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

Add mlmodelconfig for patch #80

Closed
wants to merge 1 commit into from
Closed

Conversation

john-rocky
Copy link
Contributor

@john-rocky john-rocky commented Jan 29, 2025

This fix is ​​a patch to fix a bug that caused custom models to return incorrect results on macOS 15.
Custom models will work as usual by disabling experimentalMLE5EngineUsage in MLModelConfiguration.

let config = MLModelConfiguration()
config.setValue(1, forKey: "experimentalMLE5EngineUsage")

🛠️ PR Summary

Made with ❤️ by Ultralytics Actions

🌟 Summary

Updated ML model configuration in the YOLO iOS app for optimization and consistency across all model variants.

📊 Key Changes

  • 🛠️ Introduced a new MLModelConfiguration (mlmodelConfig) with an experimental setting (experimentalMLE5EngineUsage).
  • 📈 Standardized the use of mlmodelConfig across all YOLO model variants to replace individual default configurations.
  • 🔄 Updated the app version in Info.plist from 83 to 85.

🎯 Purpose & Impact

  • 🚀 Performance Optimization: The experimental engine setting may improve ML model performance and efficiency.
  • 🧹 Code Consistency: Simplifies and standardizes how ML models are configured within the app, making maintenance easier.
  • 📱 Version Increment: Ensures users can differentiate the new app version with the improvements.

@UltralyticsAssistant UltralyticsAssistant added bug Something isn't working embedded Pertaining to IOT or low-power devices enhancement New feature or request labels Jan 29, 2025
@UltralyticsAssistant
Copy link
Member

👋 Hello @john-rocky, thank you for submitting an ultralytics/yolo-ios-app 🚀 PR! To ensure a seamless integration of your work, please review the following checklist:

  • Define a Purpose: Clearly explain the purpose of your fix or feature in your PR description, including relevant context about the macOS 15 bug and how disabling experimentalMLE5EngineUsage resolves the issue. If applicable, link to any related issues. Ensure your commit messages are precise and adhere to the project's conventions.
  • Synchronize with Source: Confirm your PR is synchronized with the ultralytics/yolo-ios-app main branch. If it's behind, please update by clicking the 'Update branch' button or merging main locally via git pull origin main && git merge main.
  • Ensure CI Checks Pass: Double-check to ensure that all Ultralytics Continuous Integration (CI) checks have passed successfully. 🚦 If a check fails, please investigate and resolve the issue promptly.
  • Update Documentation: If your changes affect app behavior, update any relevant documentation, such as usage guides, developer setup instructions, or a changelog. 📝 See Ultralytics Docs for more details.
  • Add Tests: If warranted, include or update tests to validate the new or modified functionality. Be sure all tests are passing before marking the PR as ready for review. 📊
  • Sign the CLA: If this is your first contribution, ensure you've signed our Contributor License Agreement (CLA). Add a comment stating, "I have read the CLA Document and I sign the CLA" to confirm.
  • Minimize Changes: Ensure your changes are concise and specific to the bug fix for experimentalMLE5EngineUsage. As Bruce Lee said, "It is not daily increase but daily decrease, hack away the unessential."

If you're addressing a bug or unexpected behavior, please ensure you provide a Minimum Reproducible Example (MRE) for testing. This will help us verify and better understand the issue you're fixing. 😊⚡

For more guidance, refer to our Contributing Guide. An Ultralytics engineer will review your changes and assist shortly. Let us know in a comment if you have further questions or concerns! 🚀

@john-rocky john-rocky closed this Feb 1, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working embedded Pertaining to IOT or low-power devices enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants