Sophon.jl - GitLite

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #typescript #llm #go #rust #java #windows #cli #awesome-list #pytorch #security #open-source

Sophon.jl

(★ 60)

Efficient, Accurate, and Streamlined Training of Physics-Informed Neural Networks

File Explorer

Download Latest Version (.zip)

- - CI.yml
  - CompatHelper.yml
  - register.yml
  - TagBot.yml
- dependabot.yml
- allen.png
- convection.png
- functionfitting.svg
- helmholtz.png
- Lshape.png
- poisson.png
- Schrödinger.png
- sod.png
- - api.md
  - index.md
  - qa.md
  - references.md
- bibliography.bib
- make.jl
- Project.toml
- SophonLuxCUDAExt.jl
- SophonOptimisersExt.jl
- SophonTaylorDiffExt.jl
- SophonTaylorDiffLuxCUDAExt.jl
- - activations.jl
  - basic.jl
  - containers.jl
  - nets.jl
  - operators.jl
  - utils.jl
- - discretize.jl
  - pinn_types.jl
  - pinnsampler.jl
  - sym_utils.jl
  - training_strategies.jl
  - utils.jl
- showprogress.jl
- Sophon.jl
- betasampler.jl
- functional.jl
- hybriddiff.jl
- runtests.jl
- taylordiff.jl
.gitignore
.JuliaFormatter.toml
CITATION.bib
LICENSE
Project.toml
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Sophon

[![Stable](https://img.shields.io/badge/docs-stable-blue.svg)](https://yichengdwu.github.io/Sophon.jl/stable/)
[![Dev](https://img.shields.io/badge/docs-dev-blue.svg)](https://yichengdwu.github.io/Sophon.jl/dev/)
[![Build Status](https://github.com/YichengDWu/Sophon.jl/actions/workflows/CI.yml/badge.svg?branch=main)](https://github.com/YichengDWu/Sophon.jl/actions/workflows/CI.yml?query=branch%3Amain)
[![Coverage](https://codecov.io/gh/YichengDWu/Sophon.jl/branch/main/graph/badge.svg)](https://codecov.io/gh/YichengDWu/Sophon.jl)
[![DOI](https://zenodo.org/badge/521846679.svg)](https://zenodo.org/badge/latestdoi/521846679)

`Sophon.jl` provides specialized neural networks and neural operators for Physics-informed machine learning.

Use the [documentation](https://yichengdwu.github.io/Sophon.jl/dev/) to explore the features.

Please star this repository if you find it useful.

## Installation

To install Sophon, please open Julia's interactive session (REPL) and press ] key in the REPL to use the package mode, then type the following command

```julia
pkg> add Sophon
```
## Examples

More examples can be found in [Sophon-Examples](https://github.com/YichengDWu/Sophon-Examples).

## Gallery
| ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/functionfitting.svg)     | ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/poisson.png)                 | ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/convection.png)                | ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/helmholtz.png)                |
|:---------------------------------------:|:-------------------------------------------------------------:|:------------------------------------------------------------:|:-----------------------------------------------------------:|
| [Function Fitting](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/discontinuous/) | [Multi-scale Poisson Equation](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/poisson/) | [Convection Equation](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/convection/) | [Helmholtz Equation](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/helmholtz/) |
| ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/allen.png)     | ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/Schrödinger.png)                 | ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/Lshape.png)                |    ![](https://raw.githubusercontent.com/YichengDWu/Sophon.jl/main/assets/sod.png)     |
| [Allen-Cahn Equation](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/allen_cahn/) | [Schrödinger Equation](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/Schr%C3%B6dingerEquation/) | [L-shaped Domain](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/L_shape/) | [SOD Shock Tube](https://yichengdwu.github.io/Sophon.jl/dev/tutorials/sod/) |

## 🏠 Stable & Mature Framework

The current version is highly stable and you can confidently use it for your projects.
In the immediate future, we will **not** be introducing new features to the framework. Our focus is on maintaining its stability and robustness, ensuring that it stands resilient in various use-cases and scenarios.

We're here to help you with any issues or challenges you might encounter. Feel free to reach out!

## Related Libraries

- [NeuralPDE](https://github.com/SciML/NeuralPDE.jl)
- [PaddleScience](https://github.com/PaddlePaddle/PaddleScience)
- [MindScience](https://gitee.com/mindspore/mindscience)
- [Modulus](https://docs.nvidia.com/deeplearning/modulus/index.html#)
- [DeepXDE](https://deepxde.readthedocs.io/en/latest/index.html#)
- [SimulAI](https://github.com/IBM/simulai)

## What's the difference between this package and NeuralPDE.jl?

The biggest difference is the explicit control over data sampling. Note that we have an example of an L-shape domain, and there is an example of a disk with a hole in this [file](https://github.com/YichengDWu/Sophon.jl/blob/main/docs/src/tutorials/hole.jl).