fastbook
The fastai book, published as Jupyter Notebooks
What is fastbook?
The fastai book, published as Jupyter Notebooks
Overview of fastbook
What it is
The fastai book is a collection of Jupyter Notebooks that cover an introduction to deep learning, fastai, and PyTorch. fastai is a layered API for deep learning. The notebooks are used for a MOOC and form the basis of a published book. The repository includes notebooks in multiple languages: English, Spanish, Korean, Chinese, Bengali, Indonesian, Italian, Portuguese, Vietnamese, and Japanese. A selection of chapters is available to read online.
Key features
- Covers an introduction to deep learning, fastai, and PyTorch - Notebooks are used for a MOOC and form the basis of a published book - Available in multiple languages (English, Spanish, Korean, Chinese, Bengali, Indonesian, Italian, Portuguese, Vietnamese, Japanese)
- Can be used with Google Colab without local setup - The code in notebooks and Python files is covered by the GPL v3 license - The remainder (markdown cells and other prose) is not licensed for redistribution or change of format, and no commercial or broadcast use is allowed
Use cases
- Learning deep learning from scratch - Following the fastai MOOC - Reference material for using fastai and PyTorch - Self-study or classroom instruction
Getting started
You can open the notebooks in Google Colab by clicking on the provided links in the repository README. Alternatively, clone the repository and run the notebooks locally. No specific installation commands are provided in the README; see the repository README for details.
License and pricing
The code in the notebooks and Python .py files is covered by the GPL v3 license. The remainder (including all markdown cells and other prose) is not licensed for any redistribution or change of format or medium, other than making copies of the notebooks or forking the repo for private use. No commercial or broadcast use is allowed. The book itself is available for purchase and does not have the same GPL restrictions. The metadata lists the pricing type as open source.
Based on the project's public README and repository metadata.