O'Reilly、Cloudera 主办
Make Data Work
2017年7月12-13日:培训
2017年7月13-15日:会议
北京,中国

终端设备上的机器学习: Android设备上的TensorFlow (On-device machine learning: TensorFlow on Android)

This will be presented in English.

Yufeng Guo (Google)
13:10–13:50 Saturday, 2017-07-15
AI应用 (AI applications), 英文讲话 (Presented in English)
地点: 报告厅(Auditorium) 观众水平 (Level): Beginner

必要预备知识 (Prerequisite Knowledge)

A basic understanding of machine learning

您将学到什么 (What you'll learn)

Learn how to create a custom image classifier with very little code and understand the trade-offs and considerations that need to be made when making such a system

描述 (Description)

机器学习传统上只能在服务器和高性能计算机上执行,但是能在移动设备上进行机器学习是非常有价值的,而TensorFlow内置了与移动平台的兼容性。 在本议题中,我们将在移动设备上运用深度学习模型来做运行在本地设备的预测。

首先,您将了解为什么在移动设备上拥有机器学习能力是有用的。 接下来,我们将介绍一些可用的图像分类技术。 最后,我们将使用TensorFlow实现针对自定义数据集的图像分类的机器学习模型。

我们还将讨论一些需要考虑的权衡和部署考量。 你在结束时会学到足够开始实现你自己的深度学习解决方案的知识。


Machine learning has traditionally been performed only on servers and high-performance machines, but on-device machine learning on mobile devices can be very valuable. Yufeng Guo uses TensorFlow, which has built-in compatibility with mobile platforms, to implement a deep learning model for image classification on an Android device, tailored to a custom dataset.

Yufeng begins by explaining why it’s useful to have machine learning capabilities on mobile devices before covering some of the image classification techniques available. Yufeng concludes by demonstrating how to use TensorFlow to implement a machine learning model for image classification that is tailored to a custom dataset. Along the way, Yufeng also discusses some of the trade-offs and deployment considerations needed. You’ll leave ready to get started on your own mobile deep learning solutions.

Photo of Yufeng Guo

Yufeng Guo

Google

Yufeng Guo is a developer advocate for the Google Cloud Platform, where he is trying to make machine learning more understandable and usable for all. He enjoys hearing about new and interesting applications of machine learning, so be sure to share your use case with him on Twitter.

联系OReillyData

关注OReillyData微信号获取最新会议信息并浏览前沿数据文章。

WeChat QRcode

 

Stay Connected Image 1
Stay Connected Image 3
Stay Connected Image 2

阅读关于大数据的最新理念。

ORB Data Site