Skip to Content
机器学习实战:基于Scikit-Learn、Keras 和TensorFlow (原书第2 版)
book

机器学习实战:基于Scikit-Learn、Keras 和TensorFlow (原书第2 版)

by Aurélien Géron
October 2020
Intermediate to advanced
693 pages
16h 26m
Chinese
China Machine Press
Content preview from 机器学习实战:基于Scikit-Learn、Keras 和TensorFlow (原书第2 版)
428
|
第
14
章
很难进行公平的比较,而这种比较对大多数人都有用,并且可以持续有效几个月以上。
因此我们可以通过在物体周围绘制边界框来定位对象。但是也许你想变得更加精确。让
我们看看如何来下降到像素级别。
14.10 语义分割
在语义分割中,每个像素根据其所属物体的类别(例如,道路、汽车、行人、建筑物等)
进行分类,如图 14-26 所示。请注意,没有区分相同类别的不同物体。例如分割图像右
侧的所有自行车都变成了一大块像素。此任务的主要困难在于,当图像通过常规的 CNN
时,它们会逐渐失去其空间分辨率(由于步幅大于 1 的层),因此常规的 CNN 可能最终
会知道在图像的左下方某处有一个人,但不会比这更精确了。
就像物体检测一样,有许多种方法可以解决此问题,有些方法非常复杂。但是,Jonathan
Long 等人在 2015 年的论文中提出了一个我们之前讨论过的相当简单的解决方法。作
者首先采用经过预先训练的 CNN,然后将其转换为 FCN。CNN 对输入图像应用的总步
幅为 32(如果所有步幅的总和都大于 1),则意味着最后一层输出的特征图是输入图像的
1/32。这显然太粗糙了,因此他们添加了一个单独的上采样层来把分辨率乘以 32。
图 14-26:语义分割
有几种解决方法可用于上采样(增加图像的大小),例如双线性插值,但仅在
×
4 或
×
8
时才有效。取而代之的是,他们使用转置的卷积层
注 33
:等效于首先插入空的行和列(充
满零)来拉伸图像,然后执行常规的卷积(见图 14-27)。另外,有些人更喜欢将其视为 ...
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

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’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.
Head of Cybersecurity
QuotationMarkI 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.
Field Engineer
QuotationMarkI’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.
Data Platform Tech Lead
QuotationMarkI'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.
Mark W.
Embedded Software Engineer

You might also like

算法技术手册(原书第2 版)

算法技术手册(原书第2 版)

George T.Heineman, Gary Pollice, Stanley Selkow
管理Kubernetes

管理Kubernetes

Brendan Burns, Craig Tracey

Publisher Resources

ISBN: 9787111665977