Physics-Guided Neural Networks (phygnn)
Project description
An open source implementation of Physics-Guided Neural Networks (PHYGNN). This implementation of PHYGNN augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints.
Installation
Use conda (anaconda or miniconda with python 3.7) to create a phygnn environment: conda create --name phygnn python=3.7
Activate your new conda env: conda activate phygnn
Navigate to the phygnn directory that contains setup.py and run: pip install -e . (developer install) or pip install . (static install).
Test your installation:
Start ipython and test the following import: from phygnn import PhysicsGuidedNeuralNetwork
Navigate to the tests/ directory and run the command: pytest
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for NREL_phygnn-0.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f330d675251d5e749ea07e27fbbbd4f2f0d1d03a277c1d49e51f2a7e27e62764 |
|
MD5 | a5fb297d22e9c195570fcbc7eb5a9bbe |
|
BLAKE2b-256 | 17fcb3c1b51a8ed4d1f13d3fb2452944a0c4e2625f90c952f4c2df581535daef |