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)

Exploring a curated image location dataset

Back in Chapter 2, Exploring and Cleaning Up Data with fastai, we went through the process of ingesting and exploring a variety of datasets using fastai.

In this section, we are going to explore a special curated image dataset called COCO_TINY. This is an image location dataset. Unlike the CIFAR dataset that we used in the Training a classification model with a simple curated vision dataset recipe, which had a single labeled object in each image, the images in image location datasets are labeled with bounding boxes (which indicate where in the image a particular object occurs) as well as the name of the object. Furthermore, images in the COCO_TINY dataset can contain multiple labeled objects, as shown here:

Figure 6.17 – Labeled image from an image location dataset

In the recipe in this section, we'll ingest the dataset and apply its annotation information to create a dataloaders object for the dataset...