• Stars
    star
    845
  • Rank 53,926 (Top 2 %)
  • Language
    Jupyter Notebook
  • License
    Apache License 2.0
  • Created about 4 years ago
  • Updated about 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Deep Learning for Coders, 2020, the website

Practical Deep Learning for Coders

Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD - the book and the course

Welcome to Practical Deep Learning for Coders. This web site covers the book and the 2020 version of the course, which are designed to work closely together. If you haven't yet got the book, you can buy it here. It's also freely available as interactive Jupyter Notebooks; read on to learn how to access them..

How do I get started?

If you're ready to dive in right now, here's how to get started. If you want to know more about this course, read the next sections, and then come back here.

To watch the videos, click on the Lessons section in the navigation sidebar. The lessons all have searchable transcripts; click "Transcript Search" in the top right panel to search for a word or phrase, and then click it to jump straight to video at the time that appears in the transcript. The videos are all captioned and also translated into Chinese (简体中文) and Spanish; while watching the video click the "CC" button to turn them on and off, and the setting button to change the language.

Each video covers a chapter from the book. The entirety of every chapter of the book is available as an interactive Jupyter Notebook. Jupyter Notebook is the most popular tool for doing data science in Python, for good reason. It is powerful, flexible, and easy to use. We think you will love it! Since the most important thing for learning deep learning is writing code and experimenting, it's important that you have a great platform for experimenting with code.

To get started, we recommend using a Jupyter Server from one of the recommended online platforms (click the links for instructions on how to use these for the course):

  • Gradient: Unlike Colab, this is a "real" Jupyter Notebook so everything in the course works. It also provides space to save your notebooks and models. However, sometimes the free servers get over-loaded, and when that happens it's impossible to connect
  • Colab: A popular free service from Google. Google have changed the notebook platform quite a lot, so keyboard shortcuts are different, and not everything works (e.g. much of chapter 2 doesn't work because Colab doesn't support creating web app GUIs).

If you are interested in the experience of running a full Linux server you can consider Google Cloud (extremely popular service, very reliable, but the fastest GPUs are far more expensive). We strongly suggest using one of the recommended online platforms for running the notebooks, and to not use your own computer, unless you're very experienced with Linux system adminstration and handling GPU drivers, CUDA, and so forth.

If you need help, there's a wonderful online community ready to help you at forums.fast.ai. Before asking a question on the forums, search carefully to see if your question has been answered before. (The forum system won't let you post until you've spent a few minutes on the site reading existing topics.) One bit that many students find tricky is getting signed up for the Bing API for the image download task in lesson 2; here's a helpful forum post explaining how to get the Bing API key you'll need for downloading images.

Is this course for me?

Thank you for letting us join you on your deep learning journey, however far along that you may be! Previous fast.ai courses have been studied by hundreds of thousands of students, from all walks of life, from all parts of the world. Many students have told us about how they've become multiple gold medal winners of international machine learning competitions, received offers from top companies, and having research papers published. For instance, Isaac Dimitrovsky told us that he had "been playing around with ML for a couple of years without really grokking it... [then] went through the fast.ai part 1 course late last year, and it clicked for me". He went on to achieve first place in the prestigious international RA2-DREAM Challenge competition! He developed a multistage deep learning method for scoring radiographic hand and foot joint damage in rheumatoid arthritis, taking advantage of the fastai library.

It doesn't matter if you don't come from a technical or a mathematical background (though it's okay if you do too!); we wrote this course to make deep learning accessible to as many people as possible. The only prerequisite is that you know how to code (a year of experience is enough), preferably in Python, and that you have at least followed a high school math course. The first three chapters have been explicitly written in a way that will allow executives, product managers, etc. to understand the most important things they'll need to know about deep learning -- if that's you, just skip over the code in those sections.

Deep learning is a computer technique to extract and transform data–-with use cases ranging from human speech recognition to animal imagery classification–-by using multiple layers of neural networks. A lot of people assume that you need all kinds of hard-to-find stuff to get great results with deep learning, but as you'll see in this course, those people are wrong. Here's a few things you absolutely don't need to do world-class deep learning:

Myth (don't need) Truth
Lots of math Just high school math is sufficient
Lots of data We've seen record-breaking results with <50 items of data
Lots of expensive computers You can get what you need for state of the art work for free

Deep learning has power, flexibility, and simplicity. That's why we believe it should be applied across many disciplines. These include the social and physical sciences, the arts, medicine, finance, scientific research, and many more. Here's a list of some of the thousands of tasks in different areas at which deep learning, or methods heavily using deep learning, is now the best in the world:

  • Natural language processing (NLP) Answering questions; speech recognition; summarizing documents; classifying documents; finding names, dates, etc. in documents; searching for articles mentioning a concept
  • Computer vision Satellite and drone imagery interpretation (e.g., for disaster resilience); face recognition; image captioning; reading traffic signs; locating pedestrians and vehicles in autonomous vehicles
  • Medicine Finding anomalies in radiology images, including CT, MRI, and X-ray images; counting features in pathology slides; measuring features in ultrasounds; diagnosing diabetic retinopathy
  • Biology Folding proteins; classifying proteins; many genomics tasks, such as tumor-normal sequencing and classifying clinically actionable genetic mutations; cell classification; analyzing protein/protein interactions
  • Image generation Colorizing images; increasing image resolution; removing noise from images; converting images to art in the style of famous artists
  • Recommendation systems Web search; product recommendations; home page layout
  • Playing games Chess, Go, most Atari video games, and many real-time strategy games
  • Robotics Handling objects that are challenging to locate (e.g., transparent, shiny, lacking texture) or hard to pick up
  • Other applications Financial and logistical forecasting, text to speech, and much more...

Who we are

We are Sylvain Gugger and Jeremy Howard, your guides on this journey. We're the co-authors of fastai, the software that you'll be using throughout this course.

Jeremy has been using and teaching machine learning for around 30 years. He started using neural networks 25 years ago. During this time, he has led many companies and projects that have machine learning at their core, including founding the first company to focus on deep learning and medicine, Enlitic, and taking on the role of President and Chief Scientist of the world's largest machine learning community, Kaggle. He is the co-founder, along with Dr. Rachel Thomas, of fast.ai, the organization that built the course this course is based on.

Sylvain has written 10 math textbooks, covering the entire advanced French maths curriculum! He is now a researcher at Hugging Face, and was previously a researcher at fast.ai.

We care a lot about teaching. In this course, we start by showing how to use a complete, working, very usable, state-of-the-art deep learning network to solve real-world problems, using simple, expressive tools. And then we gradually dig deeper and deeper into understanding how those tools are made, and how the tools that make those tools are made, and so on… We always teaching through examples. We ensure that there is a context and a purpose that you can understand intuitively, rather than starting with algebraic symbol manipulation.

The software you will be using

In this course, you'll be using PyTorch and fastai.

We've completed hundreds of machine learning projects using dozens of different packages, and many different programming languages. At fast.ai, we have written courses using most of the main deep learning and machine learning packages used today. We spent over a thousand hours testing PyTorch before deciding that we would use it for future courses, software development, and research. PyTorch is now the world's fastest-growing deep learning library and is already used for most research papers at top conferences.

PyTorch works best as a low-level foundation library, providing the basic operations for higher-level functionality. The fastai library is the most popular library for adding this higher-level functionality on top of PyTorch. In this course, as we go deeper and deeper into the foundations of deep learning, we will also go deeper and deeper into the layers of fastai. This course covers version 2 of the fastai library, which is a from-scratch rewrite providing many unique features.

What you will learn

After finishing this course you will know:

  • How to train models that achieve state-of-the-art results in:
    • Computer vision, including image classification (e.g., classifying pet photos by breed), and image localization and detection (e.g., finding where the animals in an image are)
    • Natural language processing (NLP), including document classification (e.g., movie review sentiment analysis) and language modeling
    • Tabular data (e.g., sales prediction) with categorical data, continuous data, and mixed data, including time series
    • Collaborative filtering (e.g., movie recommendation)
  • How to turn your models into web applications, and deploy them
  • Why and how deep learning models work, and how to use that knowledge to improve the accuracy, speed, and reliability of your models
  • The latest deep learning techniques that really matter in practice
  • How to implement stochastic gradient descent and a complete training loop from scratch
  • How to think about the ethical implications of your work, to help ensure that you're making the world a better place and that your work isn't misused for harm

Here are some of the techniques covered (don't worry if none of these words mean anything to you yet--you'll learn them all soon):

  • Random forests and gradient boosting
  • Affine functions and nonlinearities
  • Parameters and activations
  • Random initialization and transfer learning
  • SGD, Momentum, Adam, and other optimizers
  • Convolutions
  • Batch normalization
  • Dropout
  • Data augmentation
  • Weight decay
  • Image classification and regression
  • Entity and word embeddings
  • Recurrent neural networks (RNNs)
  • Segmentation
  • And much more

More Repositories

1

fastai

The fastai deep learning library
Jupyter Notebook
26,176
star
2

fastbook

The fastai book, published as Jupyter Notebooks
Jupyter Notebook
21,305
star
3

numerical-linear-algebra

Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course
Jupyter Notebook
10,134
star
4

courses

fast.ai Courses
Jupyter Notebook
5,571
star
5

course-v3

The 3rd edition of course.fast.ai
Jupyter Notebook
4,906
star
6

nbdev

Create delightful software with Jupyter Notebooks
Jupyter Notebook
4,829
star
7

fastpages

An easy to use blogging platform, with enhanced support for Jupyter Notebooks.
Jupyter Notebook
3,522
star
8

course-nlp

A Code-First Introduction to NLP course
Jupyter Notebook
3,414
star
9

course22

The fast.ai course notebooks
Jupyter Notebook
2,318
star
10

lm-hackers

Hackers' Guide to Language Models
Jupyter Notebook
1,756
star
11

fastprogress

Simple and flexible progress bar for Jupyter Notebook and console
Jupyter Notebook
1,083
star
12

fastcore

Python supercharged for the fastai library
Jupyter Notebook
961
star
13

imagenette

A smaller subset of 10 easily classified classes from Imagenet, and a little more French
Jupyter Notebook
934
star
14

fastai2

Temporary home for fastai v2 while it's being developed
Jupyter Notebook
645
star
15

fastai_dev

fast.ai early development experiments
Jupyter Notebook
639
star
16

diffusion-nbs

Getting started with diffusion
Jupyter Notebook
606
star
17

ghapi

A delightful and complete interface to GitHub's amazing API
Jupyter Notebook
528
star
18

course22p2

course.fast.ai 2022 part 2
Jupyter Notebook
471
star
19

swiftai

Swift for TensorFlow's high-level API, modeled after fastai
Jupyter Notebook
457
star
20

course-v4

Please use fastbook's /clean folder instead of this
446
star
21

imagenet-fast

Python
302
star
22

nbdev_template

Template for nbdev projects
Python
290
star
23

timmdocs

Documentation for Ross Wightman's timm image model library
Jupyter Notebook
277
star
24

numerical-linear-algebra-v2

Jupyter Notebooks for Computational Linear Algebra course, taught summer 2018 in USF MSDS program
Jupyter Notebook
269
star
25

fast_template

A template for really easy blogging with GitHub Pages
HTML
250
star
26

fastdoc

Create publication-quality books from Jupyter notebooks
Jupyter Notebook
230
star
27

fastsetup

Setup all the things
Shell
219
star
28

fastdiffusion

Notes and plans for fastdiffusion course
Jupyter Notebook
202
star
29

fastai_old

OLD REPO - PLEASE USE fastai/fastai
Jupyter Notebook
179
star
30

docker-containers

Docker images for fastai
Shell
172
star
31

book_nbs

Notebooks for upcoming fastai book (draft / incomplete)
Jupyter Notebook
166
star
32

fastscript

A fast way to turn your python function into a script
CSS
164
star
33

word-embeddings-workshop

This contains materials for the word embeddings workshop
HTML
123
star
34

fastec2

AWS EC2 computer management for regular folks
Python
121
star
35

execnb

Execute a jupyter notebook, fast, without needing jupyter
Jupyter Notebook
111
star
36

fastai1

v1 of the fastai library. v2 is the current version. v1 is still supported for bug fixes, but will not receive new features.
Jupyter Notebook
98
star
37

tf-fit

Fit your tensorflow model using fastai and PyTorch
Python
91
star
38

fastgpu

A queue service for quickly developing scripts that use all your GPUs efficiently
Jupyter Notebook
81
star
39

fastsql1

A bit of extra usability for sqlalchemy v2.
Jupyter Notebook
77
star
40

nbdev-template

Python
74
star
41

book.fast.ai

Information for readers of the fastai book
Jupyter Notebook
67
star
42

fastdot

A simple wrapper over `pydot` and `graphviz` which fixes some sharp edges
Jupyter Notebook
63
star
43

fastkaggle

Kaggling for fast kagglers!
Jupyter Notebook
52
star
44

nbprocess-old

Process and export Jupyter Notebooks fast (Jupyter not required)
Jupyter Notebook
52
star
45

randomized-SVD

demos for PyBay talk: Using Randomness to make code faster
Jupyter Notebook
50
star
46

fastai3

Research repo for code that may or may not end up in fastai3
Jupyter Notebook
50
star
47

pypi_template

A minimal template for creating a pypi package
Python
49
star
48

fastbook2e

The fastai book, 2nd edition (in progress)
Jupyter Notebook
46
star
49

fastdownload

Easily download, verify, and extract archives
Jupyter Notebook
44
star
50

course22-web

Website for Practical Deep Learning for Coders 2022
Jupyter Notebook
43
star
51

fastforest

A forest that is fast
C++
41
star
52

dotfiles

Vim Script
41
star
53

nbdev-vscode

TypeScript
41
star
54

bear_voila

Demo bear classifier with fastai and Voila
Jupyter Notebook
40
star
55

workflows

Composite Actions workflows for use in fastai projects
Python
39
star
56

tinykernel

A minimal Python kernel so you can run Python in your Python
Python
39
star
57

wireguard-fast

Simplified installation of WireGuard server for Ubuntu
Shell
37
star
58

minai

A miniture AI training framework for PyTorch
Jupyter Notebook
35
star
59

tinypets

Minimal JS interface to an image classifer
HTML
34
star
60

fastai-nbstripout

much faster nbstripout and autotrust notebooks local git configuration
Python
33
star
61

fastai-docs

Documentation for fastai
HTML
32
star
62

pagegraph

Draw, modify, and execute graphs using a simple python dict interface
Jupyter Notebook
29
star
63

masks4all

Make your own mask. My mask protects you. Your mask protects me.
Jupyter Notebook
26
star
64

apl-study

fast.ai APL study group notes
Jupyter Notebook
25
star
65

fastconda

Get packages onto your conda channel faster
Jupyter Notebook
22
star
66

git-tools

Tools to make git easier to use and to avoid the learning curve
Python
20
star
67

tweetrel

Use GitHub Actions to send a tweet when you make a new release
Jupyter Notebook
18
star
68

fastcgi

A fastcgi handler for Python's `socketserver` classes
Jupyter Notebook
17
star
69

fastrelease

DEPRECATED--all functionality moved to nbdev
Jupyter Notebook
15
star
70

fastpy

An easy way to start a python programming environment using GitHub Codespaces.
15
star
71

paperspace-setup

Setup a paperspace instance for fastai
Shell
14
star
72

ethics.fast.ai

The fast.ai data ethics course
Jupyter Notebook
14
star
73

fastcups

HTML
14
star
74

jupytercon-2023

Materials for "Write, Document, Test and Distribute Python Packages With Jupyter & Quarto", JupyterCon 2023.
Jupyter Notebook
14
star
75

fastlinkcheck

Check local static links and online links fast and in parallel
Jupyter Notebook
13
star
76

nbdev-index

nbdev docs lookup for a few libraries and python itself
Python
12
star
77

dlcert2

Web site source for Practical Deep Learning for Coders (2018)
Jupyter Notebook
12
star
78

Str8Pix

find the optimal rotation to correct skewed photos
Jupyter Notebook
11
star
79

dlcert1

Deep learning certificate part 1
10
star
80

cards_deck

A minimal example of nbdev based on Allen Downey's Think Python 2nd Ed
Jupyter Notebook
10
star
81

docments

Document parameters using comments
10
star
82

nbdev2

Temporary repo for nbdev2
Jupyter Notebook
7
star
83

spacy_conda

conda packages for spacy and deps
7
star
84

hugo-mathjax

Hugo with goldmark-mathjax
Jupyter Notebook
6
star
85

fastwebhook

A simple GitHub webhook server
Jupyter Notebook
6
star
86

wandbfastai

Jupyter Notebook
5
star
87

nbeverything

5
star
88

nbdev-jekyll-theme

CSS
4
star
89

nbdev_cards

A sample of how to create a deck of cards lib using nbdev
Jupyter Notebook
4
star
90

nbdev-demo

4
star
91

getcaddy

Simple approach to getting the Caddy web server
Shell
4
star
92

nbdev-spaces-demo

A demo of how to create a Hugging Face Space with gradio within a nbdev project.
Jupyter Notebook
4
star
93

fastdispatch

Wrapper for plum dispatch to make it more compatible with fastcore's typedispatch
Jupyter Notebook
3
star
94

tanishq_blog

CSS
3
star
95

docs

3
star
96

ghtop-demo

A CLI tool for showing GitHub events, written with Rich
Jupyter Notebook
3
star
97

logos

Logos for fastai for use in websites, icons, etc.
2
star
98

jb-nbdev

Exploring how nbdev may integrate with JupyterBook
Jupyter Notebook
2
star
99

nbdev-hello-world

Hello world from nbdev
Python
2
star
100

conda-recipes

Recipes for non-fastai projects that fastai provides packages for.
Python
2
star