From 101359ea7d4cc7f86d53cedec968f2cbbf2965ee Mon Sep 17 00:00:00 2001 From: weipengOO98 Date: Mon, 15 Aug 2022 11:16:03 +0800 Subject: [PATCH 1/2] docs: Add figure description. --- README.md | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) diff --git a/README.md b/README.md index c8018d1..5ba0465 100644 --- a/README.md +++ b/README.md @@ -7,10 +7,7 @@ [![DockerHub](https://img.shields.io/docker/pulls/idrl/idrlnet.svg)](https://hub.docker.com/r/idrl/idrlnet) [![CodeFactor](https://www.codefactor.io/repository/github/idrl-lab/idrlnet/badge/master)](https://www.codefactor.io/repository/github/idrl-lab/idrlnet/overview/master) - -**IDRLnet** is a machine learning library on top of [PyTorch](https://pytorch.org/). Use IDRLnet if you need a machine -learning library that solves both forward and inverse differential equations via physics-informed neural -networks (PINN). IDRLnet is a flexible framework inspired by [Nvidia Simnet](https://developer.nvidia.com/simnet>). +**IDRLnet** is a machine learning library on top of [PyTorch](https://pytorch.org/). Use IDRLnet if you need a machine learning library that solves both forward and inverse differential equations via physics-informed neural networks (PINN). IDRLnet is a flexible framework inspired by [Nvidia Simnet](https://developer.nvidia.com/simnet>). ## Docs @@ -66,22 +63,14 @@ pip install -e . IDRLnet supports -- complex domain geometries without mesh generation. Provided geometries include interval, triangle, rectangle, polygon, - circle, sphere... Other geometries can be constructed using three boolean operations: union, difference, and - intersection; - +- complex domain geometries without mesh generation. Provided geometries include interval, triangle, rectangle, polygon, circle, sphere... Other geometries can be constructed using three boolean operations: union, difference, and intersection; + ![Geometry](https://raw.githubusercontent.com/weipeng0098/picture/master/20210617081809.png) - sampling in the interior of the defined geometry or on the boundary with given conditions. - -- enables the user code to be structured. Data sources, operations, constraints are all represented by ``Node``. The graph - will be automatically constructed via label symbols of each node. Getting rid of the explicit construction via - explicit expressions, users model problems more naturally. - +- enables the user code to be structured. Data sources, operations, constraints are all represented by ``Node``. The graph will be automatically constructed via label symbols of each node. Getting rid of the explicit construction via explicit expressions, users model problems more naturally. - solving variational minimization problem; - + miniface - solving integral differential equation; - - adaptive resampling; - - recover unknown parameters of PDEs from noisy measurement data. It is also easy to customize IDRLnet to meet new demands. @@ -99,12 +88,10 @@ First off, thanks for taking the time to contribute! - **Reporting bugs.** To report a bug, simply open an issue in the GitHub "Issues" section. -- **Suggesting enhancements.** To submit an enhancement suggestion for IDRLnet, including completely new features and - minor improvements to existing functionality, let us know by opening an issue. - -- **Pull requests.** If you made improvements to IDRLnet, fixed a bug, or had a new example, feel free to send us a - pull-request. - +- **Suggesting enhancements.** To submit an enhancement suggestion for IDRLnet, including completely new features and minor improvements to existing functionality, let us know by opening an issue. + +- **Pull requests.** If you made improvements to IDRLnet, fixed a bug, or had a new example, feel free to send us a pull-request. + - **Asking questions.** To get help on how to use IDRLnet or its functionalities, you can as well open an issue. - **Answering questions.** If you know the answer to any question in the "Issues", you are welcomed to answer. From fcf781d5dd6746d271b2dd50efac22417a7d7f24 Mon Sep 17 00:00:00 2001 From: weipengOO98 Date: Mon, 15 Aug 2022 14:27:02 +0800 Subject: [PATCH 2/2] docs: Add figure description. --- README.md | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 5ba0465..208dbc9 100644 --- a/README.md +++ b/README.md @@ -65,12 +65,26 @@ IDRLnet supports - complex domain geometries without mesh generation. Provided geometries include interval, triangle, rectangle, polygon, circle, sphere... Other geometries can be constructed using three boolean operations: union, difference, and intersection; ![Geometry](https://raw.githubusercontent.com/weipeng0098/picture/master/20210617081809.png) -- sampling in the interior of the defined geometry or on the boundary with given conditions. -- enables the user code to be structured. Data sources, operations, constraints are all represented by ``Node``. The graph will be automatically constructed via label symbols of each node. Getting rid of the explicit construction via explicit expressions, users model problems more naturally. + +- sampling in the interior of the defined geometry or on the boundary with given conditions. + +- enables the user code to be structured. Data sources, operations, constraints are all represented by ``Node``. The graph will be automatically constructed via label symbols of each node. Getting rid of the explicit construction via explicit expressions, users model problems more naturally. + +- builds computational graph automatically; + + ![computationDomain](https://raw.githubusercontent.com/weipeng0098/picture/master/20220815142531.png) + +- user-defined callbacks; + + ![callback](https://raw.githubusercontent.com/weipeng0098/picture/master/20220815142621.png) + - solving variational minimization problem; miniface -- solving integral differential equation; -- adaptive resampling; + +- solving integral differential equation; + +- adaptive resampling; + - recover unknown parameters of PDEs from noisy measurement data. It is also easy to customize IDRLnet to meet new demands.