A convolutional neural network based Poisson solver
Project description
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.
An article describing the performance of our model is available on arXiv. A separate repository of Jupyter notebooks to generate the results outlined in the article is available.
Installation requires CUDA set up to work with tensorflow-gpu version 2.0.0 or newer. To install, please simply run
pip install poisson_CNN
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
poisson_CNN-0.2.0.tar.gz
(27.7 kB
view hashes)
Built Distribution
Close
Hashes for poisson_CNN-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 32a04f6095040ad168fa2d3f37eeb5c0eb094101d27a570062716072fc643fc0 |
|
MD5 | 1bc4e6afd47762419883a3328d835735 |
|
BLAKE2b-256 | bcf7cb998f8a9f1fd53fd442cf213b0ce476224c1d6d6b6899f51ba6960e0977 |