smyng91 Goto Github PK

ar-pde-cnn

Physics-constrained auto-regressive convolutional neural networks for dynamical PDEs

bayesgan

Tensorflow code for the Bayesian GAN (https://arxiv.org/abs/1705.09558) (NIPS 2017)

bayesian-neural-network-mnist

Bayesian neural network using Pyro and PyTorch on MNIST dataset

cans

A code for fast, massively-parallel direct numerical simulations (DNS) of canonical flows

cfd

Basic Computational Fluid Dynamics (CFD) schemes implemented in FORTRAN using Finite-Volume and Finite-Difference Methods. Sample simulations and figures are provided.

ctgan

Conditional GAN for generating synthetic tabular data.

deephx

DeepHX solves heat exchanger models using physics-informed neural networks.

deepxde

Deep learning library for solving differential equations

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

gan-for-tabular-data

We well know GANs for success in the realistic image generation. However, they can be applied in tabular data generation. We will review and examine some recent papers about tabular GANs in action.

gans-2.0

Generative Adversarial Networks in TensorFlow 2.0

gnn-powerflow

Graph Neural Network application in predicting AC Power Flow calculation. Developed with Pytorch Geometric framework.

gran

Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019

graph-generation

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

graph_nets

Build Graph Nets in Tensorflow

graphneuralsolver

graphneuralsolver_powerflow

Graph Neural Solver applied to power flow (non-linear equations)

grid2op

lesgo

The Large-Eddy Simulation framework from the Turbulence Research Group at Johns Hopkins University

liquidairplant

LiquidAirPlant is a MATLAB code allowing its users to model various liquid air power plant configurations driven by natural gas combustors, parabolic trough solar collectors, and/or ambient air.

lpinns

To address some of the failure modes in training of physics informed neural networks, a Lagrangian architecture is designed to conform to the direction of travel of information in convection-diffusion equations, i.e., method of characteristic; The repository includes a pytorch implementation of PINN and proposed LPINN with periodic boundary conditions

mad-gans

Applied generative adversarial networks (GANs) to do anomaly detection for time series data

multi-fidelity-dnns-pinns

neural-fortran

A parallel neural net microframework

pycycle

Thermodynamic cycle modeling library, built on top of OpenMDAO

pypownet

A power network simulator with a Reinforcement Learning-focused usage.

rgan

Recurrent (conditional) generative adversarial networks for generating real-valued time series data.

sciann

Deep learning for Engineers - Physics Informed Deep Learning

sdgym

Benchmarking synthetic data generation methods.

smallsample_highdim

Solving high-dimensional toy problems with small samples