https://github.com/qiauil/convdo
Convolutional Differential Operators for Physics-based Deep Learning Study
https://github.com/qiauil/convdo
convolution deep-learning differentiable-programming differential-equations physics simulation
Last synced: 6 months ago
JSON representation
Convolutional Differential Operators for Physics-based Deep Learning Study
- Host: GitHub
- URL: https://github.com/qiauil/convdo
- Owner: qiauil
- License: mit
- Created: 2024-06-19T11:55:17.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-30T12:43:13.000Z (over 1 year ago)
- Last Synced: 2025-06-26T18:47:00.574Z (7 months ago)
- Topics: convolution, deep-learning, differentiable-programming, differential-equations, physics, simulation
- Language: Python
- Homepage: https://qiauil.github.io/ConvDO/
- Size: 7.14 MB
- Stars: 25
- Watchers: 4
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
ConvDO
Convolutional Differential Operators for Physics-based Deep Learning Study
Calculate the spatial derivative differentiablly!
[📖 Documentation & Examples]
## Installation
* Install through pip: `pip install ConvDO`
* Install the latest version through pip: `pip install git+https://github.com/qiauil/ConvDO`
* Install locally: Download the repository and run `./install.sh` or `pip install .`
## Feature
Positive😀 and negative🙃 things are all features...
* PyTorch-based and only supports 2D fields at the moment.
* Powered by convolutional neural network.
* Differentiable and GPU supported (why not? It's PyTorch based!).
* Second order for Dirichlet and Neumann boundary condition.
* Up to 8th order for periodic boundary condition.
* Obstacles inside of the domain is supported.
## Documentations
Check 👉 [here](https://qiauil.github.io/ConvDO/)
## Further Reading
Projects using `ConvDO`:
* [Diffusion-based-Flow-Prediction](https://github.com/tum-pbs/Diffusion-based-Flow-Prediction): Diffusion-based flow prediction (DBFP) with uncertainty for airfoils.
* To be updated...
If you need to solve more complex PDEs using differentiable functions, please have a check on
* [PhiFlow](https://github.com/tum-pbs/PhiFlow): A differentiable PDE solving framework for machine learning
* [Exponax](https://github.com/Ceyron/exponax): Efficient Differentiable n-d PDE solvers in JAX.
For more research on physics based deep learning research, please visit the website of [our research group at TUM](https://ge.in.tum.de/publications/).