Skip to content

yakovlev31/graphpdes_experiments

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Description

Code for reproducing experiments from Learning continuous-time PDEs from sparse data with graph neural networks.

Data can be downloaded here.

You will need to install graphpdes before running the scripts.

The data comes in the following format:

  • t (time grid) ndarray with shape (simulations, timepoints)
  • x (node positions) ndarray with shape (simulations, nodes, grid dimension)
  • u (field) ndarray with shape (simulations, timepoints, nodes, field dimension)
  • bcs_dicts (only for Dirichlet BCs) - dictionary {'bc_name': [[bc_node_indices], [field_indices]], etc}. Used to zero the predicted time derivative of u at nodes in bc_node_indices and field dimensions in field_indices.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages