DANCE — BI2014a P300 event-detection checkpoint
Pretrained weights for the braindecode.models.DANCE
model, used by the tutorial "From window labels to events: asynchronous EEG
decoding with DANCE".
DANCE detects a set of (start, end, class) events directly from long,
unaligned EEG windows, without being told where an event starts. This
checkpoint was trained on the Brain Invaders BI2014a P300 dataset (flash
detection: class 1 = non-target, class 2 = target, class 0 = background).
Results
Cross-subject, held-out subject 3 (never seen in training):
| Metric | Value |
|---|---|
| F1-event (IoU > 0.5 + class match) | 0.495 |
| F1-sample (per-token macro) | 0.372 |
On the first held-out window the model predicts 51 events (ground truth: 53), mean duration ≈ 1.1 s, with confidences 0.75–0.99 — i.e. sharp, correctly localized P300 flashes.
How to load
The architecture must be built exactly as in the tutorial (the state dict is saved with these hyper-parameters):
import torch
from huggingface_hub import hf_hub_download
from braindecode.models import DANCE
model = DANCE(
n_outputs=3,
n_chans=len(chs_info), # 16 for BI2014a
chs_info=chs_info,
n_times=4096, # 32 s @ 128 Hz
sfreq=128.0,
input_window_seconds=32.0,
)
model.load_state_dict(
torch.load(hf_hub_download("braindecode/plot_dance_event_detection", "model.pt"))
)
Training
- Data: BI2014a, subjects 1, 2, 4–9 for training; subject 3 held out.
- Preprocessing (paper recipe): pick EEG, band-pass 0.1–100 Hz, resample to
128 Hz, per-channel robust scaling clamped to
[-16, 16]. - Windows: 32 s fixed length, up to 150 events/window,
num_latents = 256. - Optimiser: Adam, constant lr
5e-4, batch size 16, 120 epochs, best-by-held-out-F1-event checkpoint. - Loss:
braindecode.training.DanceLoss(matched-only IoU normalization).
Reproduce with train_checkpoint.py in this repository.
Training data
The data that shaped these weights. The ids are the datasets: field of this card,
which braindecode reads into model.card_data.datasets when you call
from_pretrained (MOABB class names for MOABB datasets, OpenNeuro / NEMAR
accessions, Hub ids otherwise). nm/on ids are datasets on NEMAR
(on = NEMAR's copy of the OpenNeuro dataset with the same number). Rows marked
private: are data the authors did not release; they are not in datasets:.
datasets: id |
Dataset | Stage | Modality |
|---|---|---|---|
nm000244 |
Brain Invaders 2014a P300 dataset (MOABB BI2014a) | training | EEG |
- Supervised DANCE event detection, cross-subject. Gradient updates on BI2014a subjects 1, 2, 4, 5, 6, 7, 8, 9 (all their sessions as loaded by MOABBDataset); subject 3 is the held-out subject but its F1-event is used to keep the best epoch (torch.save on improvement), so subject 3 selected the checkpoint. 32 s windows at 128 Hz, 120 epochs per card (script default 100).
- Sources: https://huggingface.co/braindecode/plot_dance_event_detection/resolve/main/train_checkpoint.py; W/cards-orig/plot_dance_event_detection.md; W/bd/examples/applied_examples/plot_dance_event_detection.py.
Cite Braindecode
If you use this braindecode port in scientific work, cite the software on Zenodo, doi:10.5281/zenodo.17699192, and the original model and datasets cited above.
@software{braindecode,
author = {Aristimunha, Bruno and
Guetschel, Pierre and
Wimpff, Martin and
Gemein, Lukas and
Rommel, Cedric and
Banville, Hubert and
Sliwowski, Maciej and
Wilson, Daniel and
Brandt, Simon and
Gnassounou, Théo and
Paillard, Joseph and
{Junqueira Lopes}, Bruna and
Sedlar, Sara and
Moreau, Thomas and
Chevallier, Sylvain and
Gramfort, Alexandre and
Schirrmeister, Robin Tibor},
title = {Braindecode: toolbox for decoding raw electrophysiological brain data
with deep learning models},
url = {https://github.com/braindecode/braindecode},
doi = {10.5281/zenodo.17699192},
publisher = {Zenodo},
license = {BSD-3-Clause},
}