Skip to content
This repository was archived by the owner on Sep 8, 2024. It is now read-only.

Latest commit

 

History

63 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

P-STMAE

This repository includes training and evaluation codes for P-STMAE model and RNN baselines. The specific version of code for different datasets can be found in the corresponding branches.

Running Experiments

Navigate to the desired branch of dataset and run the training script. For example, to train the P-STMAE model:

export PYTHONPATH='./'
python models/timae/train.py

Dataset Availability

The shallow water dataset is simulated with the script utils/simulate_sw.py. The diffusion reaction and compressible Navier-Stokes dataset are downloaded from PDEBench project. The NOAA sea surface temperature dataset can be accessed from NOAA website.

About

Predicting High-Dimensional Dynamical Systems with Irregular Time Steps Using Masked Autoencoders

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages