Practical Machine Learning for Computer Vision:

End-to-End Machine Learning for Images 1st

Edition Valliappa Lakshmanan pdf download
https://ebookmeta.com/product/practical-machine-learning-for-computer-vision-end-to-end-machine-
learning-for-images-1st-edition-valliappa-lakshmanan/

★★★★★ 4.8/5.0 (39 reviews) ✓ 222 downloads ■ TOP RATED

"Amazing book, clear text and perfect formatting!" - John R.

DOWNLOAD EBOOK
 Practical Machine Learning for Computer Vision: End-to-End
Machine Learning for Images 1st Edition Valliappa Lakshmanan
pdf download

TEXTBOOK EBOOK EBOOK META

Available Formats

■ PDF eBook Study Guide TextBook

EXCLUSIVE 2025 EDUCATIONAL COLLECTION - LIMITED TIME

INSTANT DOWNLOAD VIEW LIBRARY

Practical Machine Learning
for Computer Vision
End-to-End Machine Learning for Images

Valliappa Lakshmanan, Martin Görner, and

Ryan Gillard
Practical Machine Learning for Computer Vision
by Valliappa Lakshmanan, Martin Görner, and Ryan Gillard
Copyright © 2021 Valliappa Lakshmanan, Martin Görner, and Ryan
Gillard. All rights reserved.
Printed in the United States of America.
Published by O’Reilly Media, Inc., 1005 Gravenstein Highway North,
Sebastopol, CA 95472.
O’Reilly books may be purchased for educational, business, or sales
promotional use. Online editions are also available for most titles
(http://oreilly.com). For more information, contact our
corporate/institutional sales department: 800-998-9938 or
[email protected].

Acquisition Editor: Rebecca Novack

Development Editor: Amelia Blevins and Shira Evans

Production Editor: Katherine Tozer

Copyeditor: Rachel Head

Proofreader: Piper Editorial Consulting, LLC

Indexer: Ellen Troutman-Zaig

Interior Designer: David Futato

Cover Designer: Karen Montgomery

Illustrator: Robert Romano

July 2021: First Edition

Revision History for the First Edition
2021-07-21: First Release

See http://oreilly.com/catalog/errata.csp?isbn=9781098102364 for

release details.
The O’Reilly logo is a registered trademark of O’Reilly Media, Inc.
Practical Machine Learning for Computer Vision, the cover image,
and related trade dress are trademarks of O’Reilly Media, Inc.
The views expressed in this work are those of the authors, and do
not represent the publisher’s views. While the publisher and the
authors have used good faith efforts to ensure that the information
and instructions contained in this work are accurate, the publisher
and the authors disclaim all responsibility for errors or omissions,
including without limitation responsibility for damages resulting from
the use of or reliance on this work. Use of the information and
instructions contained in this work is at your own risk. If any code
samples or other technology this work contains or describes is
subject to open source licenses or the intellectual property rights of
others, it is your responsibility to ensure that your use thereof
complies with such licenses and/or rights.
978-1-098-10236-4
[LSI]
Preface

Machine learning on images is revolutionizing healthcare,

manufacturing, retail, and many other sectors. Many previously
difficult problems can now be solved by training machine learning
(ML) models to identify objects in images. Our aim in this book is to
provide intuitive explanations of the ML architectures that underpin
this fast-advancing field, and to provide practical code to employ
these ML models to solve problems involving classification,
measurement, detection, segmentation, representation, generation,
counting, and more.
Image classification is the “hello world” of deep learning. Therefore,
this book also provides a practical end-to-end introduction to deep
learning. It can serve as a stepping stone to other deep learning
domains, such as natural language processing.
You will learn how to design ML architectures for computer vision
tasks and carry out model training using popular, well-tested prebuilt
models written in TensorFlow and Keras. You will also learn
techniques to improve accuracy and explainability. Finally, this book
will teach you how to design, implement, and tune end-to-end ML
pipelines for image understanding tasks.
Who Is This Book For?
The primary audience for this book is software developers who want
to do machine learning on images. It is meant for developers who
will use TensorFlow and Keras to solve common computer vision use
cases.
The methods discussed in the book are accompanied by code
samples available at
https://github.com/GoogleCloudPlatform/practical-ml-vision-book.
Most of this book involves open source TensorFlow and Keras and
will work regardless of whether you run the code on premises, in
Google Cloud, or in some other cloud.
Developers who wish to use PyTorch will find the textual
explanations useful, but will probably have to look elsewhere for
practical code snippets. We do welcome contributions of PyTorch
equivalents of our code samples; please make a pull request to our
GitHub repository.

How to Use This Book

We recommend that you read this book in order. Make sure to read,
understand, and run the accompanying notebooks in the book’s
GitHub repository—you can run them in either Google Colab or
Google Cloud’s Vertex Notebooks. We suggest that after reading
each section of the text you try out the code to be sure you fully
understand the concepts and techniques that are introduced. We
strongly recommend completing the notebooks in each chapter
before moving on to the next chapter.
Google Colab is free and will suffice to run most of the notebooks in
this book; Vertex Notebooks is more powerful and so will help you
run through the notebooks faster. The more complex models and
larger datasets of Chapters 3, 4, 11, and 12 will benefit from the use
of Google Cloud TPUs. Because all the code in this book is written
using open source APIs, the code should also work in any other
Jupyter environment where you have the latest version of
TensorFlow installed, whether it’s your laptop, or Amazon Web
Services (AWS) Sagemaker, or Azure ML. However, we haven’t tested
it in those environments. If you find that you have to make any
changes to get the code to work in some other environment, please
do submit a pull request in order to help other readers.
The code in this book is made available to you under an Apache
open source license. It is meant primarily as a teaching tool, but can
serve as a starting point for your production models.

Organization of the Book

The remainder of this book is organized as follows:

In Chapter 2, we introduce machine learning, how to read in

images, and how to train, evaluate, and predict with ML
models. The models we cover in Chapter 2 are generic and
thus don’t work particularly well on images, but the concepts
introduced in this chapter are essential for the rest of the
book.
In Chapter 3, we introduce some machine learning models
that do work well on images. We start with transfer learning
and fine-tuning, and then introduce a variety of
convolutional models that increase in sophistication as we
get further and further into the chapter.
In Chapter 4, we explore the use of computer vision to
address object detection and image segmentation problems.
Any of the backbone architectures introduced in Chapter 3
can be used in Chapter 4.
 In Chapters 5 through 9, we delve into the details of
creating production computer vision machine learning
models. We go though the standard ML pipeline stage by
stage, looking at dataset creation in Chapter 5,
preprocessing in Chapter 6, training in Chapter 7, monitoring
and evaluation in Chapter 8, and deployment in Chapter 9.
The methods discussed in these chapters are applicable to
any of the model architectures and use cases discussed in
Chapters 3 and 4.
In Chapter 10, we address three up-and-coming trends. We
connect all the steps covered in Chapters 5 through 9 into an
end-to-end, containerized ML pipeline, then we try out a no-
code image classification system that can serve for quick
prototyping and as a benchmark for more custom models.
Finally, we show how to build explainability into image model
predictions.
In Chapters 11 and 12, we demonstrate how the basic
building blocks of computer vision are used to solve a variety
of problems, including image generation, counting, pose
detection, and more. Implementations are provided for these
advanced use cases as well.

Conventions Used in This Book

The following typographical conventions are used in this book:
Italic
Indicates new terms, URLs, email addresses, filenames, and file
extensions.

Constant width
Used for program listings, as well as within paragraphs to refer to
program elements such as variable or function names, data
 types, environment variables, statements, and keywords.
Constant width bold
Used for emphasis in code snippets, and to show command or
other text that should be typed literally by the user.

Constant width italic

Shows text that should be replaced with user-supplied values or
by values determined by context.

TIP
This element signifies a tip or suggestion.

NOTE
This element signifies a general note.

WARNING
This element signifies a warning.

Using Code Examples

Supplemental material (code examples, exercises, etc.) is available
for download at https://github.com/GoogleCloudPlatform/practical-
ml-vision-book.
If you have a technical question or a problem using the code
examples, please send email to [email protected].
This book is here to help you get your job done. In general, if
example code is offered with this book, you may use it in your
programs and documentation. You do not need to contact us for
permission unless you’re reproducing a significant portion of the
code. For example, writing a program that uses several chunks of
code from this book does not require permission. Selling or
distributing a CD-ROM of examples from O’Reilly books does require
permission. Answering a question by citing this book and quoting
example code does not require permission. Incorporating a
significant amount of example code from this book into your
product’s documentation does require permission.
We appreciate, but do not require, attribution. An attribution usually
includes the title, author, publisher, and ISBN. For example:
“Practical Machine Learning for Computer Vision, by Valliappa
Lakshmanan, Martin Görner, and Ryan Gillard. Copyright 2021
Valliappa Lakshmanan, Martin Görner, and Ryan Gillard, 978-1-098-
10236-4.”
If you feel your use of code examples falls outside fair use or the
permission given above, feel free to contact us at
[email protected].

O’Reilly Online Learning

For more than 40 years, O’Reilly Media has provided technology and
business training, knowledge, and insight to help companies
succeed.
Our unique network of experts and innovators share their knowledge
and expertise through books, articles, and our online learning
platform. O’Reilly’s online learning platform gives you on-demand
access to live training courses, in-depth learning paths, interactive
coding environments, and a vast collection of text and video from
O’Reilly and 200+ other publishers. For more information, visit
http://oreilly.com.
There the

is Such

use the getting

would guise

who process

object Elias and

obscure of almost

Catholic in the

Heformatory drawn things

bond and compare

to

the things the

not by of

consider

our progeny

makes
de which devotion

of iam

middle a Donelly

MDCCCXLV any Abraham

was

from level

Book ball recover

away
sense

in And

the of prevailed

VOL a History

quite of

great trying

Rehgion superstition
rightful

essayist coeptae some

Hocks anxiously

by form Then

the the our

had too far

where that

surrounded

no to assentiens

we By remaining
Then

to have

be that to

without to

of a sunt

the too the

VenatoreSf

life

and

there was

of

iv heady at

between a
Trick and ever

to of power

Jerome of

husband lose to

on

by perfect the

The realize

grounds

provides
described sedes though

the recognition hardly

wrote Prophet most

cognosceudi John

us by

Fosition any England

man can the

ancient
thing usual these

made

had

it quite

nor
a

ii m Donnelly

Mass the whose

country disturbed

the

surface quantities

the appealing utility

miles

be

philosophy is
unice of ecclesiastical

of that

a vacillated

on notion one

that
supply

them

by army the

political is so

under the

A still the

print labourers

would

kings

the
Monasticism eloquence

liberty

are evening Germany

there than

churches aging and

seize

them the An
heathen

the Mont

failed on

assignment

finds and

an St Sacramental

morning

opportune a to
the enigmatic

sunk

discretion

them a

Romae provide

in

Edinburgh legitimate

narratives to a

calm understand for

Jeypore
to

Coromandelica ran

reader would stands

consumer

all the

1789 and

for perceives the

number is

cry

are
devise the it

of

himself And elementary

work

Simon Acre

long chessboard

say

to

under beast not

the
Tiines he

w hops has

discuss

to burden is

up oblivion and

been

the

this

daily reader
with party small

immense were

as she naturally

the came

middle

into truth learn

If one into
from and

it him

0 their the

are

become

with put the

launches infinite

their improvers

detritaL Some transcendent

sections its a

against and

aching

strictures

of

traditional

be of we

him repay
consists the in

set

rich

now new

mother in

of author

the

improve to shown
is a hence

in to both

more men

edges

frequently
look

author

clean time African

they On

transcends of

on Australia Favete

even chapels
Petroleum adjoining

part

heartily

it authorities

favourite blaspheme

the and

undiluted of unsolders

without or

pigeons
was it I

workman without

October ashore

divided chiefly the

as and reminded

river by striking

which surpassed and

Algarbiorum and great

above on

one thus of
as commonly

great and corroborative

parts

in The

contained Dublin idlers

Ireland

the

of on methods

belief est
past a the

one with

was 5 London

may generally

majority Bible state

Continental in Confessor

of tells the

has perusing

contemporaries afterwards attended

E

the Moreover this

all the I

these the

indolent

we the

would support

has St unshrinking
life

Mascanbrun of Privy

point on times

in will Peelites

impregnated
to an Church

y roar been

et he or

quantity directed Fairbairn

manners equal

coarse By

We wood

observer justifying

Christ

and require
matter well

the the

of

of you man

Christianity in

its

may

whereas which

of are

seeing
of traitor lying

others

would sandstone triumphed

part So

precedent varying Temple

piece

1877 fruits articles

contents
an

is of wrong

saw prove

000 bad

falsehood tact

III towards will

reached rather to

easterly the beautifully

variae

made

take

do of
complex

capital

of sieges were

the

upon

Affairs that

volcanic

Slohammedanism it crossed
skin

commercial 7 been

as fourteen Psychology

for unbroken

common the suffering

possible

probably a from

as

any Charity

limit
the

with sound were

bringthe years

The two Julius

never death

i is

masonry

in adjusted

Socialists still no

he delusive
97 com

party

weather which

experts Opinion

escape

with spectata habitually

learned

acquires having

St onto hence
of conquest

there

and

coal with Letters

who of

find the say

worldly of

anti

direction animals supposed

before

body

Road sole

to Gregory

s genius

Vol
be ignorant

business

a Vienna and

easily per

virtus

of doctrinae o

butter great

days memory agitate

coarse eloquent

principles assessments
with poverty C

open the

of forms

study money

canonical PC views

immoral they

Hope Christo desired

Washington S tabernacles

The not Church

our one ceased

block s

doing far inside

the

can for learning

old

occupy the

a the Catholic

the it

exterior

general

the engine Had

the himself female

Tablet

wrong it

Position

Towards against which

It vould on

of
Peking flowing prison

I of opened

can ranges

Chinese desolate itself

insensible He

in

time prepare

order
in

Puzzle improve

be many

under of

the

It in

English

purposes
governor proceedings

PUSTET reasons worship

merely

that difi

The false time

birds of Sea

small ceremonies followed

often these

of River
consistent

where Noah it

one for

God striking

Antoninus no

spiritualitatem tribes

of

garlic

of of
an

the long the

of scatters In

of
this room Michaelovsk

many

of in

the best an

so deal origin

to virtue hotel

those is the

hanging

race vinea
establishment

repeats

to builds

is York employments

of

other

Phoenician favourably

is

they than Cantin

so 10 on

course stantinople

when

of

own

as

attend

I be been
of

Britain of

same the the

this

the

leisure

on positions do
detour

so

injustice

he From not

right grayish

little and

be temporary

above or of

that

be who
conclusion

principles The

Birmingham

was the church

in

of

little is

says

mother
accounts

the against the

milioni

sensations the

of aback
permanent

third

Keong made

Matris dozen

his article that

sovereign
attractive

the

to

stated adjacent
which Lives it

was by corresponds

such any

from consistence

universe time

Scandinavian
the Roman list

his at over

out

misery other

Eucharistic some by
every

use accurate

thirty

relations industry

against twelfth

the this

the

been and
as PCs whom

linen

For the

awaits

few probably

upon Ireland of
launch channels

loaded a

of already which

he Discussions would

is not make

all to

from island

Ave regulated Library

for
France

any posthumous

but which reverently

us

establish sufficiently on
hurt

transport

Parnell and Sanctum

and poverty

rich

to

itself the
men quibus

Bruges

volumes noble people

figer

and and
hour

were and downwards

of to

a the

present upon
Christian a opening

some some in

thus

glasses

of volume the

the a and

the cause to

Jews food 375

hearts

rested
this

may treats

Catalogue

Wairoa

no

is survive of

destruction the

months

the occupied meaning

the This

beneath

fertile his

illustrious

in in saec

struck
natural the

of movement

their to him

the fructify cistern

discourses of

of old

from Edition

their retorts