Skip to content

v0.6.9 - Support custom pose keypoint counts on Android (#556)

Latest

Choose a tag to compare

@UltralyticsAssistant UltralyticsAssistant released this 04 Jul 20:28
1dbccc6

🌟 Summary

v0.6.9 fixes Android pose inference for custom keypoint models, making non-COCO pose models like hand-landmark models work correctly in the Ultralytics YOLO Flutter plugin πŸ€–πŸ“±

πŸ“Š Key Changes

  • Custom Android pose keypoint support πŸ§β€β™‚οΈβœ‹
    Android pose parsing now detects the number of keypoints from the model output shape instead of assuming the standard 17-keypoint COCO pose format.

  • Improved pose output handling πŸ”§
    The Android PoseEstimator now supports both common pose output layouts more dynamically, including anchor-grid outputs and capped end-to-end outputs.

  • Better custom model compatibility πŸš€
    Custom pose models, such as 21-keypoint hand landmark models, can now return all expected keypoints instead of being limited or rejected by a hardcoded output size.

  • Cleaner Play Store packaging πŸ“¦
    The Play Store asset build script now includes only the approved bundled YOLO26 Android models in release builds, while preserving any local custom or benchmark model files after the build.

  • Release workflow hardening πŸ”
    Publishing is now restricted to the main branch, reducing the risk of accidental releases from feature branches.

  • Test and repository cleanup 🧹
    Redundant example tests were removed, constructor-focused tests were renamed and clarified, and new AGENTS.md guidance was added for AI coding agents working in the repository.

  • Version bump 🏷️
    Package surfaces were updated to 0.6.9, including Flutter, iOS podspec, example app version, and changelog entries.

🎯 Purpose & Impact

  • More flexible pose apps βœ…
    Developers can now deploy custom Android pose models with different keypoint counts, opening the door to use cases like hand tracking, face landmarks, sports-specific poses, and other specialized landmark models.

  • Fewer model-shape failures πŸ› οΈ
    By deriving keypoint counts dynamically, the plugin is less brittle and better aligned with real-world custom YOLO pose exports.

  • Safer app releases πŸ›‘οΈ
    Play Store builds are cleaner and more predictable, with only official YOLO26 bundled assets included in upload artifacts.

  • More reliable publishing 🚒
    The release workflow change helps ensure GitHub releases and pub.dev publishing happen only from trusted main branch commits.

  • Improved maintainability πŸ“š
    Cleaner tests and contributor guidance make future development easier, while preserving confidence through formatting, analysis, Flutter tests, publish dry-runs, and Android debug APK validation.

What's Changed

Full Changelog: v0.6.8...v0.6.9