runinchaos

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

FluidX3D

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs via OpenCL. Free for non-commercial use.

GraphSAGE

Representation learning on large graphs using stochastic graph convolutions.

graphSAGE-pytorch

A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE.

Physics-Informed-Neural-Networks

Investigating PINNs

diffusion-net

Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.

stl_tools

Python code to produce STL geometry files from plain text, LaTeX code, and 2D numerical arrays (matrices)

hyStrath

Hypersonic / Rarefied gas dynamics code developments (GPL-3.0)

dafoam

DAFoam: Discrete Adjoint with OpenFOAM for High-fidelity Multidisciplinary Design Optimization

2D-Bin-Packing

Library to solve 2D bin packing problems with irregular pieces.

DRLinFluids

An open-source Python platform of coupling deep reinforcement learning and OpenFOAM

2D-Irregular-Packing-Algorithm

Realize 2D irregular packing algorithm with python

cfd-gcn

nest2D

Nest2D is a 2D bin packaging tool for python.

svg-to-stl

Turn 2-Dimensional SVG Paths into 3-Dimensional STL Meshes

ffx

Fast Function Extraction

dugksFoam

An OpenFOAM solver for Boltzmann model equation using discrete unified gas kinetic scheme

pinn-torch

PINN (Physics-Informed Neural Networks) on Navier-Stokes Equations

MGN

MeshGraphNets (MGN)

coronary-mesh-convolution

Implementation accompanying our STACOM (MICCAI) 2021 paper (https://doi.org/10.1007/978-3-030-93722-5_11)

Nautiterm

Open a terminal of your choice from Nautilus

EpiGNN

[ECML-PKDD2022] EpiGNN: Exploring Spatial Transmission with Graph Neural Network for Regional Epidemic Forecasting

colagnn

ICLR_NACA_Dataset_V0

In this repository, you will find the different python scripts to train the available models on the 2D incompressible steady-state RAND solutions over NACA airfoils proposed at the Geometrical and Topological Representation Learning Workshop at ICLR 2022.

KOSSTPDA

Progressive data-aumgented k-omega SST model for OpenFoam

turbulent-dispersion-neuralSDE

Modelling particle turbulent dispersion with stochastic differential equations, learned from artificial neural networks using tensorflow/keras.

CityTransformer

Plume dispersion prediction in an urban area with a deep learning model

covid-transmission

Custom scalar-transport solvers for modeling aerosol transmission based on buoyantBoussinesqPimpleFoam with OpenFOAM v1906

PANS_OpenFOAMv2112

MSc graduation thesis

OpenFOAM.buoyantBoussinesqSimpleFoam.windAroundBuildings