Views
No views yet
Architecture-only repository. Documents thebraindecode.models.CTNetclass. No pretrained weights are distributed here. Instantiate the model and train it on your own data.
pip install braindecode1from braindecode.models import CTNet
2
3model = CTNet(
4 n_chans=22,
5 sfreq=250,
6 input_window_seconds=4.0,
7 n_outputs=4,
8)
| Parameter | Type | Description |
|---|---|---|
activation | nn.Module, default=nn.GELU | Activation function to use in the network. |
num_heads | int, default=4 | Number of attention heads in the Transformer encoder. |
embed_dim | int or None, default=None | Embedding size (dimensionality) for the Transformer encoder. |
num_layers | int, default=6 | Number of encoder layers in the Transformer. |
n_filters_time | int, default=20 | Number of temporal filters in the first convolutional layer. |
kernel_size | int, default=64 | Kernel size for the temporal convolutional layer. |
depth_multiplier | int, default=2 | Multiplier for the number of depth-wise convolutional filters. |
pool_size_1 | int, default=8 | Pooling size for the first average pooling layer. |
pool_size_2 | int, default=8 | Pooling size for the second average pooling layer. cnn_drop_prob: float, default=0.3 Dropout probability after convolutional layers. |
att_positional_drop_prob | float, default=0.1 | Dropout probability for the positional encoding in the Transformer. |
final_drop_prob | float, default=0.5 | Dropout probability before the final classification layer. |
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}