https://github.com/sandialabs/pancax
A set of tools for developing new methods and techniques in physics informed neural networks written in jax.
https://github.com/sandialabs/pancax
equinox jax physics physics-informed-neural-networks physics-simulation pinn pinns sciml scr-3050 snl-applications
Last synced: 5 months ago
JSON representation
A set of tools for developing new methods and techniques in physics informed neural networks written in jax.
- Host: GitHub
- URL: https://github.com/sandialabs/pancax
- Owner: sandialabs
- License: mit
- Created: 2024-11-06T14:17:33.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-27T15:54:25.000Z (5 months ago)
- Last Synced: 2025-02-27T22:26:48.194Z (5 months ago)
- Topics: equinox, jax, physics, physics-informed-neural-networks, physics-simulation, pinn, pinns, sciml, scr-3050, snl-applications
- Language: Python
- Homepage:
- Size: 6.57 MB
- Stars: 4
- Watchers: 0
- Forks: 1
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://sandialabs.github.io/pancax)
[](https://github.com/sandialabs/pancax/actions?query=workflow%3ACI)
[](https://codecov.io/gh/sandialabs/pancax)
[](https://pypi.org/project/pancax/)
# Pancax ("PANCAKES")
Physics augmented neural computations in jax
## Table of Contents
1. [Installation](#installation)
2. [Usage](#usage)
3. [Citation](#citation)
## Installation
### CPU installation instructions
To install pancax using pip (recommended) for CPU usage you can type the following command
``pip install pancax[cpu]``
### GPU installation instructions
Currently only CUDA has been tested, so only a CUDA option is supplied.
#### CUDA installation instructions
To install pancax using pip (recommended) for CPU usage you can type the following command
``pip install pancax[cuda]``
### Developer installation instructions
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]``
## Usage
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
## Citation
```bibtex
@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