YOLOv10-LiteRT on Android for Object Detection

This repository is an implementation of converting the YOLOv10 object detection model to LiteRT (.tflite) format and deploy it on Android using Google AI Edge for on-device inference.

Pipeline

Demo Output

Steps to run:

1. Clone the repository on your local machine.
2. Open the Colab notebook to export YOLOv10-N to LiteRT (TF Lite) format.
3. Download the LiteRT model on your local machine and copy it in the assets folder.
4. Open the Android_App project in Android Studio and let it build.
5. Install the app on your phone and enjoy real-time object detection on Android.

Resources

1. Colab Notebook:
2. Medium Blog for step-by-step implementation
3. Official documentation of YOLOv10 by Ultralytics
4. Google AI Edge LiteRT

Acknowledgment

This project was developed during Google's ML Developer Programs AI Sprint. Thanks to the MLDP team for providing Google Cloud credits to support this project.