Scholarlink

This paper introduces YOLO-OptiMob, a comprehensive pipeline for optimizing YOLO11 models for deployment on edge devices. The process begins with creating and preprocessing a custom dataset featuring seven object classes: bike, car, cat, dog, person, handbag, and water bottle. The YOLO11 model is trained on this dataset and optimized using L1 unstructured pruning, with rates of 30%, 40%, and 50% evaluated. Based on the results, a 40% pruning rate was selected as it offered the best balance between model size reduction and accuracy retention. Post-training INT8 quantization further compresses the model, reducing its size from 11.4 to 2.5 MB. The optimized model is then converted into TensorFlow Lite (TFLite) format, ensuring compatibility with Android-based edge devices. This work presents a practical pipeline for efficiently adapting YOLO11 to resource-constrained environments, achieving significant size reduction while maintaining high detection accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

YOLO-OptiMob: A Pipeline for Optimizing YOLO11 Models for Edge Deployment

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anish M. Bhat,
  • Aditya M. Eeragond,
  • Jayant Nandyal,
  • Aryan Shetty,
  • Sneha Varur,
  • Channabasappa Muttal

摘要

This paper introduces YOLO-OptiMob, a comprehensive pipeline for optimizing YOLO11 models for deployment on edge devices. The process begins with creating and preprocessing a custom dataset featuring seven object classes: bike, car, cat, dog, person, handbag, and water bottle. The YOLO11 model is trained on this dataset and optimized using L1 unstructured pruning, with rates of 30%, 40%, and 50% evaluated. Based on the results, a 40% pruning rate was selected as it offered the best balance between model size reduction and accuracy retention. Post-training INT8 quantization further compresses the model, reducing its size from 11.4 to 2.5 MB. The optimized model is then converted into TensorFlow Lite (TFLite) format, ensuring compatibility with Android-based edge devices. This work presents a practical pipeline for efficiently adapting YOLO11 to resource-constrained environments, achieving significant size reduction while maintaining high detection accuracy.