Skip to main content

Sapsan project

Project description

Sapsan Sapsan logo

Sapsan is a pipeline for Machine Learning (ML) based turbulence modeling. While turbulence is important in a wide range of mediums, the pipeline primarily focuses on astrophysical application. With Sapsan, one can create their own custom models or use either conventional or physics-informed ML approaches for turbulence modeling included with the pipeline (estimators). Sapsan is designed to take out all the hard work from data preparation and analysis, leaving you focused on ML model design, layer by layer.

Feel free to check out a website version at sapsan.app. The interface is indentical to the GUI of the local version of Sapsan, except lacking the ability to edit the model code on the fly.

Sapsan's Wiki

Please refer to Sapsan's github wiki to learn more about framework's details and capabilities.

Quick Start

1. Install PyTorch (prerequisite)

Sapsan can be run on both cpu and gpu. Please follow the instructions on PyTorch to install the latest version (torch>=1.7.1 & CUDA>=11.0).

2. Clone from git (recommended)

git clone https://github.com/pikarpov-LANL/Sapsan.git
cd Sapsan/
python setup.py install

OR Install via pip

pip install sapsan

Note: see Installation Page on the Wiki for complete instructions with Graphviz and Docker installation.

Run Examples

To make sure everything is alright and to familiarize yourself with the interface, please run the following CNN example on 3D data:

jupyter notebook sapsan/examples/cnn_example.ipynb

alternatively, you can try out the physics-informed convolutional auto-encoder (PICAE) example on random 3D data:

jupyter notebook sapsan/examples/picae_example.ipynb

or a KRR example on 2D data:

jupyter notebook sapsan/examples/krr_example.ipynb

Sapsan has a BSD-style license, as found in the LICENSE file.

© (or copyright) 2019. Triad National Security, LLC. All rights reserved. This program was produced under U.S. Government contract 89233218CNA000001 for Los Alamos National Laboratory (LANL), which is operated by Triad National Security, LLC for the U.S. Department of Energy/National Nuclear Security Administration. All rights in the program are reserved by Triad National Security, LLC, and the U.S. Department of Energy/National Nuclear Security Administration. The Government is granted for itself and others acting on its behalf a nonexclusive, paid-up, irrevocable worldwide license in this material to reproduce, prepare derivative works, distribute copies to the public, perform publicly and display publicly, and to permit others to do so.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sapsan-0.2.11.tar.gz (50.9 kB view hashes)

Uploaded Source

Built Distribution

sapsan-0.2.11-py3-none-any.whl (68.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page