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 applications. 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 identical to the GUI of the local version of Sapsan, except lacking the ability to edit the model code on the fly.

pypi pypi DOI

Documentation

Please refer to Sapsan's Wiki for detailed installation, tutorials, troubleshooting, and API, as well as to learn more about the framework's 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. Install via pip (recommended)

pip install sapsan

OR Clone from git

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

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

3. Test Installation

To make sure everything is alright, run a test of your setup:

sapsan test

4. Run Examples

To get started and familiarize yourself with the interface, feel free to run the included examples (CNN, PIMLTurb, PICAE or on 3D data, and KRR on 2D data). To copy the examples, type:

sapsan get_examples

This will create a folder ./sapsan_examples with appropriate example jupyter notebooks.

5. Create Custom Projects!

To start a custom project, designing your own custom estimator, i.e., network, go ahead and run:

sapsan create {name}

where {name} should be replaced with your custom project name. As a result, a pre-filled template for the estimator, a jupyter notebook to run everything from, and Docker will be initialized.


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-0.6.5.tar.gz (11.0 MB view details)

Uploaded Source

Built Distribution

sapsan-0.6.5-py3-none-any.whl (11.0 MB view details)

Uploaded Python 3

File details

Details for the file sapsan-0.6.5.tar.gz.

File metadata

  • Download URL: sapsan-0.6.5.tar.gz
  • Upload date:
  • Size: 11.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for sapsan-0.6.5.tar.gz
Algorithm Hash digest
SHA256 00ba4aae52490d1ece60685a68fec9a831bed426124d2f3e2dd87e29cd885124
MD5 3de8f8980cca734e38a031ea20cc165a
BLAKE2b-256 b315ad32ed4da356f86552553e821039356cb15c392d220e1f9756b2f16f1259

See more details on using hashes here.

File details

Details for the file sapsan-0.6.5-py3-none-any.whl.

File metadata

  • Download URL: sapsan-0.6.5-py3-none-any.whl
  • Upload date:
  • Size: 11.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for sapsan-0.6.5-py3-none-any.whl
Algorithm Hash digest
SHA256 2864f4d6a9ba454cfb9765ba110dfdfca77fcbf9b80a8d039a88ac4a9e7af193
MD5 7d4f95d4a4e0fe9de6207e5e91102eee
BLAKE2b-256 2e200d9a5ba4a5068025eff53837346d3a5e2da2d091ac3c1fbbca9be3e065fa

See more details on using hashes here.

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