Metadata-Version: 2.4
Name: torchfsm
Version: 0.0.2
Summary: Fourier Spectral Method with PyTorch
Home-page: https://qiauil.github.io/torchfsm
Author: Qiang Liu, Felix Koehler, Nils Thuerey
Author-email: qiangliu.7@outlook.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: ipython
Requires-Dist: matplotlib
Requires-Dist: numpy
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: vape4d
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-dist
Dynamic: summary

<h1 align="center">
  <br>TorchFSM<br>
</h1>
<h4 align="center">Fourier Spectral Method with PyTorch</h4>
<p align="center">
  [<a href="https://qiauil.github.io/torchfsm/"> Documentation & Examples</a>]
</p>

## TL;DR
`TorchFSM` is a PyTorch-based library for solving PDEs using Fourier spectral method. It is designed for physics-based deep learning and differentiable simulations.

## Feature

* **Modular by design**: TorchFSM offers a modular architecture with essential mathematical operators—like divergence, gradient, and convection—so you can build custom solvers like stacking building blocks, quickly and intuitively.

* **GPU-accelerated**: TorchFSM leverages GPU computing to speed up simulations dramatically. Run complex 3D PDEs in minutes, not hours, with seamless hardware acceleration.

* **Batched simulation support**: Built on PyTorch, TorchFSM enables batched simulations with varied initial conditions—ideal for parameter sweeps, uncertainty quantification, or ensemble analysis.

* **Differentiable and ML-ready**: Fully differentiable by design, TorchFSM integrates naturally with machine learning workflows—for residual operators, differentiable physics, or dataset generation.

## Documentations

Check 👉 [here](https://qiauil.github.io/torchfsm/) for more details.
