Skip to content
A PyTorch-based framework for building deep learning models for document classification
Branch: master
Clone or download
Pull request Compare This branch is 17 commits ahead, 2 commits behind castorini:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

This repo contains PyTorch deep learning models for document classification, implemented by the Data Systems Group at the University of Waterloo.


Each model directory has a with further details.

Setting up PyTorch

Hedwig is designed for Python 3.6 and PyTorch 0.4. PyTorch recommends Anaconda for managing your environment. We'd recommend creating a custom environment as follows:

$ conda create --name castor python=3.6
$ source activate castor

And installing PyTorch as follows:

$ conda install pytorch=0.4.1 cuda92 -c pytorch

Other Python packages we use can be installed via pip:

$ pip install -r requirements.txt

Code depends on data from NLTK (e.g., stopwords) so you'll have to download them. Run the Python interpreter and type the commands:

>>> import nltk


Download the Reuters, AAPD and IMDB datasets, along with word2vec embeddings from hedwig-data.

$ git clone
$ git clone

Organize your directory structure as follows:

├── hedwig
└── hedwig-data

After cloning the hedwig-data repo, you need to unzip the embeddings and run the preprocessing script:

cd hedwig-data/embeddings/word2vec 
gzip -d GoogleNews-vectors-negative300.bin.gz 
python GoogleNews-vectors-negative300.bin GoogleNews-vectors-negative300.txt 

If you are an internal Hedwig contributor using the machines in the lab, follow the instructions here.

You can’t perform that action at this time.