全新PyTorch深度学习编程()(美)伊恩·波特9787564188795

Preface

1． Getting Started with PyTorch

Building a Custom Deep Learning Machine

GPU

CPU/Motherboard

RAM

Storage

Deep Learning in the Cloud

Google Colaboratory

Cloud Providers

Which Cloud Provider Should I Use?

Using Jupyter Notebook

Installing PyTorch from Scratch

Download CUDA

Anaconda

Finally， PyTorch！（and Jupyter Notebook）

Tensors

Tensor Oraios

Tensor Broadcasting

Conclusion

Further Reading

2． Image Classification with PyTorch

Our Classification Problem

Traditional Challenges

But First， Data

PyTorch and Data Loaders

Building a Training Dataset

Building Validation and Test Datasets

Finally， a Neural Network！

Activation Functions

Creating a Network

Loss Functions

Optimizing

Training

Making It Work on the GPU

Putting It All Together

Making Predictions

Model Saving

Conclusion

Further Reading

3． Convolutional Neural Networks

Our First Convolutional Model

Convolutions

Pooling

Dropout

History of CNN Architectures

AlexNet

Inception/GoogLeNet

VGG

ResNet

Other Architectures Are Available！

Using Pretrained Models in PyTorch

Examining a Models Structure

BatchNorm

Which Model Should You Use?

One-Stop Shopping for Models： PyTorch Hub

Conclusion

Further Reading

4． Transfer Learning and Other Tricks

Transfer Learning with ResNet

Finding That Learning Rate

Differential Learning Rates

Data Augmentation

Torchvision Transforms

Color Spaces and Lambda Transforms

Custom Transform Classes

Start Small and Get Bigger！

Ensembles

Conclusion

Further Reading

5． Text Classificati0n

Recurrent Neural Networks

Long Short-Term Memory Networks

Gated Recurrent Units

biLSTM

Embeddings

torchtext

Getting Our Data： Tweets！

Defining Fields

Building a Vocabulary

Creating Our Model

Updating the Training Loop

Classifying Tweets

Data Augmentation

Random Insertion

Random Deletion

Random Swap

Back Translation

Augmentation and torchtext

Transfer Learning?

Conclusion

Further Reading

6． A Journey into Sound

Sound

The ESC-50 Dataset

Obtaining the Dataset

Playing Audio in Jupyter

Exploring ESC-50

SoX and LibROSA

torchaudio

Building an ESC-50 Dataset

A CNN Model for ESC-50

This Frequency Is My Universe

Mel Spectrograms

A New Dataset

A Wild ResNet Appears

Finding a Learning Rate

Audio Data Augmentation

torchaudio Transforms

SoX Effect Chains

SpecAugment

Further Experiments

Conclusion

Further Reading

7． Debugging PyTorch Models

Its 3 a．m． What Is Your Data Doing?

TensorBoard

Installing TensorBoard

Sending Data to TensorBoard

PyTorch Hooks

Plotting Mean and Standard Deviation

Class Activation Mapping

Flame Graphs

Installing py-spy

Reading Flame Graphs

Fixing a Slow Transformation

Debugging GPU Issues

Checking Your GPU

Gradient Checkpointing

Conclusion

Further Reading

8． PyTorch in Production

Model Serving

Building a Flask Service

Setting Up the Model Parameters

Building the Docker Container

Local Versus Cloud Storage

Logging and Telemetry

Deploying on Kubernetes

Setting Up on Google Kubernetes Engine

Creating a k8s Cluster

Scaling Services

Updates and Cleaning Up

TorchScript

Tracing

Scripting

TorchScript Limitations

Working with libTorch

Obtaining libTorch and Hello World

Importing a TorchScript Model

Conclusion

Further Reading

9． PyTorch in the Wild

Data Augmentation： Mixed and Smoothed

mixup

Label Smoothing

Computer， Enhance！

Introduction to Super-Resolution

An Introduction to GANs

The Forger and the Critic

Training a GAN

The Dangers of Mode Collapse

ESRGAN

Further Adventures in Image Detection

Object Detection

Faster R-CNN and Mask R-CNN

Adversarial Samples

Black-Box Attacks

Defending Against Adversarial Attacks

More Than Meets the Eye： The Transformer Architecture

Paying Attention

Attention Is All You Need

BERT

FastBERT

GPT-2

Generating Text with GPT-2

ULMFiT

What to Use?

Conclusion

Further Reading

Index