Modelpublic

braindecode/REVE

sourceHugging Facebsd-3-clauseupdated 5mo agoView on Hugging Face

0likes

Model Card

REVE

R\ epresentation for E\ EG with V\ ersatile E\ mbeddings (REVE) from El Ouahidi et al. (2025) [reve].

Architecture-only repository. Documents the braindecode.models.REVE class. No pretrained weights are distributed here. Instantiate the model and train it on your own data.

Quick start

bash

pip install braindecode

python

from braindecode.models import REVE

model = REVE(
    n_chans=22,
    sfreq=250,
    input_window_seconds=4.0,
    n_outputs=4,
)

The signal-shape arguments above are illustrative defaults — adjust to match your recording.

Documentation

—Full API reference: <https://braindecode.org/stable/generated/braindecode.models.REVE.html>
—Interactive browser (live instantiation, parameter counts): <https://huggingface.co/spaces/braindecode/model-explorer>
—Source on GitHub: <https://github.com/braindecode/braindecode/blob/master/braindecode/models/reve.py#L35>

Architecture

REVE architecture

Parameters

Parameter	Type	Description
`embed_dim`	int, default=512	Embedding dimension. Use 512 for REVE-Base, 1250 for REVE-Large.
`depth`	int, default=22	Number of Transformer layers.
`heads`	int, default=8	Number of attention heads.
`head_dim`	int, default=64	Dimension per attention head.
`mlp_dim_ratio`	float, default=2.66	FFN hidden dimension ratio: `mlp_dim = embed_dim × mlp_dim_ratio`.
`use_geglu`	bool, default=True	Use GEGLU activation (recommended) or standard GELU.
`freqs`	int, default=4	Number of frequencies for Fourier positional embedding.
`patch_size`	int, default=200	Temporal patch size in samples (200 samples = 1 second at 200 Hz).
`patch_overlap`	int, default=20	Overlap between patches in samples.
`attention_pooling`	bool, default=False	Pooling strategy for aggregating transformer outputs before classification. If `False` (default), all tokens are flattened into a single vector of size `(n_chans x n_patches x embed_dim)`, which is then passed through LayerNorm and a linear classifier. If `True`, uses attention-based pooling with a learnable query token that attends to all encoder outputs, producing a single embedding of size `embed_dim`. Attention pooling is more parameter-efficient for long sequences and variable-length inputs.

References

1.El Ouahidi, Y., Lys, J., Thölke, P., Farrugia, N., Pasdeloup, B., Gripon, V., Jerbi, K. & Lioi, G. (2025). REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects. The Thirty-Ninth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?id=ZeFMtRBy4Z
2.Défossez, A., Caucheteux, C., Rapin, J., Kabeli, O., & King, J. R. (2023). Decoding speech perception from non-invasive brain recordings. Nature Machine Intelligence, 5(10), 1097-1107.

Citation

Cite the original architecture paper (see References above) and braindecode:

bibtex

@article{aristimunha2025braindecode,
  title   = {Braindecode: a deep learning library for raw electrophysiological data},
  author  = {Aristimunha, Bruno and others},
  journal = {Zenodo},
  year    = {2025},
  doi     = {10.5281/zenodo.17699192},
}

License

BSD-3-Clause for the model code (matching braindecode). Pretraining-derived weights, if you fine-tune from a checkpoint, inherit the licence of that checkpoint and its training corpus.