braindecode.models.FBCNet#

class braindecode.models.FBCNet(n_chans=None, n_outputs=None, chs_info=None, n_times=None, input_window_seconds=None, sfreq=None, n_bands=9, n_filters_spat=32, temporal_layer='LogVarLayer', n_dim=3, stride_factor=4, activation=<class 'torch.nn.modules.activation.SiLU'>, linear_max_norm=0.5, cnn_max_norm=2.0, filter_parameters=None)[source]#

FBCNet from Mane, R et al (2021) [fbcnet2021].

Convolution Filterbank

FBCNet Architecture

The FBCNet model applies spatial convolution and variance calculation along the time axis, inspired by the Filter Bank Common Spatial Pattern (FBCSP) algorithm.

Parameters:

  • n_chans (int) – Number of EEG channels.

  • n_outputs (int) – Number of outputs of the model. This is the number of classes in the case of classification.

  • chs_info (list of dict) – Information about each individual EEG channel. This should be filled with info["chs"]. Refer to mne.Info for more details.

  • n_times (int) – Number of time samples of the input window.

  • input_window_seconds (float) – Length of the input window in seconds.

  • sfreq (float) – Sampling frequency of the EEG recordings.

  • n_bands (int or None or list[tuple[int, int]]], default=9) – Number of frequency bands. Could

  • n_filters_spat (int) – Number of spatial filters for the first convolution.

  • temporal_layer (str) – Type of temporal aggregator layer. Options: ‘VarLayer’, ‘StdLayer’, ‘LogVarLayer’, ‘MeanLayer’, ‘MaxLayer’.

  • n_dim (int) – Number of dimensions for the temporal reductor

  • stride_factor (int) – Stride factor for reshaping.

  • activation (type[Module]) – Activation function class to apply in Spatial Convolution Block.

  • linear_max_norm (float) – Maximum norm for the final linear layer.

  • cnn_max_norm (float) – Maximum norm for the spatial convolution layer.

  • filter_parameters (dict[Any, Any] | None) – Dictionary of parameters to use for the FilterBankLayer. If None, a default Chebyshev Type II filter with transition bandwidth of 2 Hz and stop-band ripple of 30 dB will be used.

Raises:

ValueError – If some input signal-related parameters are not specified: and can not be inferred.

Notes

This implementation is not guaranteed to be correct and has not been checked by the original authors; it has only been reimplemented from the paper description and source code [fbcnetcode2021]. There is a difference in the activation function; in the paper, the ELU is used as the activation function, but in the original code, SiLU is used. We followed the code.

References

[fbcnet2021]

Mane, R., Chew, E., Chua, K., Ang, K. K., Robinson, N., Vinod, A. P., … & Guan, C. (2021). FBCNet: A multi-view convolutional neural network for brain-computer interface. preprint arXiv:2104.01233.

Hugging Face Hub integration

When the optional huggingface_hub package is installed, all models automatically gain the ability to be pushed to and loaded from the Hugging Face Hub. Install with:

pip install braindecode[hub]

Pushing a model to the Hub:

from braindecode.models import FBCNet

# Train your model
model = FBCNet(n_chans=22, n_outputs=4, n_times=1000)
# ... training code ...

# Push to the Hub
model.push_to_hub(
    repo_id="username/my-fbcnet-model",
    commit_message="Initial model upload",
)

Loading a model from the Hub:

from braindecode.models import FBCNet

# Load pretrained model
model = FBCNet.from_pretrained("username/my-fbcnet-model")

# Load with a different number of outputs (head is rebuilt automatically)
model = FBCNet.from_pretrained("username/my-fbcnet-model", n_outputs=4)

Extracting features and replacing the head:

import torch

x = torch.randn(1, model.n_chans, model.n_times)
# Extract encoder features (consistent dict across all models)
out = model(x, return_features=True)
features = out["features"]

# Replace the classification head
model.reset_head(n_outputs=10)

Saving and restoring full configuration:

import json

config = model.get_config()            # all __init__ params
with open("config.json", "w") as f:
    json.dump(config, f)

model2 = FBCNet.from_config(config)    # reconstruct (no weights)

All model parameters (both EEG-specific and model-specific such as dropout rates, activation functions, number of filters) are automatically saved to the Hub and restored when loading.

See Loading and Adapting Pretrained Foundation Models for a complete tutorial.

Methods

forward(x)[source]#

Forward pass of the FBCNet model.

Parameters:

x (Tensor) – Input tensor with shape (batch_size, n_chans, n_times).

Returns:

Output tensor with shape (batch_size, n_outputs).

Return type:

Tensor

On this page