Pinned Repositories
2D-Navier-Stokes-Solver
As the field of Computational Fluid Dynamics (CFD) progresses, the fluid flows are more and more analysed by using simulations with the help of high speed computers. In order to solve and analyse these fluid flows we require intensive simulation involving mathematical equations which governs the fluid flow, these are Navier Stokes (NS) equation. Solving these equations has become a necessity as almost every problem which is related to fluid flow analysis call for solving of Navier Stokes equation. These NS equations are partial differential equations so different numerical methods are used to solve these equations. Solving these partial differential equations so different numerical methods requires large amount of computing power and huge amount of memory is in play. Only practical feasible way to solve these equation is write a parallel program to solve them, which can then be run on powerful hardware capable of parallel processing to get the desired results High speed supercomputer will provide us very good performance in terms of reduction in execution time. In paper focus will be on finite volume as a numerical method. We will also see what GPGPU (General-Purpose computing on Graphics Processing Units) is and how we are taking its advantages to solve CFD problems.
3DUnetCNN
Keras 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
AID1906
Tarena training course
algo
数据结构和算法必知必会的50个代码实现
awesome-latex-cv
Latex CV template built with Font Awesome.
awesome-public-datasets
A topic-centric list of high-quality open datasets in public domains. Propose NEW data ☛☛☛PR☛☛☛
BasicOpenFOAMProgrammingTutorials
Introduces basic C++ concepts to beginner users of the OpenFOAM open-source CFD libraries.
bayesgan
Tensorflow code for the Bayesian GAN (https://arxiv.org/abs/1705.09558) (NIPS 2017)
boreas
Random Forests for Film Cooling Package
brain-tokyo-workshop
🧠🗼
QiWang-SJTU's Repositories
QiWang-SJTU/cfd-gcn
QiWang-SJTU/CFDPython
A sequence of Jupyter notebooks featuring the "12 Steps to Navier-Stokes" http://lorenabarba.com/
QiWang-SJTU/circuit_training
QiWang-SJTU/deeponet
Learning nonlinear operators via DeepONet
QiWang-SJTU/deepxde
Deep learning library for solving differential equations and more
QiWang-SJTU/dominant-balance
Methods and code for J. L. Callaham, J. N. Kutz, B. W. Brunton, and S. L. Brunton (2020)
QiWang-SJTU/drl_shape_optimization
Deep reinforcement learning to perform shape optimization
QiWang-SJTU/engauge-digitizer
Extracts data points from images of graphs
QiWang-SJTU/fenics-DRL
Repository from the paper https://arxiv.org/abs/1908.04127, to train Deep Reinforcement Learning in Fluid Mechanics Setup.
QiWang-SJTU/FluTO
Graded Multiscale Fluid Topology Optimization using Neural Networks
QiWang-SJTU/fourier_neural_operator
Use Fourier transform to learn operators in differential equations.
QiWang-SJTU/geppy
A framework for gene expression programming (an evolutionary algorithm) in Python
QiWang-SJTU/graph-pde
Using graph network to solve PDEs
QiWang-SJTU/gym
A toolkit for developing and comparing reinforcement learning algorithms.
QiWang-SJTU/introRL
Intro to Reinforcement Learning (强化学习纲要）
QiWang-SJTU/jax-cfd
Computational Fluid Dynamics in JAX
QiWang-SJTU/learn2learn
A PyTorch Library for Meta-learning Research
QiWang-SJTU/leedeeprl-notes
李宏毅《深度强化学习》笔记，在线阅读地址：https://datawhalechina.github.io/leedeeprl-notes/
QiWang-SJTU/machine-learning-applied-to-cfd
Examples of how to use machine learning algorithms in computational fluid dynamics.
QiWang-SJTU/morphogenesis-resources
Comprehensive list of resources on the topic of digital morphogenesis (the creation of form through code). Includes links to major articles, code repos, creative projects, books, software, and more.
QiWang-SJTU/MTO
Parallel solver for thermal-fluid-structural topology optimization on structured grids.
QiWang-SJTU/MTO_new
New parallel solver on unstructured grids！
QiWang-SJTU/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
QiWang-SJTU/pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
QiWang-SJTU/Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions
Solutions of Reinforcement Learning, An Introduction
QiWang-SJTU/smarties
Lightweight and scalable framework for Reinforcement Learning
QiWang-SJTU/T-Blade3
T-Blade3 VERSION 1.2: T-Blade3 is a general parametric 3D blade geometry builder. The tool can create a variety of 3D blade geometries based on few basic parameters and limited interaction with a CAD system. The geometric and aerodynamic parameters are used to create 2D airfoils and these airfoils are stacked on the desired stacking axis. The tool generates a specified number of 2D blade sections in a 3D Cartesian coordinate system. The geometry modeler can also be used for generating 3D blades with special features like bent tip, split tip and other concepts, which can be explored with minimum changes to the blade geometry. The use of control points for the definition of splines makes it easy to modify the blade shapes quickly and smoothly to obtain the desired blade model. The second derivative of the mean-line (related to the curvature) is controlled using B-splines to create the airfoils. This is analytically integrated twice to obtain the mean-line. A smooth thickness distribution is then added to the airfoil with two options either the Wennerstrom distribution or a quartic B-spline thickness distribution. B-splines have also been implemented to achieve customized airfoil leading and trailing edges.
QiWang-SJTU/tbnns
Tensor Basis Neural Network for Scalar Mixing
QiWang-SJTU/tensorforce
Tensorforce: a TensorFlow library for applied reinforcement learning
QiWang-SJTU/Turbulent-Flow-Net