TensorFlow Lite: On-Device Machine Learning Framework

被引：0
|
作者：
Li S. [1 ]
机构：
[1] Google TensorFlow Team, Beijing
来源：
Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2020年 / 57卷 / 09期
关键词：
IoT; Machine learning; Mobile; On-device machine learning (ODML); TensorFlow; TensorFlow Lite; TFLite;
D O I：
10.7544/issn1000-1239.2020.20200291
中图分类号：
学科分类号：
摘要：
TensorFlow Lite (TFLite) is a lightweight, fast and cross-platform open source machine learning framework specifically designed for mobile and IoT. It's part of TensorFlow and supports multiple platforms such as Android, iOS, embedded Linux, and MCU etc. It greatly reduces the barrier for developers, accelerates the development of on-device machine learning (ODML), and makes ML run everywhere. This article introduces the trend, challenges and typical applications of ODML; the origin and system architecture of TFLite; best practices and tool chains suitable for ML beginners; and the roadmap of TFLite. © 2020, Science Press. All right reserved.
引用
收藏
页码：1839 / 1853
页数：14
相关论文
共 72 条
  • [1] TensorFlow Lite: ML for mobile and IoT
  • [2] Abadi M, Barham P, Chen Jianmin, Et al., TensorFlow: A system for large-scale machine learning, Proc of the 12th USENIX Symp on Operating Systems Design and Implementation (OSDI 2016), pp. 265-283, (2016)
  • [3] TensorFlow: An end-to-end open source machine learning platform
  • [4] TensorFlow open-source project in github
  • [5] TensorFlow Lite open-source project in github
  • [6] Dea S O., Number of smartphone users worldwide from 2016 to 2021
  • [7] Lueth K L., State of the IoT 2018: Number of IoT devices now at 7B-Market accelerating
  • [8] CoreML: Integrate machine learning models into your app
  • [9] Tencent NCNN: High-performance neural network inference framework optimized for the mobile platform
  • [10] Xiaomi, Xiaomi MACE: A deep learning inference framework optimized for mobile heterogeneous computing platforms
12345678