What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Key benefits

Discover how to apply state-of-the-art deep learning techniques to real-world problems

Build and train neural networks using the power and flexibility of the fastai framework

Use deep learning to tackle problems such as image classification and text classification

Description

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 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.

Who is this book for?

This 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.

What you will learn

Prepare real-world raw datasets to train fastai deep learning models

Train fastai deep learning models using text and tabular data

Create recommender systems with fastai

Find out how to assess whether fastai is a good fit for a given problem

Deploy fastai deep learning models in web applications

Train fastai deep learning models for image classification

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

NZ$71.99

Machine Learning for Time-Series with Python

NZ$80.99

NZ$87.99

Total NZ$ 240.97

Richa Sethi Oct 29, 2021

As the name of the book describes, this book is actually a cookbook where it starts from the very basic ingredients (setting up the environment) needed for fastai, and eventually builds up the pace by getting deep into data cleaning and exploration. It then delves into training tabular data, text data and recommender systems, and finally gets into model deployment and maintenance. Great for beginners as well as individuals like me who have used fastai for certain applications before. This book should allow anyone apply fastai to create end-to-end deep learning models to make predictions on a wide variety of datasets.

Amazon Verified review

Daniel Armstrong Oct 30, 2021

This book is filled with great examples of how you can apply fast.ai to a wide range of deep learning projects. I may be a little biased because I am a huge fan of fast.ai, but I really enjoyed this book. I am glad to have it as part of my library. It not only covers the major deep learning topics like CV, NLP, and Tabular data, but is also covers other topics like using callback, memory management, and model deployment. The only part that I was a little disappointed about was the section on object detection, the author did a great job covering the subject, but the fast.ai library doesn't cover an easy way to do object detection out of the box. The good new is their is a library called Ice Vision that is built and maintained by a group of former Fast.ai student/alumni, which is built on top of fast.ai that does a great job making object detection possible and as easy as most things you can do in fast.ai.

Amazon Verified review

Guangping zhang Sep 24, 2021

Finally I read a book for FastAI, "Deep Learning with fastai Cookbook".Fist this book discusses how to setting up a fastai environment in Google Colab, then introduce theapplications: tables, text, recommender systems, and images.After discussing data cleaning, which is a necessary step using fastai, this book discuss the four typesof application of Fastai chapter by chapter, all the application share same training and predict api, fit_one_cycleand predict, for transfer learning, you can use fine_tune() replace fit_one_cycle.Several steps for model web deployment and advanced deployment, including export(), load_learner() and web_flask_deploy and/or web_flask_deploy_image_mode()were discussed using two chapter in this book.This book uses clean logic and easy understanding language to introduce fastai to readers, I suggest you read this book if you plan to use fastai.

Amazon Verified review

Erfan Chowdhury Nov 30, 2021

This book is perfect for people who wants to utilize the highly optimized Fastai library. Jeremy Howard , the creator of Fastai, has a free of charge online series where he demonstrates and teaches how to use the library. He even published a book "Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a PhD" to follow along with the course. However , many topics were just brushed over in these videos and the book and the task was left for the user to go and tinker around.This is time consuming unfortunately. But here is the good part! This is the book that basically spoon feeds the Fastai library to you. This book contains in-depth explanations to topics that were not deeply covered in the series or the book. All the chapters in the book comes with their own datasets to test out what you have learnt. Starting from cleaning the data to solving all different kinds of structured and unstructured problems that you might face in the field of deep learning, this book teaches you how to effectively use the Fastai toolkit. This book also demonstrates how you can deploy the models that you trained. The "Test Your Knowledge" section at the end of every chapter is like a brain teaser that strengthens your conceptualization of that particular chapter.The book is well written and well organized. I thoroughly enjoyed the book. Highly Recommended!

Amazon Verified review

Carlo Nov 29, 2021

This book provides an excellent starting point to anyone interested in building deep learning applications.It effectively shows how to use fastai, a powerful and intuitive deep learning framework.The book provides detailed instructions and tutorials to quickly dive into deep learning examples. A very nice aspect is the step-by-step guidance in setting up the right working environment to run the examples.It is a perfect book for practitioners and machine learning beginners that want to get started as quickly as possible. However, it doesn't provide much theoretical background on machine learning and how models work, so should definitely be accompanied by other resources for practitioners with no background on machine learning who want to understand the inner workings of ML models.Overall it's a useful book especially recommended to anyone who wants to use the fast.ai framework to build powerful deep learning models quickly.

Amazon Verified review

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

What do you get with eBook?