Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Weightcalibration #44

Open
wants to merge 26 commits into
base: main
Choose a base branch
from

Conversation

john-rocky
Copy link
Contributor

@john-rocky john-rocky commented Jul 11, 2024

Added calibration calculation to the weight of the Human model.

🛠️ PR Summary

Made with ❤️ by Ultralytics Actions

🌟 Summary

This PR adds significant updates and improvements to the YOLO iOS app, including model enhancements and UI adjustments for better user experience.

📊 Key Changes

  • Project Configuration: Updated object version and build settings.
  • New Source Files: Added PostProcessing.swift, HumanModel.swift, TrackingModel.swift, and SaveResults.swift.
  • Updated Interface:
    • Changes to Main.storyboard and LaunchScreen.storyboard.
    • Added new images and modified existing ones in Assets.xcassets.
  • Code Enhancements:
    • Added post-processing steps for model output.
    • Introduced human tracking (TrackingModel.swift) and post-processing (PostProcessing.swift).
    • Added functionality to save detection results to CSV (SaveResults.swift).
    • Enhanced bounding box functionality in BoundingBoxView.swift.
  • Model Switching and Handling:
    • Separated logic for different model types (detection vs. human).
    • Added observer for device orientation changes.
    • Included functionality to adjust camera orientation dynamically in VideoCapture.swift.
    • New UI elements for task switching (detection vs. human) and tracking mode.

🎯 Purpose & Impact

  • Improved Usability:
    • Enhanced the app's user interface for a smoother experience.
    • Improved handling of model switching and dynamic orientation adjustment.
    • New Task Segment Control for toggling between detection and human tasks, enhancing flexibility.
  • Enhanced Features:
    • Added sophisticated post-processing and human tracking capabilities.
    • Enabled saving of detection results in a more organized CSV format for better data management.
    • Introduced more accurate and informative bounding boxes with additional inner text details.
  • Developer Feedback & Modes:
    • Improved developer mode with better saving and handling of detection data.
    • Allowed real-time updates to developer settings and data-saving mechanisms.

These changes significantly enhance the application's functionality, making it more versatile and user-friendly while providing robust features for detection and tracking. 🚀📱

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants