Skip to main content

TBNN-s - Tensor Basis Neural Network for Scalar Mixing

Project description

## TBNN-s v0.5.0 - Tensor Basis Neural Network for Scalar Mixing

This package implements the vanilla Tensor Basis Neural Network [1] as the TBNN class, and also the Tensor Basis Neural Network for Scalar Flux Modeling [2] as the TBNNS class. They are described in the following references:

[1] Ling, Kurzawski, Templeton. “Reynolds averaged turbulence modelling using deep neural networks with embedded invariance.” J. Fluid Mech. 807 (2016)

[2] Milani, Ling, Eaton. “Turbulent scalar flux in inclined jets in crossflow: counter gradient transport and deep learning modelling” J. Fluid Mech. (under review)

Author: Pedro M. Milani (email:

Last modified: 08/06/2020

Developed and tested in Python 3.7 using tensorflow 1.15

### Installation To install, run the following (optionally within a virtual environment):

pip install tbnns [–user] [–upgrade]

This will install the stable version from the Python Package Index. Use the flag –user in case you do not have administrator privileges and the flag –upgrade to get the newest version.

To test the program while it is being developed, run the command below from the current directory. This is useful when you are developing the code.

pip install -e .

To uninstall, run:

pip uninstall tbnns

The commands above will also install some dependencies (included in the file “requirements.txt”) needed for this package.

### Examples and Testing

The folder test contains a script and three representative datasets. For an example of training a TBNN-s and applying it to a test set, run the following inside the folder test:



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

tbnns-0.5.0.tar.gz (35.6 kB view hashes)

Uploaded source

Built Distribution

tbnns-0.5.0-py3-none-any.whl (39.9 kB view hashes)

Uploaded py3

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