neural-fluid-fields

A small library for doing fluid simulation with neural networks.

https://github.com/tovacinni/neural-fluid-fields

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.9%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

A small library for doing fluid simulation with neural networks.

Basic Info
  • Host: GitHub
  • Owner: tovacinni
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 57.6 KB
Statistics
  • Stars: 23
  • Watchers: 6
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 4 years ago · Last pushed about 4 years ago
Metadata Files
Readme License Citation

README.md

Neural Fluid Fields

drawing

This is a small library for doing fluid simulation with neural fields. Check out our review paper, Neural Fields in Visual Computing and Beyond if you want to learn more about neural fields!

Code Organization

neuralff contains the bulk of the library. The library can be installed as a usual Python module, by doing python setup.py develop or any equivalent.

The library contains of several components:

The neuralff.ops module contains the core utility functions. In particular, neuralff/ops/fluid_physics_ops.py contains PDE loss functions, neuralff/ops/vector_ops.py contains differential operators, and neuralff/ops/fluid_ops.py contains functions for performing advection.

These functions generally take as input a neuralff.Field class, which can be a grid-based vector field, or a neural field so long as it can sample vectors on continuous coordinates with some mechanism.

Running the Demo

The demo is located in app. These are standalone demos which use the neuralff library to do things like real-time fluid simulation using neural fields.

The demo runs on glumpy and pycuda, which can be annoying to install. To install:

git clone https://github.com/inducer/pycuda git submodule update --recursive --init python configure.py --cuda-root=$CUDA_HOME --cuda-enable-gl python setup.py develop pip install pyopengl pip install glumpy

To run the demo, simply run python3 app/interactive_app.py.

To change the inital image of the animation, set an arbitrary image named test.png in ./data.

Owner

  • Name: Towaki
  • Login: tovacinni
  • Kind: user
  • Company: NVIDIA / UofT

research scientist at nvidia and phd student at uoft (the one in canada)

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Takikawa"
  given-names: "Towaki"
  orcid: "https://orcid.org/0000-0003-2019-1564"
- family-names: "Mozaffari"
  given-names: "Mohammad"
  orcid: "https://orcid.org/0000-0000-0000-0000"
title: "Neural Fluid Fields"
version: 1.0.0
date-released: 2021-12-07
url: "https://github.com/tovacinni/neural-fluid-fields"

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 0
  • Total pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
  • tovacinni (2)
Top Labels
Issue Labels
Pull Request Labels