pose_detection 2.0.2
pose_detection: ^2.0.2 copied to clipboard
Pose, person and landmark detection using on-device TFLite models.
2.0.2 #
- Update flutter_litert 2.0.5 -> 2.0.6
2.0.1 #
- Fix Xcode build warnings by declaring PrivacyInfo.xcprivacy as a resource bundle in iOS and macOS podspecs
2.0.0 #
Breaking: Point now uses double coordinates. BoundingBox is now a 4-corner Point-based type.
- Use shared
PointandBoundingBoxfromflutter_litert2.0.0 toPixel()now returns full-precisiondoublecoordinates (was truncating toint)- Extract
PersonDetectorBaseshared between native and web detectors - Simplify model classes and detector implementations
- Remove integration tests from unit test suite
- Remove dead test helpers (
test_config.dart)
1.0.7 #
- Update
camera_desktop1.0.1 -> 1.0.3
1.0.6 #
- Update
flutter_litert-> 1.2.0 - Refactor to use
flutter_litertshared utilities (InterpreterFactory,InterpreterPool,PerformanceConfig)
1.0.5 #
- Update
opencv_dart2.1.0 -> 2.2.1 - Update
flutter_litert1.0.2 -> 1.0.3
1.0.4 #
- Update
flutter_litert1.0.1 -> 1.0.2
1.0.3 #
- Update documentation
1.0.2 #
- Update
flutter_litertto 1.0.1,camerato 0.12.0
1.0.1 #
- Update
flutter_litertto 0.2.2
1.0.0 #
- Initial release
- Person detection using YOLOv8
- Pose landmark detection with MediaPipe Pose
- Support for lite, full, and heavy models
- Box-only and full landmark detection modes