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.

Sign up for GitHub

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

Jump to bottom

Testing the difference between learning responses and ellipticities #1

Open
andrevitorelli opened this issue Mar 23, 2022 · 2 comments
Open

Testing the difference between learning responses and ellipticities #1

andrevitorelli opened this issue Mar 23, 2022 · 2 comments
Assignees
@andrevitorelli
Labels
investigation

Comments

@andrevitorelli
Copy link
Contributor

This issue is to track the investigation/comparison between training the model to have a unitary response matrix and just calculating ellipticities out of galaxy stamps.
@andrevitorelli andrevitorelli self-assigned this Mar 23, 2022
@EiffL
Copy link
Member

EiffL commented Apr 13, 2022

So how are we doing here? Does it train with our loss on response matrices?

@andrevitorelli
Copy link
Contributor Author

So how are we doing here? Does it train with our loss on response matrices?

It doesn't as we've seen recently. And the training of ellipticities as it is right now is contentious, it seems to be overfitting. I'll post our current plots later.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@andrevitorelli andrevitorelli

Labels
investigation
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@EiffL @andrevitorelli