A convolutional neural network based Poisson solver
Project description
poisson_CNN
poisson_CNN is a convolutional neural network model whih estimates the solution of the Poisson equation with four Dirichlet boundary conditions on rectangular grids of variable sizes.
Installation requires CUDA set up to work with tensorflow-gpu version 2.3 or newer. To install, please use the Dockerfile appropriate for your CPU architecture (in most cases, docker/Dockerfile-amd64
)
An article describing the performance of our model is available: journal | arXiv
If you use this repo in your work, please cite our paper:
Özbay AG, Hamzehloo A, Laizet S, Tzirakis P, Rizos G, Schuller B. Poisson CNN: Convolutional neural networks for the solution of the Poisson equation on a Cartesian mesh. Data-Centric Engineering. [Online] Cambridge University Press; 2021;2: e6. Available from: doi:10.1017/dce.2021.7
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 poisson_CNN-0.3.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8292edd8129a335e41cca122abafda23cd10082125613859afdc468f6b0129cc |
|
MD5 | 988d880510e73ec85da50066dbd882cb |
|
BLAKE2b-256 | 825aaccf863c4c74fbe7feca1e0524489aebad572c513df1e644b4212c0474c2 |