Bounding box on a wrong located on Mi Pad 6s pro interface. Android device

[Phat-P]

Search before asking

• I have searched the HUB issues and found no similar bug report.

HUB Component

No response

Bug

Environment

No response

Minimal Reproducible Example

No response

Additional

No response

[UltralyticsAssistant]

👋 Hello @Phat-P, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:

• Quickstart. Start training and deploying YOLO models with HUB in seconds.
• Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
• Projects: Creating and Managing. Group your models into projects for improved organization.
• Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
• Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
• Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
  • iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
  • Android. Explore TFLite acceleration on mobile devices.
• Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.

It seems you've reported a visual issue with bounding boxes on the Mi Pad 6s Pro Android interface. If this is a 🐛 Bug Report, please provide a minimum reproducible example (MRE) to help us investigate the issue effectively. For example:

1. The specific model used (e.g., YOLOv5, YOLOv8).
2. Steps to reproduce the problem, including dataset information or screenshots beyond the one already provided.
3. Your app version and environment details.

An Ultralytics engineer will review your report and assist you as soon as possible! Thank you for your patience and for helping us improve HUB 😊

[pderrenger]

@Phat-P hello!

It looks like you're experiencing an issue with the bounding box placement on your Mi Pad 6s Pro when using the Ultralytics HUB app. Thanks for bringing this to our attention, and including the screenshot, this helps a lot!

A few things that might help resolve this:

1. App Version: Ensure you're running the latest version of the Ultralytics HUB app from the Google Play Store. Android - Ultralytics YOLO Docs

2. Model Compatibility: Double-check that the model you are using is optimized for mobile deployment. Quantization can affect model accuracy, especially INT8. Android - Ultralytics YOLO Docs

3. Image Resolution Differences: Bounding box inaccuracies can be caused by differences between the image resolution that the model was trained on, and the input image resolution.

The Ultralytics team is dedicated to improving the user experience and resolving bugs. The YOLO community is also a great resource.