TensorFlow implementation of the Lorentz Boost Network (LBN). https://arxiv.org/abs/1812.09722.
TensorFlow implementation of the Lorentz Boost Network from arXiv:1812.09722 [hep-ex].
Original repository: git.rwth-aachen.de/3pia/lbn
from lbn import LBN # initialize the LBN, set 10 combinations and pairwise boosting lbn = LBN(10, boost_mode=LBN.PAIRS) # create a feature tensor based on input four-vectors features = lbn(four_vectors) # use the features as input for a subsequent, application-specific network ...
Installation and dependencies
pip install lbn
NumPy and TensorFlow are the only dependencies.
Tests should be run for Python 2 and 3. The following commands assume you are root directory of the LBN respository:
python -m unittest test # or via docker, python 2 docker run --rm -v `pwd`:/root/lbn -w /root/lbn tensorflow/tensorflow:latest python -m unittest test # or via docker, python 3 docker run --rm -v `pwd`:/root/lbn -w /root/lbn tensorflow/tensorflow:latest-py3 python -m unittest test
If you like to contribute, we are happy to receive pull requests. Just make sure to add new test cases and run the tests. Also, please use a coding style that is compatible with our