Views
No views yet
Architecture-only repository. Documents thebraindecode.models.LUNAclass. No pretrained weights are distributed here. Instantiate the model and train it on your own data.
pip install braindecode1from braindecode.models import LUNA
2
3model = LUNA(
4 n_chans=22,
5 sfreq=250,
6 input_window_seconds=4.0,
7 n_outputs=4,
8)
| Parameter | Type | Description |
|---|---|---|
patch_size | int | Number of time samples per patch. Default: 40. |
num_queries | int | Number of learned queries for channel unification. Paper uses: 4 (Base), 6 (Large), 8 (Huge). Default: 4. |
embed_dim | int | Embedding dimension for patch features. Paper uses: 64 (Base), 96 (Large), 128 (Huge). Default: 64. |
depth | int | Number of transformer encoder blocks. Paper uses: 8 (Base), 10 (Large), 24 (Huge). Default: 8. |
num_heads | int | Number of attention heads in channel unification. Default: 2. |
mlp_ratio | float | Ratio of MLP hidden dimension to embedding dimension. Default: 4.0. |
norm_layer | nn.Module | Normalization layer class. Default: nn.LayerNorm. |
drop_path | float | Stochastic depth rate. Default: 0.0. |
1@article{aristimunha2025braindecode,
2 title = {Braindecode: a deep learning library for raw electrophysiological data},
3 author = {Aristimunha, Bruno and others},
4 journal = {Zenodo},
5 year = {2025},
6 doi = {10.5281/zenodo.17699192},
7}