Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

【Hackathon 8th No.15】Diffeomorphism Neural Operator 论文复现 #1088

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
69 changes: 69 additions & 0 deletions rfcs/Science/20250310_DpNO.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
# Diffeomorphism-Neural-Operator 设计文档

> RFC 文档相关记录信息
| | |
| ------------ | ------------------ |
| 提交作者 | a162837 |
| 提交时间 | 2025-03-10 |
| RFC 版本号 | v1.0 |
| 依赖飞桨版本 | release 3.0 版本 |
| 文件名 | 20250310_DpNO.md |

## 1. 概述

### 1.1 相关背景

[NO.15 Diffeomorphism Neural Operator 论文复现](https://github.com/PaddlePaddle/community/blob/master/hackathon/hackathon_8th/%E3%80%90Hackathon_8th%E3%80%91%E4%B8%AA%E4%BA%BA%E6%8C%91%E6%88%98%E8%B5%9B%E2%80%94%E5%A5%97%E4%BB%B6%E5%BC%80%E5%8F%91%E4%BB%BB%E5%8A%A1%E5%90%88%E9%9B%86.md#no15-diffeomorphism-neural-operator-%E8%AE%BA%E6%96%87%E5%A4%8D%E7%8E%B0)

论文主要尝试解决在不同几何域和参数下求解偏微分方程(PDEs)的问题。传统的数值方法在处理不同几何域和参数时非常耗时和资源密集,因为每次参数或几何域发生变化都需要重新计算。论文提出了一种新的神经算子学习框架,称为Diffeomorphism Neural Operator(DNO),该框架可以将不同物理域映射到一个通用域上,从而在通用域上学习PDE的解,进而提高模型的泛化能力和计算效率。

### 1.2 功能目标

1. 复现 Diffeomorphism-Neural-Operator 代码,实现完整的推理流程。
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

实现完整的推理流程 -> 实现完整的训练、推理流程

2. 保持精度与论文精度一致,相对误差在 ±10% 以内。
3. 产出论文相关文档、图片、视频等。

### 1.3 意义

复现 Diffeomorphism-Neural-Operator 代码,能够使用 Diffeomorphism-Neural-Operator 模型进行推理。
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

进行推理。 -> 进行完整的训练、推理。


## 2. PaddleScience 现状

PaddleScience 套件暂无 Diffeomorphism-Neural-Operator 代码案例。

## 3. 目标调研

- 论文解决的问题:
Diffeomorphism-Neural-Operator 模型用于在不同几何域和参数下高效求解偏微分方程(PDEs),DNO通过将不同物理域微分同胚映射到一个通用域上,将不同域上的PDE求解问题转化为通用域上的问题。该框架结合了物理域和通用域的几何信息,通过神经算子学习参数函数与解函数之间的映射关系。
- 链接:
代码:[https://github.com/Zhaozhiwhy/Diffeomorphism-Neural-Operator](https://github.com/Zhaozhiwhy/Diffeomorphism-Neural-Operator)
论文:[https://arxiv.org/abs/2402.12475](https://arxiv.org/abs/2402.12475)

需将 Pytorch 代码转换为 Paddle

## 4. 设计思路与实现方案

参考 PaddleScience 已有代码实现 Diffeomorphism-Neural-Operator

1. 数据预处理
2. 模型构建
3. 超参数设定
4. 模型推理的评估指标

### 4.1 补充说明[可选]


## 5. 测试和验收的考量

复现 Diffeomorphism-Neural-Operator 中的模型,跑通对应的推理。

## 6. 可行性分析和排期规划

- 202503:调研
- 202503:复现代码并作调整
- 202504:整理项目产出,撰写案例文档

## 7. 影响面

丰富 PaddleScience 的应用案例,在 ppsci.arch 中新增 Diffeomorphism-Neural-Operator model