"Keras应用指南：深度神经网络在机器学习和数据科学中的应用"

需积分: 0 199 浏览量更新于2024-01-25 收藏 5.21MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

深度神经网络应用(Keras)是一本介绍深度学习应用的开源电子书，由Jeff Heaton编写。本书的内容涵盖了机器学习、深度学习、数据科学、数据分析等众多领域，以及Keras、TensorFlow、PyTorch、强化学习、数学基础等相关技术。本书的内容是通过整理从各平台的原作者公开分享中得到的。本书的作者Jeff Heaton从2016年春季学期开始，开始为圣路易斯华盛顿大学教授T81-558深度学习的应用课程。他将课程材料、例子和作业放在GitHub上，并逐渐丰富发展成了这本电子书。本书的目录一共包括了14个章节。第1章介绍了Python的预备课程，为后续章节的学习做好基础。第2章介绍了用于机器学习的Python的相关知识和技术。第3章简单介绍了TensorFlow的基本概念和用法。第4章探讨了表格数据训练的技巧和方法。第5章介绍了正则化和Dropout等用于提高模型性能和减少过拟合的技术。第6章详细介绍了卷积神经网络在计算机视觉中的应用。第7章介绍了生成对抗网络的原理和应用。第8章涉及到了Kaggle数据集的应用。第9章介绍了迁移学习的原理和实践方法。第10章介绍了在Keras中处理时间序列数据的技术。第11章介绍了Hugging Face库在自然语言处理中的应用。第12章则深入讨论了强化学习的基本概念和应用技巧。第13章涉及一些高级和其他主题。最后一章则探讨了其他神经网络技术的应用。本书的出版商是Heaton Research, Inc.，作者在内容的创作过程中借鉴了其他作者的分享的资源，并在书中给予了相应的引用。本书的目标读者包括对深度学习和相关技术感兴趣的学生、研究人员和从业者。读者可以通过自行学习本书的内容，深入了解深度神经网络在各个领域的应用，并运用Keras等工具进行实际项目的开发和实践。总之，《深度神经网络应用(Keras)》旨在通过系统细致的讲解，帮助读者掌握深度学习和Keras等相关技术，并在实际应用中取得良好的效果。本书的内容全面，适合初学者和有一定基础的读者阅读学习。读者可以在学习的过程中参考书中提供的示例代码，并通过实践来加深对知识的理解和应用。同时，本书也是一个优秀的参考资料和学习指南，读者可以随时查询相关章节的内容来解决问题和加深理解。

资源详情

资源推荐

2 CHAPTER 1. PYTHON PRELIMINARIES

Figure 1.1: Neural Network Luminaries

• Yoshua Bengio, University of Montreal and Botler AI. Extensive research into deep learning, neural

networks, and machine learning.

• Andrew Ng, Badiu and Stanford University. Extensive research into deep learning, neural networks,

and application to robotics.

Geoﬀrey Hinton, Yann LeCun, and Yoshua Bengio won the Turing Award for their contributions to deep

learning.

1.1.2 What is Deep Learning

The focus of this book is deep learning, which is a prevalent type of machine learning that builds upon

the original neural networks popularized in the 1980s. There is very little diﬀerence between how a deep

neural network is calculated compared with the ﬁrst neural network. We’ve always been able to create and

calculate deep neural networks. A deep neural network is nothing more than a neural network with many

layers. While we’ve always been able to create/calculate deep neural networks, we’ve lacked an eﬀective

means of training them. Deep learning provides an eﬃcient means to train deep neural networks.

If deep learning is a type of machine learning, this begs the question, "What is machine learning?"

Figure 1.2 illustrates how machine learning diﬀers from traditional software development.

• Traditional Software Development - Programmers create programs that specify how to transform

input into the desired output.

• Machine Learning - Programmers create models that can learn to produce the desired output for

given input. This learning ﬁlls the traditional role of the computer program.

4 CHAPTER 1. PYTHON PRELIMINARIES

• Time Series - The use of machine learning to detect patterns in time. Typical time series applications

are ﬁnancial applications, speech recognition, and even natural language processing (NLP).

• Generative Models - Neural networks can learn to produce new original synthetic data from input.

We will examine StyleGAN, which learns to create new images similar to those it saw during training.

1.1.3 Regression, Classiﬁcation and Beyond

Machine learning research looks at problems in broad terms of supervised and unsupervised learning.

Supervised learning occurs when you know the correct outcome for each item in the training set. On the

other hand, unsupervised learning utilizes training sets where no correct outcome is known. Deep learning

supports both supervised and unsupervised learning; however, it also adds reinforcement and adversarial

learning. Reinforcement learning teaches the neural network to carry out actions based on an environment.

Adversarial learning pits two neural networks against each other to learn when the data provides no correct

outcomes. Researchers continue to add new deep learning training techniques.

Machine learning practitioners usually divide supervised learning into classiﬁcation and regression.

Classiﬁcation networks might accept ﬁnancial data and classify the investment risk as risk or safe. Similarly,

a regression neural network outputs a number and might take the same data and return a risk score.

Additionally, neural networks can output multiple regression and classiﬁcation scores simultaneously.

One of the most powerful aspects of neural networks is that the input and output of a neural network

can be of many diﬀerent types, such as:

• An image

• A series of numbers that could represent text, audio, or another time series

• A regression number

• A classiﬁcation class

1.1.4 Why Deep Learning?

For tabular data, neural networks often do not perform signiﬁcantly better that diﬀerent than other models,

such as:

• Support Vector Machines

• Random Forests

• Gradient Boosted Machines

Like these other models, neural networks can perform both classiﬁcation and regression. When applied

to relatively low-dimensional tabular data tasks, deep neural networks do not necessarily add signiﬁcant

accuracy over other model types. However, most state-of-the-art solutions depend on deep neural networks

for images, video, text, and audio data.

1.1.5 Python for Deep Learning

We will utilize the Python 3.x programming language for this book. Python has some of the widest

support for deep learning as a programming language. The two most popular frameworks for deep learning

in Python are:

1.1. PART 1.1: OVERVIEW 5

• TensorFlow/Keras (Google)

• PyTorch (Facebook)

Overall, this book focused on the application of deep neural networks. This book focuses primarily upon

Keras, with some applications in PyTorch. For many tasks, we will utilize Keras directly. We will utilize

third-party libraries for higher-level tasks, such as reinforcement learning, generative adversarial neural

networks, and others. These third-party libraries may internally make use of either PyTorch or Keras. I

chose these libraries based on popularity and application, not whether they used PyTorch or Keras.

To successfully use this book, you must be able to compile and execute Python code that makes use of

TensorFlow for deep learning. There are two options for you to accomplish this:

• Install Python, TensorFlow and some IDE (Jupyter, TensorFlow, and others).

• Use Google CoLab in the cloud, with free GPU access.

If you look at this notebook on Github, near the top of the document, there are links to videos that describe

how to use Google CoLab. There are also videos explaining how to install Python on your local computer.

The following sections take you through the process of installing Python on your local computer. This

process is essentially the same on Windows, Linux, or Mac. For speciﬁc OS instructions, refer to one of

the tutorial YouTube videos earlier in this document.

To install Python on your computer, complete the following instructions:

• Installing Python and TensorFlow - Windows/Linux

• Installing Python and TensorFlow - Mac Intel

• Installing Python and TensorFlow - Mac M1

1.1.6 Check your Python Installation

Once you’ve installed Python, you can utilize the following code to check your Python and library versions.

If you have a GPU, you can also check to see that Keras recognize it.

Code

# What v er s i on o f Python do you have ?

import s ys

import t e nso r f l o w . k er as

import pandas as pd

import s k l ea r n as sk

import t e nso r f l o w as t f

check_gpu = len ( t f . c o n f i g . l i s t _ p h y s i c a l _ d e v i c e s ( 'GPU' ))>0

print ( f " Tensor␣Flow␣ Vers ion : ␣{ t f . __version__} " )

print ( f " Keras␣ Ver sion : ␣{ t e n so r f l o w . k er as . __version__} " )

print ( )

print ( f " Python ␣{ s ys . v e r s i o n } " )

6 CHAPTER 1. PYTHON PRELIMINARIES

print ( f " Pandas ␣{pd . __version__} " )

print ( f " S c i k i t −Learn ␣{ sk . __version__} " )

print ( "GPU␣ i s " , " a v a i l a b l e " i f check_gpu \

el se "NOT␣AVAILABLE" )

Output

Tensor Flow Ve rsion : 2 . 8 . 0

Keras Ve rsio n : 2 . 8 . 0

Python 3 . 7 . 1 3 ( d e fa u lt , Mar 16 20 22 , 1 7 : 3 7 : 1 7 )

[GCC 7 . 5 . 0 ]

Pandas 1 . 3 . 5

S c i k i t −Learn 1 . 0 . 2

GPU i s a v a i l a b l e

1.1.7 Module 1 Assignment

You can ﬁnd the ﬁrst assignment here: assignment 1

1.2 Part 1.2: Introduction to Python

Python is an interpreted, high-level, general-purpose programming language. Created by Guido van

Rossum and ﬁrst released in 1991, Python’s design philosophy emphasizes code readability with its notable

use of signiﬁcant whitespace. Its language constructs and object-oriented approach aim to help program-

mers write clear, logical code for small and large-scale projects. Python has become a common language

for machine learning research and is the primary language for TensorFlow.

Python 3.0, released in 2008, was a signiﬁcant revision of the language that is not entirely backward-

compatible, and much Python 2 code does not run unmodiﬁed on Python 3. This course makes use of

Python 3. Furthermore, TensorFlow is not compatible with versions of Python earlier than 3. A non-

proﬁt organization, the Python Software Foundation (PSF), manages and directs resources for Python

development. On January 1, 2020, the PSF discontinued the Python 2 language and no longer provides

security patches and other improvements. Python interpreters are available for many operating systems.

The ﬁrst two modules of this course provide an introduction to some aspects of the Python programming

language. However, entire books focus on Python. Two modules will not cover every detail of this language.

The reader is encouraged to consult additional sources on the Python language.

Like most tutorials, we will begin by printing Hello World.

Code

print ( " H e ll o ␣World " )

剩余576页未读，继续阅读

ShowMeAI

粉丝: 6224
资源: 42

"Keras应用指南：深度神经网络在机器学习和数据科学中的应用"

Learn Keras for Deep Neural Networks

Learn Keras for Deep Neural Networks (2019)

python keras

keras_applications安装

keras.applications安装

buildroot keras-applications

https://github.com/bonlime/keras-deeplab-v3-plus/

Deep learning toolbox

keras.applications.resnet50

输入以上代码后，jupyter显示这个Exception: URL fetch failure on https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5: None -- [WinError 10061] 由于目标计算机积极拒绝，无法连接。，怎么解决

Deep Learning Toolbox

linux keras

卷积神经网络代码keras

tf.keras.applications.mobilenetv2

神经网络和卷积神经网络相关参考文献

ModuleNotFoundError: No module named 'keras.applications.resnet50'

jupyter 报错URL fetch failure on https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5: None -- [WinError 10061] 由于目标计算机积极拒绝，无法连接。

https://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_224_tf_no_top.h5

最新资源