EEGPT

EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals from Wang et al. (2024) [eegpt].

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

Quick start

pip install braindecode

from braindecode.models import EEGPT

model = EEGPT(
    n_chans=22,
    sfreq=200,
    input_window_seconds=4.0,
    n_outputs=2,
)

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

Documentation

• Full API reference: https://braindecode.org/stable/generated/braindecode.models.EEGPT.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/eegpt.py#L21

Architecture

Parameters

Parameter	Type	Description
return_encoder_output	bool, default=False	Whether to return the encoder output or the classifier output.
patch_size	int, default=64	Size of the patches for the transformer.
patch_stride	int, default=32	Stride of the patches for the transformer.
embed_num	int, default=4	Number of summary tokens used for the global representation.
embed_dim	int, default=512	Dimension of the embeddings.
depth	int, default=8	Number of transformer layers.
num_heads	int, default=8	Number of attention heads.
mlp_ratio	float, default=4.0	Ratio of the MLP hidden dimension to the embedding dimension.
drop_prob	float, default=0.0	Dropout probability.
attn_drop_rate	float, default=0.0	Attention dropout rate.
drop_path_rate	float, default=0.0	Drop path rate.
init_std	float, default=0.02	Standard deviation for weight initialization.
qkv_bias	bool, default=True	Whether to use bias in the QKV projection.
norm_layer	torch.nn.Module, default=None	Normalization layer. If None, defaults to nn.LayerNorm with epsilon layer_norm_eps.
layer_norm_eps	float, default=1e-6	Epsilon value for the normalization layer.

References

1. Wang, G., Liu, W., He, Y., Xu, C., Ma, L., & Li, H. (2024). EEGPT: Pretrained transformer for universal and reliable representation of eeg signals. Advances in Neural Information Processing Systems, 37, 39249-39280. Online: https://proceedings.neurips.cc/paper_files/paper/2024/file/4540d267eeec4e5dbd9dae9448f0b739-Paper-Conference.pdf

Citation

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

@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.