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)

Test your knowledge

Now that you have completed the recipes in this chapter, follow the steps shown here to exercise what you have learned. You will do this by adapting one of the notebooks you worked through in this chapter so that it works with a new dataset.

Getting ready

Follow these steps to upload a new tabular dataset:

  1. Go to the site for the Kaggle competition on future sales prediction (https://www.kaggle.com/c/competitive-data-science-predict-future-sales/data) and accept the conditions for the competition to get access to the datasets associated with the competition.
  2. Download the sales_train.csv.zip and test.csv.zip files.
  3. Unzip the downloaded files to extract sales_train.csv and test.csv.
  4. From the Terminal in your Gradient environment, make your current directory /storage/archive:
    cd /storage/archive
  5. Create a folder called /storage/archive/price_prediction:
    mkdir price_prediction
  6. Upload sales_train.csv and test.csv to /storage/archive/price_prediction...