braindecode.models.CTNet

class braindecode.models.CTNet(n_outputs=None, n_chans=None, sfreq=None, chs_info=None, n_times=None, input_window_seconds=None, activation: ~torch.nn.modules.module.Module = <class 'torch.nn.modules.activation.GELU'>, drop_prob_cnn: float = 0.3, drop_prob_posi: float = 0.1, drop_prob_final: float = 0.5, heads: int = 4, emb_size: int = 40, depth: int = 6, n_filters_time: int = 20, kernel_size: int = 64, depth_multiplier: int = 2, pool_size_1: int = 8, pool_size_2: int = 8)

CTNet from Zhao, W et al (2024) [ctnet].

A Convolutional Transformer Network for EEG-Based Motor Imagery Classification

CTNet is an end-to-end neural network architecture designed for classifying motor imagery (MI) tasks from EEG signals. The model combines convolutional neural networks (CNNs) with a Transformer encoder to capture both local and global temporal dependencies in the EEG data.

The architecture consists of three main components:

1. Convolutional Module:

   • Apply EEGNetV4 to perform some feature extraction, denoted here as

   _PatchEmbeddingEEGNet module.

2. Transformer Encoder Module:

   • Utilizes multi-head self-attention mechanisms as EEGConformer but

   with residual blocks.

3. Classifier Module:

   • Combines features from both the convolutional module

   and the Transformer encoder. - Flattens the combined features and applies dropout for regularization. - Uses a fully connected layer to produce the final classification output.

Parameters:

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

• n_chans (int) – Number of EEG channels.

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

• 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.

• activation (nn.Module, default=nn.GELU) – Activation function to use in the network.

• drop_prob_cnn (float, default=0.3) – Dropout probability after convolutional layers.

• drop_prob_posi (float, default=0.1) – Dropout probability for the positional encoding in the Transformer.

• drop_prob_final (float, default=0.5) – Dropout probability before the final classification layer.

• heads (int, default=4) – Number of attention heads in the Transformer encoder.

• emb_size (int, default=40) – Embedding size (dimensionality) for the Transformer encoder.

• depth (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.

Raises:

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

• FutureWarning – If add_log_softmax is True, since LogSoftmax final layer: will be removed in the future.

Notes

This implementation is adapted from the original CTNet source code [ctnetcode] to comply with Braindecode’s model standards.

References

[ctnet]

Zhao, W., Jiang, X., Zhang, B., Xiao, S., & Weng, S. (2024). CTNet: a convolutional transformer network for EEG-based motor imagery classification. Scientific Reports, 14(1), 20237.

[ctnetcode]

Zhao, W., Jiang, X., Zhang, B., Xiao, S., & Weng, S. (2024). CTNet source code: snailpt/CTNet

Methods

forward(x: Tensor) → Tensor

Forward pass of the CTNet model.

Parameters:

x (Tensor) – Input tensor of shape (batch_size, n_channels, n_times).

Returns:

Output with shape (batch_size, n_outputs).

Return type:

Tensor