万本电子书0元读

万本电子书0元读

顶部广告

PyTorch Deep Learning Hands-On电子书

售       价:¥

12人正在读 | 0人评论 6.2

作       者:Sherin Thomas

出  版  社:Packt Publishing

出版时间:2019-04-30

字       数:266.6万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:数字商品不支持退换货,不提供源文件,不支持导出打印

为你推荐

  • 读书简介
  • 目录
  • 累计评论(0条)
  • 读书简介
  • 目录
  • 累计评论(0条)
All the key deep learning methods built step-by-step in PyTorch Key Features * Understand the internals and principles of PyTorch * Implement key deep learning methods in PyTorch: CNNs, GANs, RNNs, reinforcement learning, and more * Build deep learning workflows and take deep learning models from prototyping to production Book Description PyTorch is a new, lightweight, and Python-first tool for deep learning. Built by Facebook to offer flexibility and speed, it has quickly become the preferred tool for deep learning experts. PyTorch helps you release deep learning models faster than ever before. PyTorch Deep Learning Hands-On shows how to implement every major deep learning architecture in PyTorch. Starting with simple neural networks, it covers PyTorch for computer vision (CNN), natural language processing (RNN), GANs, and reinforcement learning. You will also build deep learning workflows with the PyTorch framework, migrate models built in Python to highly efficient TorchScript, and deploy to production using the most sophisticated available tools. Each chapter focuses on a different area of deep learning. Chapters start with a refresher on the core principles, before sharing the code you need to implement them in PyTorch. If you want to become a deep learning expert this book is for you. What you will learn Use PyTorch to build: * Simple Neural Networks – build neural networks the PyTorch way, with high-level functions, optimizers, and more * Convolutional Neural Networks – create advanced computer vision systems * Recurrent Neural Networks – work with sequential data such as natural language and audio * Generative Adversarial Networks – create new content with models including SimpleGAN and CycleGAN * Reinforcement Learning – develop systems that can solve complex problems such as driving or game playing * Deep Learning workflows – move effectively from ideation to production with proper deep learning workflow using PyTorch and its utility packages * Production-ready models – package your models for high-performance production environments Who this book is for Machine learning professionals and enthusiasts who know Python and want to build efficient and powerful deep learning systems in PyTorch.
目录展开

PyTorch Deep Learning Hands-On

PyTorch Deep Learning Hands-On

Why subscribe?

Packt.com

Contributors

About the authors

About the reviewers

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

1. Deep Learning Walkthrough and PyTorch Introduction

Understanding PyTorch's history

What is PyTorch?

Installing PyTorch

What makes PyTorch popular?

Using computational graphs

Using static graphs

Using dynamic graphs

Exploring deep learning

Getting to know different architectures

Fully connected networks

Encoders and decoders

Recurrent neural networks

Recursive neural networks

Convolutional neural networks

Generative adversarial networks

Reinforcement learning

Getting started with the code

Learning the basic operations

The internals of PyTorch

Summary

References

2. A Simple Neural Network

Introduction to the neural network

The problem

Dataset

Novice model

Autograd

Autograd attributes of a tensor

Building the graph

Finding error

Backpropagation

Parameter update

The PyTorch way

High-level APIs

nn.Module

apply()

cuda() and cpu()

train() and eval()

parameters()

zero_grad()

Other layers

The functional module

The loss function

Optimizers

Summary

References

3. Deep Learning Workflow

Ideation and planning

Design and experimentation

The dataset and DataLoader classes

Utility packages

torchvision

torchtext

torchaudio

Model implementation

Bottleneck and profiling

Training and validation

Ignite

Engine

Events

Metrics

Saving checkpoints

Summary

References

4. Computer Vision

Introduction to CNNs

Computer vision with PyTorch

Simple CNN

Model

Semantic segmentation

LinkNet

Deconvolution

Skip connections

Model

ConvBlock

DeconvBlock

Pooling

EncoderBlock

DecoderBlock

Summary

References

5. Sequential Data Processing

Introduction to recurrent neural networks

The problem

Approaches

Simple RNN

Word embedding

RNNCell

Utilities

Pad sequence

Pack sequence

Encoder

Classifier

Dropout

Training

Advanced RNNs

LSTM

GRUs

Architecture

LSTMCell and GRUCell

LSTMs and GRUs

Increasing the number of layers

Bidirectional RNN

Classifier

Attention

Recursive neural networks

Reduce

Tracker

SPINN

Summary

References

6. Generative Networks

Defining the approaches

Autoregressive models

PixelCNN

Masked convolution

Gated PixelCNN

WaveNet

GANs

Simple GAN

CycleGAN

Summary

References

7. Reinforcement Learning

The problem

Episodic versus continuous tasks

Cumulative discounted rewards

Markov decision processes

The solution

Policies and value functions

Bellman equation

Finding the optimal Q-function

Deep Q-learning

Experience replay

Gym

Summary

References

8. PyTorch to Production

Serving with Flask

Introduction to Flask

Model serving with Flask

A production-ready server

ONNX

MXNet model server

MXNet model archiver

Load testing

Efficiency with TorchScript

Exploring RedisAI

Summary

References

Another Book You May Enjoy

Leave a review - let other readers know what you think

Index

累计评论(0条) 0个书友正在讨论这本书 发表评论

发表评论

发表评论,分享你的想法吧!

买过这本书的人还买过

读了这本书的人还在读

回顶部