Refactor API for auto_label_units
#4338
Open
+119
−25
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| classified_df.to_csv(f"{sorting_path}/cluster_prediction.tsv", sep="\t", index_label="cluster_id") | ||
|
|
||
|
|
||
| def auto_label_units( |
Member
There was a problem hiding this comment.
Can we deprecate auto_label_units (slowly!)? I think a lot of people have copies of unitRefine notebooks using it!
| ---------- | ||
| sorting_analyzer : SortingAnalyzer | ||
| The sorting analyzer object containing the spike sorting results. | ||
| noise_neural_classifier : str or Path or None, default: "SpikeInterface/UnitRefine_noise_neural_classifier_lightweight" |
Member
There was a problem hiding this comment.
I'm scared of making these default. The models are trained with NP data, on data in physical units, using metrics computed using si < 0.104 etc.
I think people should investigate and decide what to use. The model on the si page is also already out of date with the model used in the paper, which is on Anoushka's hfh: https://huggingface.co/AnoushkaJain3/noise_neural_classifier_lightweight
Member
There was a problem hiding this comment.
I'm worried about people blindly using this without understanding the assumptions that went into it.
Co-authored-by: Chris Halcrow <57948917+chrishalcrow@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The
auto_label_unitswas used only for the model-based labeling, but there are other ways to label units! (see #4304 )This PR renames
auto_label_unitstomodel_based_label_units. In addition, it adds aunitrefine_label_unitsthat automate the noise/neural + MUA/SUA classification. By default, lightweight models are used since they give almost the same performance as the full models, but don't depend on PCA metrics.