-
Notifications
You must be signed in to change notification settings - Fork 112
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
Neural networks for instationary problems #1120
Conversation
@renefritze Do you see what is wrong with the documentation? I can't figure out where the warnings come from. |
Did you see these? |
Yes, but I do not really understand what the problem is. |
Indent was off-by-one. |
Thanks, I don't know why I did not see that... |
Cause it's literally only two spaces and the warning message from docutils is effectively emitted for the transformed text. I have indent guides on in atom, that made it easier to spot for me. |
Codecov Report
|
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.
Only some minor things ...
@sdrave Thanks for taking a look. In the meantime, @ftalbrecht started to restructure the implementation of our neural network-based reductor and related stuff. At the moment, I am preparing a PR for these changes. Maybe it makes more sense to first do the restructuring and implement the instationary case afterwards. |
If you think the new PR will be ready soonish, then yes, it probably makes sense to close this PR for now. On the other hand, this is almost good to merge, and it would be nice to have it in the next release. You decide what to do .. |
3e4f590
to
58cbb6c
Compare
The other PR will still take some time. I am also not completely convinced about the new structure introduced there. We need to further discuss that at some point. Consequently, I would propose to finish this PR first, since there were quite a few questions regarding neural networks for instationary problems at the pyMOR course as well. Some people seemed to be interested in that. |
ca35785
to
cee7c49
Compare
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.
I just noticed that you always leave two empty lines between class members. PEP8 states that it should only be 1 (two lines between global definitions.) So probably my linter would complain.
Oh, I'm sorry, I will fix that! |
Co-authored-by: Stephan Rave <stephanrave@uni-muenster.de>
8f7ee4f
to
9402b0d
Compare
I think this can be merged if the checks pass. |
This pull request adds a
NeuralNetworkInstationaryReductor
that handles instationary problems. Furthermore, a demo solving Burgers' equation is implemented and added topymortests
.