July 2018
Intermediate to advanced
310 pages
8h 21m
Chinese
Content preview from 深度学习入门 : 基于Python的理论与实现
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
第 8章 深度学习
248
实践中经常会灵活应用使用ImageNet 这个巨大的数据集学习到的权
重数据，这称为迁移学习，将学习完的权重（的一部分）复制到其他
神经网络，进行再学习（fine tuning）。比如，准备一个和 VGG 相同
结构的网络，把学习完的权重作为初始值，以新数据集为对象，进
行再学习。迁移学习在手头数据集较少时非常有效。
8.3
深度学习的高速化
随着大数据和网络的大规模化，深度学习需要进行大量的运算。虽然到
目前为止，我们都是使用
CPU
进行计算的，但现实是只用
CPU
来应对深度
学习无法令人放心。实际上，环视一下周围，大多数深度学习的框架都支持
GPU（
Graphics Processing Unit
），可以高速地处理大量的运算。另外，最
近的框架也开始支持多个
GPU
或多台机器上的分布式学习。本节我们将焦
点放在深度学习的计算的高速化上，然后逐步展开。深度学习的实现在8.1
节就结束了，本节要讨论的高速化（支持
GPU
等）并不进行实现。
8.3.1
需要努力解决的问题
在介绍深度学习的高速化之前，我们先来看一下深度学习中什么样的处
理比较耗时。图8
-
14 中以
AlexNet
的
forward
处理为对象，用饼图展示了各
层所耗费的时间。
从图中可知，
AlexNex
中，大多数时间都被耗费在卷积层上。实际上，
卷积层的处理时间加起来占
GPU
整体的95
%
，占
CPU
整体的89
%
！因此，
如何高速、高效地进行卷积层中的运算是深度学习的一大课题。虽然图8
-
14
是推理时的结果，不过学习时也一样，卷积层中会耗费大量时间。 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.