Final report with code for KAIST Course KSE 801.

Overview

🧮 KSE 801 Final Report with Code

This is the final report with code for KAIST course KSE 801.

Author: Chuanbo Hua, Federico Berto.

💡 Introduction About the OSC

Orthogonal collocation is a method for the numerical solution of partial differential equations. It uses collocation at the zeros of some orthogonal polynomials to transform the partial differential equation (PDE) to a set of ordinary differential equations (ODEs). The ODEs can then be solved by any method. It has been shown that it is usually advantageous to choose the collocation points as the zeros of the corresponding Jacobi polynomial (independent of the PDE system) [1].

Orthogonal collocation method was famous at 1970s, mainly developed by BA Finlayson [2]. Which is a powerful collocation tool in solving partial differential equations and ordinary differential equations.

Orthogonal collocation method works for more than one variable, but here we only choose one variable cases, since this is more simple to understand and most widely used.

💡 Introduction About the GNN

You can find more details from the jupter notebook within gnn-notebook folder. We include the dataset init, model training and test in the folder.

Reminder: for dataset, we provide another repository for dataset generator. Please refer to repo: https://github.com/DiffEqML/pde-dataset-generator.

🏷 Features

  • Turoritals. We provide several examples, including linear and nonlinear problems to help you to understand how to use it and the performance of this model.
  • Algorithm Explanation. We provide a document to in detail explain how this alogirthm works by example, which we think it's easier to get. For more detail, please refer to Algorithm section.

⚙️ Requirement

Python Version: 3.6 or later
Python Package: numpy, matplotlib, jupyter-notebook/jupyter-lab, dgl, torch

🔧 Structure

  • src: source code for OSC algorithm.
  • fig: algorithm output figures for readme
  • osc-notebook: tutorial jupyter notebooks about our osc method
  • gnn-notebook: tutorial jupyter notebooks about graph neural network
  • script: some training and tesing script of the graph neural network

🔦 How to use

Step 1. Download or Clone this repository.

Step 2. Refer to osc-notebook/example.ipynb, it will introduce how to use this model in detail by examples. Main process would be

  1. collocation1d(): generate collocation points.
  2. generator1d(): generate algebra equations from PDEs to be solved.
  3. numpy.linalg.solve(): solve the algebra equations to get polynomial result,
  4. polynomial1d(): generate simulation value to check the loss.

Step 3. Refer to notebooks under gnn-notebook to get the idea of training graph model.

📈 Examples

One variable, linear, 3 order Loss: <1e-4

One variable, linear, 4 order Loss: 2.2586

One variable, nonlinear Loss: 0.0447

2D PDEs Simulation

Dam Breaking Simulation

📜 Algorithm

Here we are going to simply introduce how 1D OSC works by example. Original pdf please refer to Introduction.pdf in this repository.

📚 References

[1] Orthogonal collocation. (2018, January 30). In Wikipedia. https://en.wikipedia.org/wiki/Orthogonal_collocation.

[2] Carey, G. F., and Bruce A. Finlayson. "Orthogonal collocation on finite elements." Chemical Engineering Science 30.5-6 (1975): 587-596.

Owner
Chuanbo HUA
HIT, POSTECH, KAIST.
Chuanbo HUA
GMFlow: Learning Optical Flow via Global Matching

GMFlow GMFlow: Learning Optical Flow via Global Matching Authors: Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Dacheng Tao We streamline the

Haofei Xu 298 Jan 04, 2023
Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)

Self-Tuning for Data-Efficient Deep Learning This repository contains the implementation code for paper: Self-Tuning for Data-Efficient Deep Learning

THUML @ Tsinghua University 101 Dec 11, 2022
This is a simple framework to make object detection dataset very quickly

FastAnnotation Table of contents General info Requirements Setup General info This is a simple framework to make object detection dataset very quickly

Serena Tetart 1 Jan 24, 2022
Non-Official Pytorch implementation of "Face Identity Disentanglement via Latent Space Mapping" https://arxiv.org/abs/2005.07728 Using StyleGAN2 instead of StyleGAN

Face Identity Disentanglement via Latent Space Mapping - Implement in pytorch with StyleGAN 2 Description Pytorch implementation of the paper Face Ide

Daniel Roich 58 Dec 24, 2022
Repositorio de los Laboratorios de Análisis Numérico / Análisis Numérico I de FAMAF, UNC.

Repositorio de los Laboratorios de Análisis Numérico / Análisis Numérico I de FAMAF, UNC. Para los Laboratorios de la materia, vamos a utilizar el len

Luis Biedma 18 Dec 12, 2022
RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation

RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation Anonymous submission Abstract 3D obj

30 Sep 16, 2022
[ECE NTUA] 👁 Computer Vision - Lab Projects & Theoretical Problem Sets (2020-2021)

Computer Vision - NTUA (2020-2021) This repository hosts the lab projects and theoretical problem sets of the Computer Vision course held by ECE NTUA

Dimitris Dimos 6 Jul 21, 2022
[NeurIPS2021] Code Release of Learning Transferable Perturbations

Learning Transferable Adversarial Perturbations This is an official release of the paper Learning Transferable Adversarial Perturbations. The code is

Krishna Kanth 17 Nov 11, 2022
InferPy: Deep Probabilistic Modeling with Tensorflow Made Easy

InferPy: Deep Probabilistic Modeling Made Easy InferPy is a high-level API for probabilistic modeling written in Python and capable of running on top

PGM-Lab 141 Oct 13, 2022
Make your master artistic punk avatar through machine learning world famous paintings.

Master-art-punk Make your master artistic punk avatar through machine learning world famous paintings. 通过机器学习世界名画制作属于你的大师级艺术朋克头像 Nowadays, NFT is beco

Philipjhc 53 Dec 27, 2022
A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

SEAL ⠀⠀⠀ A PyTorch implementation of Semi-Supervised Graph Classification: A Hierarchical Graph Perspective (WWW 2019) Abstract Node classification an

Benedek Rozemberczki 202 Dec 27, 2022
Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

PixelTransformer Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation". Project Page Installation Please insta

Shubham Tulsiani 24 Dec 17, 2022
Cascading Feature Extraction for Fast Point Cloud Registration (BMVC 2021)

Cascading Feature Extraction for Fast Point Cloud Registration This repository contains the source code for the paper [Arxive link comming soon]. Meth

7 May 26, 2022
NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Xintao 593 Jan 03, 2023
Automatically replace ONNX's RandomNormal node with Constant node.

onnx-remove-random-normal This is a script to replace RandomNormal node with Constant node. Example Imagine that we have something ONNX model like the

Masashi Shibata 1 Dec 11, 2021
Subnet Replacement Attack: Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

Subnet Replacement Attack: Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks Official implementation of paper Towards Practic

Xiangyu Qi 8 Dec 30, 2022
Experiments with differentiable stacks and queues in PyTorch

Please use stacknn-core instead! StackNN This project implements differentiable stacks and queues in PyTorch. The data structures are implemented in s

Will Merrill 141 Oct 06, 2022
Codebase for Diffusion Models Beat GANS on Image Synthesis.

Codebase for Diffusion Models Beat GANS on Image Synthesis.

Katherine Crowson 128 Dec 02, 2022
Tiny-NewsRec: Efficient and Effective PLM-based News Recommendation

Tiny-NewsRec The source codes for our paper "Tiny-NewsRec: Efficient and Effective PLM-based News Recommendation". Requirements PyTorch == 1.6.0 Tensor

Yang Yu 3 Dec 07, 2022
OpenDelta - An Open-Source Framework for Paramter Efficient Tuning.

OpenDelta is a toolkit for parameter efficient methods (we dub it as delta tuning), by which users could flexibly assign (or add) a small amount parameters to update while keeping the most paramters

THUNLP 386 Dec 26, 2022