Conditional random field in PyTorch.
This package provides an implementation of linear-chain conditional random field (CRF) in PyTorch. This implementation borrows mostly from AllenNLP CRF module <https://github.com/allenai/allennlp/blob/master/allennlp/modules/conditional_ra ndom_field.py> with some modifications.
https://pytorch-crf.readthedocs.io/
MIT
Contributions are welcome! Please follow these instructions to install dependencies and running the tests and linter.
Make sure you setup a virtual environment with Python. Then, install all the dependencies in requirements.txt
file and install this package in development mode.
pip install -r requirements.txt
pip install -e .
Simply run:
ln -s ../../pre-commit.sh .git/hooks/pre-commit
Run pytest
in the project root directory.
Run flake8
in the project root directory. This will also run mypy
, thanks to flake8-mypy
package.