Skip to content

Conversation

ethanbb
Copy link
Collaborator

@ethanbb ethanbb commented Sep 5, 2025

This is an enhancement to use seeded CNMF that I've been using regularly in my own code. Basically you just compute the seed however you want, save it as an .npy file, and pass the path to that file in the "Ain_path" field of the params dict. It's not super elegant, but I didn't want to assume how I or others might want to compute the seed in the future, so figured it would be better to just allow loading a seed rather than try to add functionality or parameters for actually computing it. I also added tests and new ground truth data for seeded CNMF and CNMFE.

There's one other piece to this, which is updating the get_params_diffs function so that it shows differing parameters anywhere in the dict, not just within "main," but also lifts the contents of "main" to the top level when computing/showing diffs for convenience. I changed this because I wanted to see which "Ain" (if any) was used; in my own code I encoded some parameters for how to compute Ain in the filename. And I factored out the part of the code that computes the diffs so that it just deals with lists of dicts rather than anything to do with pandas (I think I wanted to use it somewhere else). Again, this is what I've been using for a while, but unfortunately it's not currently tested.

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