-
Notifications
You must be signed in to change notification settings - Fork 294
【Hackathon 6th No.39】XPINN 迁移至 PaddleScience #835
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 6th No.39】XPINN 迁移至 PaddleScience #835
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
感谢提交PR,辛苦看一下comment
2. 模型构建 | ||
|
||
在 `ppsci.arc` 中实现 `XPINN` 模型,并用以下形式调用模型。 | ||
|
||
```python | ||
model = ppsci.arch.XPINN | ||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
XPINN本身应该是一种扩展性很强的算法,跟arch绑定感觉不太好,可以考虑参考modulus的做法:https://github.com/NVIDIA/modulus-sym/blob/main/examples/ldc/ldc_2d_domain_decomposition.py。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
好的,有个疑问,需要把 xpinn 算法模块化成 api 吗,还是只在 examples 中实现呢?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
好的,有个疑问,需要把 xpinn 算法模块化成 api 吗,还是只在 examples 中实现呢?
可以是API或者是像modulus这种具备快速扩展到其他案例上的代码块。前者作为API的话,可以考虑归类在PDE模块下,后者可以是像modulus里的一个代码块(函数)。如果做成API的话,可能需要考虑一下怎么设计才是容易扩展又符合正常使用逻辑的,如果是后者,那就只要写一个函数就行了
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
已修改,辛苦 review
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
No description provided.