Physics augmented neural computations in jax
To install pancax using pip (recommended) for CPU usage you can type the following command
pip install pancax[cpu]
Currently only CUDA has been tested, so only a CUDA option is supplied.
To install pancax using pip (recommended) for CPU usage you can type the following command
pip install pancax[cuda]
If you would like to do development in pancax, please first clone the repo and in the pancax folder, run the following command
pip install -e .[cuda,docs,test]
Currently the main entry point to pancax is through a python script (although a yaml input file is also in the works). To run a script you can run the following command
python -m pancax -i my_script.py
where my_script.py is the name of the scipt you've written. This will run the python script while also
respecting several environment variables which can be supplied after the pancax keyword above. A list of
these can be displayed with the help message
python -m pancax -h
If you leverage these tools for your own research, please cite the following article
@article{hamel2023calibrating,
title={Calibrating constitutive models with full-field data via physics informed neural networks},
author={Hamel, Craig M and Long, Kevin N and Kramer, Sharlotte LB},
journal={Strain},
volume={59},
number={2},
pages={e12431},
year={2023},
publisher={Wiley Online Library}
}SCR #3050.0