How to Install fastai on Mac

The fastai is a Python library that simplifies training fast and accurate neural nets using modern best practices. It’s based on research into deep learning best practices undertaken at fast.ai, including “out of the box” support for vision, text, tabular, and collab (collaborative filtering) models.

Mac does not support Nvidia GPUs well so it is not a good platform for training deep neural nets with a lot of data. A GPU can speed up the learning process about 15 times. If you want to use a GPU then you can use Kaggle or Colaboratory when you can get access to a Jupyter notebook environment with a GPU.

Having the environment on your computer is useful for development without the need to be online, exploration of the dataset, preprocessing of the data, or try new things on a small subset of data.

We will use the Terminal application to install the fastai library and its prerequisites.

1. Install Homebrew

Homebrew is a package for macOS. Install it using the following command:

/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

You should get a following message at the end:

==> Installation successful!

2. Install Anaconda Python

Anaconda is the easiest way to perform Python data science and machine learning on Linux, Windows, and macOS.