pytorch-crf

Conditional random field in PyTorch.

This package provides an implementation of conditional random field (CRF) in PyTorch. This implementation borrows mostly from AllenNLP CRF module with some modifications.

Documentation

https://pytorch-crf.readthedocs.io/

License

MIT

Contributing

Contributions are welcome! Please follow these instructions to install dependencies and running the tests and linter.

Installing dependencies

Make sure you setup a virtual environment with Python and PyTorch installed. Then, install all the dependencies in requirements.txt file and install this package in development mode.

pip install -r requirements.txt
pip install -e .

Setup pre-commit hook

Simply run:

ln -s ../../pre-commit.sh .git/hooks/pre-commit

Running tests

Run pytest in the project root directory.

Running linter

Run flake8 in the project root directory. This will also run mypy, thanks to flake8-mypy package.