed

• sv.get_video_frames_generator documentation to better describe actual behavior. (Update stride definition #135)

🏆 Contributors

@capjamesg @dankresio @SkalskiP

---

This discussion was created from the release supervision-0.10.0.