Python深度学习实践：从Theano到TensorFlow与Keras

5星 · 超过95%的资源需积分: 9 201 浏览量更新于2024-07-19 收藏 4.75MB PDF 举报

"《Deep Learning with Python》是Jason Brownlee所著的一本书，专注于使用Python、Theano和TensorFlow通过Keras开发深度学习模型。这本书适合初学者，以实践为主，理论介绍较少，适合用于入门和巩固基础知识。" 在深入讨论Python深度学习之前，我们先了解一些基本概念。深度学习是一种人工智能技术，它模拟人脑神经网络的工作原理，通过大量数据进行学习，从而实现诸如图像识别、语音识别和自然语言处理等复杂任务。《Deep Learning with Python》一书以错误的深度学习方法为引子，强调了正确理解和应用深度学习的重要性。书中首先介绍了Theano，这是一个Python库，用于构建和求解多维数学表达式，特别是用于机器学习中的张量操作。Theano提供了高效的数值计算，并支持GPU加速。安装Theano后，书中通过一个简单的例子展示了如何使用它来执行基本的数学运算，并提到了一些扩展和包装Theano的工具，以及更多的学习资源。接下来，书中转向了TensorFlow，这是由Google开发的开源库，同样用于数值计算和大规模机器学习。TensorFlow以其灵活性和可部署性而闻名，支持多种平台。书中详细解释了如何安装TensorFlow，并引导读者通过编写第一个TensorFlow程序来理解其工作原理。此外，还介绍了如何构建更复杂的深度学习模型，以展示TensorFlow的潜力。然后，书中的重点转向了Keras，这是一个高级神经网络API，运行在Theano和TensorFlow之上，简化了模型构建过程。Keras的设计目标是快速实验，使得研究人员能够快速迭代想法。书中阐述了Keras的基本概念，包括如何安装和启动，以及如何利用Keras构建和训练简单的神经网络模型。《Deep Learning with Python》提供了一个友好的起点，引导读者进入深度学习的世界。无论你是初学者还是有经验的开发者，都可以从中受益。对于新手，它提供了足够的实践机会，而对于资深开发者，它可以作为一个快速参考和复习工具，帮助回顾和巩固深度学习的基础知识。尽管这本书在理论深度上可能有限，但它的实用性使其成为Python深度学习领域的一个宝贵资源。

1.4. Requirements For This Book 6

1.3.6 Part 6: Recurrent N eur al Networks

In this part you will recei ve a crash course in the dominant model for data with a sequence or

time component and how you can best exploit th e capa b i l i ti e s of the Keras API for your own

projects. This part of the book includes the following lessons:

Crash Course In Recurrent Neural Ne tworks.

Multilayer Perceptron Models for Time Series Problems.

LSTM Models for Time Series Problems.

Understanding State in LSTM Models for Sequence Prediction.

The best way to learn about t h i s com p l e x type of neural network model i s t o apply it.

You will work through two larger projects and apply RNN to sequence classiﬁcation and text

generation.

Project: Sequence Classiﬁcation of Movie Reviews.

Project: Text Generation With Alice in Wonderl a n d .

After completing the lessons and project s in this part you will have the skills and the

conﬁdence of complete and working templates and recipes to tackle your own deep learning

projects using recurrent neural networks.

1.3.7 Conclusions

The book concludes with some resources that you can use to learn more information about a

speciﬁc topi c or ﬁnd help if you need it as you start to d evelop and evaluate your own deep

learning models.

1.3.8 Recipes

Building up a catalog of code recipes is an im portant part of your deep learning journey. Each

time you learn about a new technique or new problem type, you should write up a short co de

recipe that demonstrates it. This will give you a starting point to use on your next deep learning

or machine learning project.

As pa r t of this book you will receive a catal o g of deep learning recipes. This includes recipes

for all of the lessons presented in this book, as well as the complete code for all of the projects.

You are strongly encouraged to add to and build upon this catalog of recipes as you expand

your use and knowledge of deep learning in Python.

1.4 Requirements For This Book

1.4.1 Python and SciPy

You do not need to be a Python exp ert, but it would be helpful if you knew how to install and

setup Python and SciPy. The lessons and projects assume that you have a Python and SciPy

1.5. Your Outcomes From Reading This Book 7

environment available. This may be on your workstation or laptop, it may be i n a VM or a

Docker instance that you run, or it may be a server instance that you can conﬁgure in the cloud

as taught in Part II of this book.

Technical Requirements

:Thetechnicalrequirementsforthecodeandtutorialsinthis

book are as follows:

Python version 2 or 3 i n st all ed . This book was d eveloped using Python version 2.7. 11.

SciPy and NumPy instal l ed . This book was developed with Sci Py version 0.17.0 and

NumPy version 1.11. 0 .

Matplotlib installed. This book was developed with Matplotlib version 1.5.1.

Pandas installed. This book was developed with Pandas version 0.18.0.

scikit-learn installed. This book was developed with scikit-learn 0.17.1.

You do not need to match the version exactly, but if you are having problems running a

speciﬁc code example, please ensure th at you update to the same or higher version as the library

speciﬁed. You will be guided as to how to install the deep learning libraries Theano, TensorFlow

and Keras in Part II of the book.

1.4.2 Machine Lea r ning

You do not need to be a machine learning expert, but it would be helpfu l if you knew how to

navigate a small machine learning problem using scikit-learn. Basic concepts like cross-validation

and one hot encoding used in lessons and projects are described, but only brieﬂy. There are

resources to go into these topics in more detail at the end of the book, but some knowledge of

these areas might make things easier for you.

1.4.3 Deep Lear ning

You do not need to know the math and theory of deep learning algorithms, but it would be

helpful to have some basic idea of the ﬁeld. You will get a crash co ur se in neur a l netwo r k

terminology and models, but we will not go into much detail. Again, there will be resources for

more information at the end of the book, but it might be helpful if you can start with some

idea about neural networks.

Note

: All tutorials can be co m p l eted on standard workstati o n hardware with a CPU. A

GPU is not required. Some tutorials later in the book can be sped up signiﬁcantly by running

on the GPU and a suggestion is provided to consider using GPU hardware at the beginning of

those sections. You can access GPU hardware easily and cheaply in the cloud and a step-by-step

procedure is taught on how to do this in Chapter 5.

1.5 Your Outco mes From Reading This Book

This book will lead you from being a developer who is interested in deep learning with Pyt h on

to a developer who has the resources and capabilities to work through a new dataset end-to-end

using Python and develop accurate deep learning models. Speciﬁcally, you will know:

1.6. What This Book is Not 8

How to develop and evaluate neural network models end-to-end.

How to use more advanc ed techniques required for developing state-of-the-art deep learning

models.

How to build lar ger models for image and text data.

How to use advanced image augmentation techniques in order to lift model performance.

How to get help with deep learning in Python.

From here you can start to dive into the speciﬁcs of the functi o n s, techniques and algorithms

used with the goal of learning how to use them better in order to deliver more accurate predictive

models, more reliably in less time. There are a few ways you can read this book. You can dip

into th e lessons and projects as your need or interests motivate you. Alternatively, you can

work through the book end-to-end and take advantage of how the lessons and projects build in

complexity and ran ge. I recomm en d t h e l at t er approach.

To get the very most from thi s book, I recommend taking each lesson and project and build

upon them. Attempt to improve the results, apply the method to a similar but di↵erent problem,

and so on. Write u p what you tried or lea rn e d and share it on your blog, socia l media or send

me an email at

jason@MachineLearningMastery.com

.Thisbookisreallywhatyoumakeofit

and by putting in a little extra, you can quickly become a t r u e force in applied deep learning.

1.6 What This Book is Not

This book solves a speciﬁc p r o b l em of getting you, a developer, up to speed applying deep

learning to your own machine learn i n g projects in Python. As such, this book was not intended

to b e everything to everyone and it is very imp ortant to calibrate your expectations. Speciﬁcally:

This is not a deep learning textbook

.Wewillnotbegettingintothebasictheory

of artiﬁcial neural networks or deep learning algorithms. You are also expected to have

some familiarity with machine learning basics, or be able to pick them up yourself.

This is not an algorithm book

.Wewillnotbeworkingthroughthedetailsofhow

speciﬁc deep learning algorithms work. You are expected to have some basic knowledge of

deep learning algorithms or how to pick up this knowledge yourself.

This is not a Python programming book

.Wewillnotbespendingalotoftimeon

Python syntax and p r ogram m i n g (e.g. basic programming task s in Python). You are

expected to al read y be familiar with Python or a developer who can pick up a new C-like

language relatively quickly.

You can still get a lot out of this b o ok if you are weak in one or two of these areas, but you

may struggle picking up the language or require some more explanation of the techniques. If

this is the case, see the Getting More Help chapter at the end of the book and seek out a good

companion reference text.

剩余254页未读，继续阅读

利

粉丝: 0
资源: 8

Python深度学习实践：从Theano到TensorFlow与Keras

Jason-Brownlee-deep_learning_with_python(pdf + sourcecode v1.15 2018).zip

Deep Learing with python +Deep Learing with python Keras合集

Deep_Learning_with_Python

[machine_learning_mastery系列]deep_learning_with_python.pdf(with code)

Deep_Learning_with_Python_Keras_francois

Deep_Learning_with_Python_2018.pdf

deep_learning_with_python_Jason_Brownlee.zip

Deep_Learning_with_Python_Keras PDF高清版

Deep_Learning_With_Python.pdf

deep_learning_with_python By Jason Brownlee

最新资源