Deep Learning with fastai Cookbook - PDF

Скачать полную версию книги "Deep Learning with fastai Cookbook - PDF"

Deep Learning with fastai Cookbook: Leverage the easy-to-use fastai framework to unlock the power of deep learning by Mark Ryan

fastai 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 of the predominant low-level deep learning frameworks today (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.


We will start by summarizing the value of fastai and showing a simple "hello world" deep learning application with fastai. Then, we will describe how to use fastai for each of the four application areas that the framework explicitly supports: tabular data, text data (NLP), recommender systems, and vision data. You will work through a series of practical examples that illustrate how to create real-world applications of each type. After that, you will learn how to deploy fastai models. For example, you will learn how to create a simple web application that predicts what object is depicted in an image. Finally, we will wrap up with an overview of the advanced features of fastai.


By the end of this book, you will be able to create your own deep learning applications using fastai. You'll know how to use fastai to prepare raw datasets, explore datasets, train deep learning models, and deploy trained models.


Who this book is for

This book is for data scientists, machine learning developers, and deep learning enthusiasts who are looking to learn and explore the fastai framework using a recipe-based approach. Working knowledge of the Python programming language and machine learning basics are strongly recommended to get the most out of this book.


This book provides practical examples of how to use fastai to tackle a variety of deep learning application areas, but it is not an exhaustive reference for the platform. To get comprehensive details on fastai, please see the Conclusion and additional resources on fastai section in Chapter 8, Extended fastai and Deployment Features. This section points to additional fastai content, including the excellent deep learning courses built around fastai created by Jeremy Howard and his team.


15
Просмотры
0
Лайкнули

Лицензии:

  • CC BY-NC-SA 3.0 PH
  • Ссылка автора не требуется

Поделиться в сетях

Информация о книге:

Комментарии (0) Добавить

Кликните на изображение чтобы обновить код, если он неразборчив
Комментариев пока нет. Ваш комментарий будет первым!