Metadata-Version: 2.1
Name: AdeptML
Version: 1.0
Summary: A High-Level PyTorch based Library for Hybrid Physics-Informed Machine Learning Models
Author: Manaswin Oddiraju
Requires-Python: >=3.9.0,<3.13
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Provides-Extra: docs
Requires-Dist: Sphinx (==7.3.7) ; extra == "docs"
Requires-Dist: jax (>=0.4.18,<0.5.0)
Requires-Dist: joblib (>=1.3.2,<2.0.0)
Requires-Dist: sphinx-rtd-theme (==2.0.0) ; extra == "docs"
Requires-Dist: sphinxcontrib-napoleon (==0.7) ; extra == "docs"
Requires-Dist: tensorboard (>=2.16.2,<3.0.0)
Requires-Dist: torch (>=2.1.0,<3.0.0)
Description-Content-Type: text/markdown

# Auto-differentiable embedding of Physics and Torch Machine Learning (AdePT-ML):

This is a convienience library built on top of PyTorch to enable easy integration and training of hybrid models involving physics and deep learning modules. 

### Features
1. Pre-defined Modules and configs for physics and MLP architectures.
2. Physics Module accepts physics functions which return numpy arrays.
3. Ability to input custom PyTorch nn classes.
4. Ensemble Module allows easy integration of constituent physics and ML modules for simple inference and training.
5. Auto-log training data with tensorboard.

## Installation
Installing with pip
```
pip install adeptml 
```
## Requirements (Automatically installed with pip): 
1. PyTorch (https://pytorch.org/)
2. Joblib (https://joblib.readthedocs.io/en/latest/) (For loading and saving model parameters)
3. Tensorboard

## Documentation:
Visit our [Read the docs page](https://adept-ml.readthedocs.io/en/latest/)

## Examples:
Refer to the tests file. Additional examples will be added soon.


