Types of problems you can apply the fastai library to

Application fields

The fastai library allows you to train a Model on a certain DataBunch very easily by binding them together inside a Learner object. This module regroups the tools the library provides to help you preprocess and group your data in this format.

collab

This submodule handles the collaborative filtering problems.

tabular

This sub-package deals with tabular (or structured) data.

text

This sub-package contains everything you need for Natural Language Processing.

vision

This sub-package contains the classes that deal with Computer Vision.

Module structure

In each case (except for collab), the module is organized this way:

transform

This sub-module deals with the pre-processing (data augmentation for images, cleaning for tabular data, tokenizing and numericalizing for text).

data

This sub-module defines the dataset class(es) to deal with this kind of data.

models

This sub-module defines the specific models used for this kind of data.

learner

When it exists, this sub-module contains functions that will directly bind this data with a suitable model and add the necessary callbacks.

Usage

To start using any of the above applications, simply import the top level module.
All the submodules get included.

The general structure is:

from fastai.[APPLICATION] import *

For example, to use collab:

from fastai.collab import *

For more information on imports

Open This Notebook