Python Deep Learning Cookbook电子书

Title Page

Copyright

Python Deep Learning Cookbook

Credits

About the Author

About the Reviewer

www.PacktPub.com

Why subscribe?

Customer Feedback

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the example code

Errata

Piracy

Questions

Programming Environments, GPU Computing, Cloud Solutions, and Deep Learning Frameworks

Introduction

Setting up a deep learning environment

How to do it...

Launching an instance on Amazon Web Services (AWS)

Getting ready

How to do it...

Launching an instance on Google Cloud Platform (GCP)

Getting ready

How to do it...

Installing CUDA and cuDNN

Getting ready

How to do it...

Installing Anaconda and libraries

How to do it...

Connecting with Jupyter Notebooks on a server

How to do it...

Building state-of-the-art, production-ready models with TensorFlow

How to do it...

Intuitively building networks with Keras

How to do it...

Using PyTorch’s dynamic computation graphs for RNNs

How to do it...

Implementing high-performance models with CNTK

How to do it...

Building efficient models with MXNet

How to do it...

Defining networks using simple and efficient code with Gluon

How to do it...

Feed-Forward Neural Networks

Introduction

Understanding the perceptron

How to do it...

Implementing a single-layer neural network

How to do it...

Building a multi-layer neural network

How to do it...

Getting started with activation functions

How to do it...

Experiment with hidden layers and hidden units

How to do it...

There's more...

Implementing an autoencoder

How to do it...

Tuning the loss function

How to do it...

Experimenting with different optimizers

How to do it...

Improving generalization with regularization

How to do it...

Adding dropout to prevent overfitting

How to do it...

Convolutional Neural Networks

Introduction

Getting started with filters and parameter sharing

How to do it...

Applying pooling layers

How to do it...

Optimizing with batch normalization

How to do it...

Understanding padding and strides

How to do it...

Experimenting with different types of initialization

How to do it...

Implementing a convolutional autoencoder

How to do it...

Applying a 1D CNN to text

How to do it...

Recurrent Neural Networks

Introduction

Implementing a simple RNN

How to do it...

Adding Long Short-Term Memory (LSTM)

How to do it...

Using gated recurrent units (GRUs)

How to do it...

Implementing bidirectional RNNs

How to do it...

Character-level text generation

How to do it...

Reinforcement Learning

Introduction

Implementing policy gradients

Getting ready

How to do it...

Implementing a deep Q-learning algorithm

Getting ready

How to do it...

Generative Adversarial Networks

Introduction

Understanding GANs

How to do it...

Implementing Deep Convolutional GANs (DCGANs)

How to do it...

Upscaling the resolution of images with Super-Resolution GANs (SRGANs)

How to do it...

Computer Vision

Introduction

Augmenting images with computer vision techniques

How to do it...

Classifying objects in images

How to do it...

Localizing an object in images

How to do it...

Real-time detection frameworks

Segmenting classes in images with U-net

How to do it...

Scene understanding (semantic segmentation)

How to do it...

Finding facial key points

How to do it...

Recognizing faces

How to do it...

Transferring styles to images

How to do it...

Natural Language Processing

Introduction

Analyzing sentiment

How to do it...

Translating sentences

How to do it...

Summarizing text

How to do it...

Speech Recognition and Video Analysis

Introduction

Implementing a speech recognition pipeline from scratch

How to do it...

Identifying speakers with voice recognition

How to do it...

Understanding videos with deep learning

How to do it...

Time Series and Structured Data

Introduction

Predicting stock prices with neural networks

How to do it...

Predicting bike sharing demand

How to do it...

Using a shallow neural network for binary classification

How to do it...

Game Playing Agents and Robotics

Introduction

Learning to drive a car with end-to-end learning

Getting started

How to do it...

Learning to play games with deep reinforcement learning

How to do it...

Genetic Algorithm (GA) to optimize hyperparameters

How to do it..

Hyperparameter Selection, Tuning, and Neural Network Learning

Introduction

Visualizing training with TensorBoard and Keras

How to do it...

Working with batches and mini-batches

How to do it...

Using grid search for parameter tuning

How to do it...

Learning rates and learning rate schedulers

How to do it...

Comparing optimizers

How to do it...

Determining the depth of the network

Adding dropouts to prevent overfitting

How to do it...

Making a model more robust with data augmentation

How to do it...

Leveraging test-time augmentation (TTA) to boost accuracy

Network Internals

Introduction

Visualizing training with TensorBoard

How to do it..

Visualizing the network architecture with TensorBoard

Analyzing network weights and more

How to do it...

Freezing layers

How to do it...

Storing the network topology and trained weights

How to do it...

Pretrained Models

Introduction

Large-scale visual recognition with GoogLeNet/Inception

How to do it...

Extracting bottleneck features with ResNet

How to do it...

Leveraging pretrained VGG models for new classes

How to do it...

Fine-tuning with Xception

How to do it...