Skip to content

Update MEDiCINe amplitude_threshold_quantile docs and require medicine-neuro>=1.7 #4872

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

Merged
alejoe91 merged 1 commit into from
Oct 16, 2026
+5 −3
Merged

Update MEDiCINe amplitude_threshold_quantile docs and require medicine-neuro>=1.7 #4872

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,7 @@ sortingcomponents = [
# pip install torch
# `medicine-neuro` is likewise optional (and itself depends on torch), needed only
# for the "medicine" motion estimation method. Install separately if needed:
# pip install medicine-neuro
# pip install "medicine-neuro>=1.7"
]

sorters_internal = [
Expand Down Expand Up @@ -314,7 +314,7 @@ test-exporters = [{include-group = "test-common"}]
test-sortingcomponents = [
{include-group = "test-common"},
"torch", # neural network peak detection, motion, matching
"medicine-neuro", # "medicine" motion estimation method
"medicine-neuro>=1.7", # "medicine" motion estimation method
"huggingface_hub", # for `test_single_channel_toy_denoiser_in_peak_pipeline`
]
test-generation = [
Expand Down
4 changes: 3 additions & 1 deletion src/spikeinterface/sortingcomponents/motion/medicine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,9 @@ class MedicineRegistration:
activity_network_hidden_features : tuple, default: (256, 256)
Hidden layer sizes for MEDiCINe's activity network.
amplitude_threshold_quantile : float, default: 0.0
Cutoff quantile in [-1, 1] for peak amplitudes. See MEDiCINe's documentation for details.
Fraction in [0, 1) of peaks with the smallest absolute amplitude to ignore. If 0, all peaks are used.
Requires medicine-neuro >= 1.7 (earlier versions thresholded signed amplitudes and accepted values in
[-1, 1]). See MEDiCINe's documentation for details.
batch_size : int, default: 4096
Batch size used for training.
training_steps : int, default: 10000
Expand Down
Loading