This code is written in Python 3.7 and requires the packages listed in requirements.txt.
Clone the repository to your machine and directory of choice.
To run the code, we recommend setting up a virtual environment, e.g. using virtualenv or conda:
# pip install virtualenv
cd <path-to-CVDD-PyTorch-directory>
virtualenv myenv
source myenv/bin/activate
pip install -r requirements.txt
cd <path-to-CVDD-PyTorch-directory>
conda create --name myenv
source activate myenv
while read requirement; do conda install -n myenv --yes $requirement; done < requirements.txt
After installing the packages, run python -m spacy download en to download the spaCy en
library.
You can run CVDD experiments using the main.py script.
The following are examples on how to run experiments on
Reuters-21578,
20 Newsgroups, and
IMDB Movie Reviews as reported in the paper.
cd <path-to-CVDD-PyTorch-directory>
source myenv/bin/activate # or 'source activate myenv' for conda
cd src
python3 main.py reuters cvdd_Net ../log/test_reuters ../data/reuters0.pt