Deep learning with fastai cookbook : leverage the easy-to-use fastai framework to unlock the power of deep learning / Mark Ryan.

Format:

Book

Author/Creator:

Ryan, Mark, author.

Language:

English

Subjects (All):

Machine learning.

Physical Description:

1 online resource (340 pages)

Place of Publication:

Birmingham, England ; Mumbai : Packt, [2021]

Summary:

Harness the power of the easy-to-use, high-performance fastai framework to rapidly create complete deep learning solutions with few lines of codeKey FeaturesDiscover how to apply state-of-the-art deep learning techniques to real-world problemsBuild and train neural networks using the power and flexibility of the fastai frameworkUse deep learning to tackle problems such as image classification and text classificationBook Descriptionfastai is an easy-to-use deep learning framework built on top of PyTorch that lets you rapidly create complete deep learning solutions with as few as 10 lines of code. Both predominant low-level deep learning frameworks, TensorFlow and PyTorch, require a lot of code, even for straightforward applications. In contrast, fastai handles the messy details for you and lets you focus on applying deep learning to actually solve problems. The book begins by summarizing the value of fastai and showing you how to create a simple 'hello world' deep learning application with fastai. You'll then learn how to use fastai for all four application areas that the framework explicitly supports: tabular data, text data (NLP), recommender systems, and vision data. As you advance, you'll work through a series of practical examples that illustrate how to create real-world applications of each type. Next, you'll learn how to deploy fastai models, including creating a simple web application that predicts what object is depicted in an image. The book wraps up with an overview of the advanced features of fastai. By the end of this fastai book, you'll be able to create your own deep learning applications using fastai. You'll also have learned how to use fastai to prepare raw datasets, explore datasets, train deep learning models, and deploy trained models.What you will learnPrepare real-world raw datasets to train fastai deep learning modelsTrain fastai deep learning models using text and tabular dataCreate recommender systems with fastaiFind out how to assess whether fastai is a good fit for a given problemDeploy fastai deep learning models in web applicationsTrain fastai deep learning models for image classificationWho this book is forThis book is for data scientists, machine learning developers, and deep learning enthusiasts looking to explore the fastai framework using a recipe-based approach. Working knowledge of the Python programming language and machine learning basics is strongly recommended to get the most out of this deep learning book.

Contents:

Cover

Title Page

Copyright and Credits

Contributors

Table of Contents

Preface

Chapter 1: Getting Started with fastai

Technical requirements

Setting up a fastai environment in Paperspace Gradient

Getting ready

How to do it...

How it works...

There's more...

Setting up a fastai environment in Google Colab

Setting up JupyterLab environment in Gradient

Hello world" for fastai - creating a model for MNIST

Getting ready...

Understanding the world in four applications: tables, text, recommender systems, and images

Working with PyTorch tensors

Contrasting fastai with Keras

Test your knowledge

Chapter 2: Exploring and Cleaning Up Data with fastai

Getting the complete set of oven-ready fastai datasets

Examining tabular datasets with fastai

Examining text datasets with fastai

Examining image datasets with fastai

Cleaning up raw datasets with fastai

Chapter 3: Training Models with Tabular Data

Training a model in fastai with a curated tabular dataset

Training a model in fastai with a non-curated tabular dataset

Getting ready.

How to do it...

Training a model with a standalone dataset

Assessing whether a tabular dataset is a good candidate for fastai

Saving a trained tabular model

Chapter 4: Training Models with Text Data

Training a deep learning language model with a curated IMDb text dataset

Training a deep learning classification model with a curated text dataset

Training a deep learning language model with a standalone text dataset

Training a deep learning text classifier with a standalone text dataset

Chapter 5: Training Recommender Systems

Training a recommender system on a small curated dataset

Training a recommender system on a large curated dataset

Training a recommender system on a standalone dataset

Chapter 6: Training Models with Visual Data

Training a classification model with a simple curated vision dataset

Exploring a curated image location dataset

Training a classification model with a standalone vision dataset

Training a multi-image classification model with a curated vision dataset

Chapter 7: Deployment and Model Maintenance

Setting up fastai on your local system

Deploying a fastai model trained on a tabular dataset

Deploying a fastai model trained on an image dataset

Maintaining your fastai model

Chapter 8: Extended fastai and Deployment Features

Getting more details about models trained with tabular data

Getting more details about image classification models

Training a model with augmented data

Using callbacks to get the most out of your training cycle

Making your model deployments available to others

Displaying thumbnails in your image classification model deployment

Explore the value of repeatable results

Displaying multiple thumbnails in your image classification model deployment

Conclusion and additional resources on fastai

Other Books You May Enjoy

Index.

Notes:

Description based on print version record.

Includes index.

ISBN:

1-80020-999-1

OCLC:

1262328450