DynaBench documentation
Date: Jul 04, 2024 Version: 0.3.5
Useful links: Install | Source Repository | Dataset |
DynaBench (pronounced “Die-Nah-Bench”) is an open-source benchmark dataset for evaluating deep learning models for all sort of task concerning physical spatiotemporal systems. The DynaBench package started as a benchmark dataset for learning dynamical systems from low-resolution data. It has since evolved into a full-fledged package for generating synthetic data, training models, and evaluating them on various tasks concerning partial differential equations. The package is designed to be easy to use and flexible, allowing for easy extension and modification of the existing models, data generation algorithms and physical equations.
Getting Started
The Getting Started guide will help you get started with DynaBench. It shows how to download the data use our data iterator.
API reference
The reference guide contains a description of the DynaBench components.
Benchmark results
The benchmark results show the performance of different models on the DynaBench dataset.
Paper
The DynaBench paper has been published in the Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2023. The paper describes the benchmark and the results in detail.