/d2l-pytorch

This project reproduces the book Dive Into Deep Learning (www.d2l.ai), adapting the code from MXNet into PyTorch.

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0


This project is adapted from the original Dive Into Deep Learning book by Aston Zhang, Zachary C. Lipton, Mu Li, Alex J. Smola and all the community contributors. GitHub of the original book: https://github.com/d2l-ai/d2l-en. We have made an effort to modify the book and convert the MXnet code snippets into PyTorch.

Note: Some ipynb notebooks may not be rendered perfectly in Github. We suggest cloning the repo or using nbviewer to view the notebooks.

Installation

Many of you will not have Python 3.6 already installed on your computers. Conda is an easy way to manage many different environments, each with its own Python versions and dependencies. This allows us to avoid conflicts between our preferred Python version and that of other classes. We’ll walk through how to set up and use a conda environment.

Prerequisite: Anaconda. Many of you will have it installed from classes such as EE 16A; if you don’t, install it through the link.

Creating a Conda Environment

conda create --name <env-name> python=3.6

Entering the Environment

conda activate <env-name>

Setting the Environment

pip install -r requirements.txt

Chapters

Contributing

  • Please feel free to open a Pull Request to contribute a notebook in PyTorch for the rest of the chapters. Before starting out with the notebook, open an issue with the name of the notebook in order to contribute for the same. We will assign that issue to you (if no one has been assigned earlier).

  • Strictly follow the naming conventions for the IPython Notebooks and the subsections.

  • Also, if you think there's any section that requires more/better explanation, please use the issue tracker to open an issue and let us know about the same. We'll get back as soon as possible.

  • Find some code that needs improvement and submit a pull request.

  • Find a reference that we missed and submit a pull request.

  • Try not to submit huge pull requests since this makes them hard to understand and incorporate. Better send several smaller ones.

Support

If you like this repo and find it useful, please consider (★) starring it, so that it can reach a broader audience.

References

[1] Original Book Dive Into Deep Learning -> Github Repo

[2] Deep Learning - The Straight Dope

[3] PyTorch - MXNet Cheatsheet

Cite

If you use this work or code for your research please cite the original book with the following bibtex entry.

@book{zhang2020dive,
    title={Dive into Deep Learning},
    author={Aston Zhang and Zachary C. Lipton and Mu Li and Alexander J. Smola},
    note={\url{https://d2l.ai}},
    year={2020}
}