bcic_iv_4_ecog_trial
Pretrained artifacts for the Braindecode tutorial examples/applied_examples/bcic_iv_4_ecog_trial.py.
These files are meant to be loaded by the tutorial so the docs can show stable predictions without retraining the model from scratch.
Stored files
params.safetensors: classifier parametershistory.json: Skorch training history used by the tutorial plotsmetadata.json: summary metrics for the stored checkpoint
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 |
|---|---|---|---|
BCIC-IV-4 |
BCI Competition IV dataset 4 (ECoG finger flexion, 3 subjects), loaded with braindecode BCICompetitionIVDataset4 from the Miller ECoG library | training | iEEG |
- Supervised ShallowFBCSPNet regression of finger 1 (thumb) flexion only (target_transform x[0:1]), subject 1 only, whole recordings (the gallery example crops to 30 s; the trainer does not). Train session windows split chronologically (train_test_split shuffle=False, test_size=0.2): first 80% gradient updates, last 20% validation for EarlyStopping(load_best=True). The competition test session is used only for the reported test Pearson r.
- Sources: braindecode git 05e606dd^:scripts/train_and_push_tutorial_checkpoints.py (offline trainer that produced the tutorial checkpoints; removed from the repo in 05e606dd, 2026-04-19, and moved to https://gist.github.com/bru...; W/bd/examples/applied_examples/bcic_iv_4_ecog_trial.py; https://huggingface.co/braindecode/bcic_iv_4_ecog_trial/resolve/main/metadata.json.
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},
}