fixed bug in translate coords for detectImage func

[yangga]

There is a bug in detectImage function on iOS devices where the x coordinate is a bit weird. This PR is to fix that. And also remove unnecessary print.

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Improves object detection bounding box calculations for iOS devices in the YOLO Flutter app.

📊 Key Changes

• Removed unnecessary print statements used for debugging.
• Adjusted transformation calculations for bounding boxes on iPhones and iPads to improve precision.

🎯 Purpose & Impact

• Cleaner Code: By removing print statements, the code is less cluttered and more efficient.
• Enhanced Accuracy: Adjustments to bounding box transformations ensure better alignment on screens, enhancing object detection accuracy across different iOS devices. This leads to a more reliable user experience when using the app for detecting objects. 📱✅

[UltralyticsAssistant]

👋 Hello @yangga, thank you for submitting an ultralytics/yolo-flutter-app 🚀 pull request! This is an automated response, but an Ultralytics engineer will assist you soon. In the meantime, here are a few steps to help ensure your contribution is ready for review:

• ✅ Define a Purpose: Clearly detail the goal of your bug fix in the PR description. Linking directly to any related issues would be beneficial. Your commit messages should be precise and adhere to the project's conventions.
• ✅ Synchronize with Source: Double-check that your pull request aligns with the latest main branch of ultralytics/yolo-flutter-app. If it's outdated, update by clicking 'Update branch' or executing git pull and git merge main on your local repository.
• ✅ Ensure CI Checks Pass: All our Continuous Integration (CI) checks should pass without issues. If any fail, please address these promptly.
• ✅ Update Documentation: Make sure to adjust the documentation if your bug fix involves changes that impact the behavior or use of the software.
• ✅ Add Tests: If possible, include or edit tests that cover your changes, ensuring that all tests pass successfully.
• ✅ Sign the CLA: Confirm that you have signed our Contributor License Agreement if this is your first contribution. Write "I have read the CLA Document and I sign the CLA" in a new comment to complete this.
• ✅ Provide an MRE: If not already included, provide a Minimum Reproducible Example to demonstrate the bug and how your changes address it. This helps expedite the review process. 🛠️

For more detailed guidance, our Contributing Guide is available as a resource. Feel free to ask questions by leaving a comment directly on this PR. Thanks again for contributing to Ultralytics and helping us make our projects better! 🎉

[glenn-jocher]

@yangga thank you for the PR! Do you think we might need this change in https://github.com/ultralytics/yolo-ios-app as well?

@john-rocky FYI.

[yangga]

@yangga thank you for the PR! Do you think we might need this change in https://github.com/ultralytics/yolo-ios-app as well?

@john-rocky FYI.

@glenn-jocher No problem. I'm not sure that https://github.com/ultralytics/yolo-ios-app needs this change. (even I couldn't find the function such as detecting image). But if that repos has this change, it gonna be helpful for someone. Thanks.

[john-rocky]

@glenn-jocher @yangga
The modified code works correctly in cases where the aspect ratio of the input image and the display image match, such as single image input.
However, in cases where the input camera image and the display size are different, such as real-time camera inference, the existing code works better. Therefore, I think the existing code is more suitable for Yolo-iOS-app, which performs real-time inference.