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

[Example] Add battery-electrochemical-performance prediction model #967

Open
wants to merge 1,380 commits into
base: develop
Choose a base branch
from

Conversation

huohuohuohuohuo123
Copy link

PR types

PR changes

Describe

HydrogenSulfate and others added 30 commits January 11, 2024 19:06
* fix coner case for FusedDerivativeNode is placed at the end of nodes group

* add UT for fuse derivatives

* fix bug
* update phygeonet doc

* fix model name
* refine documents and remove redundant blankline toml

* refine more documents
* update quick_start

* convert all  sh

* update version note for release 2.6

* update optimizer usage code
* [Add] arch examples

* [Change] examples

* [Change] examples

* [Change] register_input_transform

* [Change] data with rand

---------

Co-authored-by: HydrogenSulfate <[email protected]>
* [Add] phylstm examples

* [Change] phylstm examples

* [Change] remove blank line
* update docstring

* remove spaces in args

* update

* remove extra blank line
…ent Network for Solving Spatiotemporal PDEs (PaddlePaddle#674)

* Add files via upload

* Create readme.md

* Add files via upload

* Update __init__.py

* Add files via upload

* Add files via upload

* add

* add

* add

* add

* add

* add

* add

* add

* add

* add

* a

* a

* Update phycrnet.md

* Update phycrnet.md

* Update phycrnet.md

* a

* d

* d

* a

* a

* a

* a

* a

* a

* p

* a

* a

* a

* update .md file

* update .md file

* update .md file

* fix

* edit md

* eval

* m

* m

* edit

* edit

---------

Co-authored-by: WG <[email protected]>
Co-authored-by: wangguan <[email protected]>
* add 3 install method in README.md

* add more contributors
* (WIP)Add tutorial page

* fix document

* fix

* change split_to_dict and concat_to_tensor to staticmethod

* update batch_index class variable for all datasets

* move legend to outter-right of curve box and set dpi to 200

* add 1 more aistudio url
* update copyright header

* update docstring of PhyCRNet
* add RegAE example

* add RegAE

---------

Co-authored-by: HydrogenSulfate <[email protected]>
* add validation for hydra config

* update unitest for pydantic

* fix for OptimizerList

* fix
…med neural networks for the incompressible Navier-Stokes equations (PaddlePaddle#670)

* Add files via upload

* add

* add

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* a

* edit

* m

* edit

* a

* Update nsfnet4.md

* m

* m

* Update nsfnet4.md

* finish

* m

* debug

* edit

* add

* a

* a

* a

* a

* a

* a

* a

* d

* Update nsfnet4.md

* d

* d

* d

* d

* over

* reformat docs

* fix inference

* fix lr scheduler

---------

Co-authored-by: WG <[email protected]>
Co-authored-by: wangguan <[email protected]>
* add yinglong inference code

* add readme file for yinglong

* update yinglong predict code

* add copyright in predict_12layers.py

* update readme

* add reference for timefeatures.py

* update predict_12layers and readme
* (WIP)fix doctest and refine document

* update docs

* fix wrong code in ldc2d

* update code

* update paranoma

* fix

* refine doc
* add yinglong inference code

* add readme file for yinglong

* update yinglong predict code

* add copyright in predict_12layers.py

* update readme

* add reference for timefeatures.py

* update predict_12layers and readme

* add visualize and update readme

* add figure for yinglong

* update yinglong readme

* fix readme for yinglong

* add predict for yinglong 24 layers

* update readme

* add plot for yinglong

* update predict code

* update readme

* update file path

* add version check

* fix doc string

* update readme
@huohuohuohuohuo123
Copy link
Author

您好,文档部分的格式进行了一些修改,辛苦看一下,哪里是否需要修改

@leeleolay
Copy link

文档的部分辛苦按照链接里的教程再修改一下吧
https://paddlescience-docs.readthedocs.io/zh-cn/latest/zh/development/#3

@leeleolay leeleolay removed their assignment Nov 1, 2024
@huohuohuohuohuo123
Copy link
Author

您好,已经按照文档链接修改了,辛苦看下哪里还有问题

@leeleolay
Copy link

leeleolay commented Nov 11, 2024

1.加载文档的时候,该案例为能正确显示,还存在一些bug:
image
2.另外example里的文件里,我看到有数据集,辛苦整理到一个文件夹里;
3.另外辛苦修正完后再运行一下检查一些是否有运行过程中存在的一些bug

关于训练好的模型权重文件,已经上传到云上,您可以将这个权重文件的链接参考其他案例附到案例介绍的文档中
https://paddle-org.bj.bcebos.com/paddlescience/models/MLP_LI/MLP_LI_pretrained.pdparams

@huohuohuohuohuo123
Copy link
Author

您好,之前说的问题已经修改,辛苦看一下哪里还有问题

@leeleolay
Copy link

leeleolay commented Nov 12, 2024

image
运行MLP_LI.py文件运行错误,如果需要安装第三方包,请在文档里表明要安装的依赖包,并在文档里注明训练命令和数据集。文件夹中的数据集的位置比较散乱,请做一下整理。关于result_out,这个文件夹的作用是什么?里面还有一些图片格式的文件,看起来是补充文档里的信息,如何只和文档有关,请移动到文档相关的位置。

@huohuohuohuohuo123
Copy link
Author

您好,已提交修改,辛苦看一下

@leeleolay
Copy link

leeleolay commented Jan 2, 2025

有如下问题,辛苦确认一下:
1.精度问题:
按照文档运行python MLP_LI.p,测试结果的精度和文档里有差距
58c1bbc6180a76b34d3ed602d9deb35b
2.文件存储路径问题,有中文,数据集改为data比较好
95e68c9bd543f611022c223e546a17cf

@huohuohuohuohuo123
Copy link
Author

训练结果 我这边的训练结果和文档中是一致的,不知道是什么原因和你运行的结果和文档的结果有差距,其他问题已经更正,辛苦看一下

@leeleolay
Copy link

leeleolay commented Jan 12, 2025

提供的MLP_LI.py文件里没有提供加载预训练模型的代码和测试预训练模型的相关代码,使用提供的代码进行训练得到的模型进行测试后的精度结果是我发出的图片里的数字。
image
屏幕打印消息V C E建议在文档中表明各个符号的含义

@huohuohuohuohuo123
Copy link
Author

您好,已经修改,辛苦看一下

Copy link
Collaborator

Choose a reason for hiding this comment

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

这里的换行可以删除

Comment on lines +55 to +58




Copy link
Collaborator

Choose a reason for hiding this comment

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

Suggested change

Copy link
Collaborator

Choose a reason for hiding this comment

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

该权重文件已上传:https://paddle-org.bj.bcebos.com/paddlescience%2Fmodels%2FMLP_LI_pretrained.pdparams

可以在PR中删除这个文件,然后相关的权重链接更新为该url即可

Copy link
Collaborator

Choose a reason for hiding this comment

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

这个文件能使用vscode的markdown格式化插件格式化一下吗?如果没有安装vscode的话就算了

Copy link
Collaborator

Choose a reason for hiding this comment

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

这个文件跟另一个docs下的同名文件是什么关系?

Copy link
Collaborator

@HydrogenSulfate HydrogenSulfate left a comment

Choose a reason for hiding this comment

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

我上传了必要的文件,一些重复的文件可以删除,文档顺便更新一下

Copy link
Collaborator

Choose a reason for hiding this comment

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

Copy link
Collaborator

Choose a reason for hiding this comment

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

Copy link
Collaborator

Choose a reason for hiding this comment

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

Copy link
Collaborator

Choose a reason for hiding this comment

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

Copy link
Collaborator

Choose a reason for hiding this comment

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

Copy link
Collaborator

Choose a reason for hiding this comment

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

=== "模型训练命令"

``` sh
python MLP_LI.py
Copy link
Collaborator

Choose a reason for hiding this comment

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

训练命令上面请参考:https://paddlescience-docs.readthedocs.io/zh-cn/latest/zh/examples/allen_cahn/#__tabbed_1_1,添加数据集下载的命令

``` sh
python MLP_LI.py
```

Copy link
Collaborator

Choose a reason for hiding this comment

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

请添加模型评估命令,即直接基于下面训练好的模型进行评估

Copy link
Collaborator

Choose a reason for hiding this comment

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

模型训练和评估建议放到train和evaluate函数里,不要直接写在一起

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.