Book Image

Deep Learning with fastai Cookbook

By : Mark Ryan
Book Image

Deep Learning with fastai Cookbook

By: Mark Ryan

Overview of this book

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.
Table of Contents (10 chapters)

"Hello world" for fastai – creating a model for MNIST

Now that you have set up your environment for fastai, it's time to run through an example. In this section, you will go through the process of creating a simple deep learning model trained on the MNIST dataset. This dataset consists of images of handwritten digits. The goal of the trained model is to predict the digit given an image. For example, we want the trained model to predict that the following digits are 6, 3, 9, and 6:

Figure 1.30 – Sample handwritten digits from the MNIST dataset

We won't be covering every detail of the fastai solution for MNIST in this section, but we will be running a complete example that demonstrates one of the key values of fastai—getting a powerful deep learning result with only a few lines of code. This example should also whet your appetite for the more advanced fastai examples that are coming in subsequent chapters.

Getting ready...