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

sparse variant of the naive fusion #81

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

erjel
Copy link
Contributor

@erjel erjel commented Apr 7, 2022

It is probably a good idea to provide a naive fusion which also works with the predict_sparse.

I just wrote down my (naive) ideas how this could look like.

ToDos:

  • Implement tests
  • Add grid calculations
  • add 2D variant (yet, I do not see any dimension dependency)
  • test with production dataset
  • Make naming consistent with rest of the code

Signed version of #79

@erjel
Copy link
Contributor Author

erjel commented Apr 7, 2022

Added a simple function test. The coverage is below 100%, so the test cases have to be extended

  • Push coverage to 100%

@erjel erjel mentioned this pull request Apr 7, 2022
5 tasks
Copy link
Contributor Author

@erjel erjel left a comment

Choose a reason for hiding this comment

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

Need to check whether the sparse prediction threshold is the optimal one


lbl = np.zeros(lbl_shape, dtype=np.uint16)

prob_order = np.argsort(probs)[::-1]
Copy link
Contributor Author

Choose a reason for hiding this comment

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

sparse thresh != optimal thresh

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

Successfully merging this pull request may close these issues.

1 participant