Deep Learning for Coders with fastai and PyTorch

by Jeremy Howard

Book Reviews

  • Big thanks to @OReillyMedia for allowing us to freely publish portions of the book online -- if you like it, then here's where you can order the whole thing: https://t.co/guKT7y9VfMLink to Tweet
  • There are 9 lessons, and each lesson is around 90 minutes long. It's based on our 5⭐rated book, which is freely available online. Special hardware/software isn't needed—we show how to use free resources for everything. https://t.co/guKT7ys4tULink to Tweet
  • The new course will be similar to the existing course, in that it will (roughly) follow the presentation of material in our book, but will include new stuff too (e.g transformers networks) https://t.co/guKT7ys4tULink to Tweet
  • We're really proud of what people are saying about the new book. https://t.co/guKT7y9VfM https://t.co/Rqge3lUsrpLink to Tweet
  • fastai v2 is not API-compatible with fastai v1 (it’s a from-scratch rewrite). It’s much easier to use, more powerful, and better documented than v1, and there’s even a book (624 pages!) about it https://t.co/guKT7y9VfMLink to Tweet
  • We've been blown away by the amazing comments from reviewers for *Deep Learning for Coders*. Google's Peter Norvig, an amazing researcher and writer, said it's "one of the best sources for a programmer to become proficient in deep learning." https://t.co/Uy3cZLkuwa https://t.co/2jp2JCTAm3Link to Tweet
  • In our forthcoming book & course, you'll learn how to build a real deep learning web app from scratch, including downloading images using Bing's API. You'll also learn what can go wrong! (h/t @rajiinio) https://t.co/guKT7y9VfM https://t.co/p8Ur0mChXULink to Tweet

About Book

Deep learning has the reputation as an exclusive domain for math PhDs. Not so. With this book, programmers comfortable with Python will learn how to get started with deep learning right away. Using PyTorch and the fastai deep learning library, you'll learn how to train a model to accomplish a wide range of tasks--including computer vision, natural language processing, tabular data, and generative networks. At the same time, you'll dig progressively into deep learning theory so that by the end of the book you'll have a complete understanding of the math behind the library's functions.