torcheeg.models

Convolutional Neural Networks

EEGNet	A compact convolutional neural network (EEGNet).
FBCCNN	Frequency Band Correlation Convolutional Neural Network (FBCCNN).
FBCNet	An Efficient Multi-view Convolutional Neural Network for Brain-Computer Interface.
FBMSNet	FBMSNet, a novel multiscale temporal convolutional neural network for MI decoding tasks, employs Mixed Conv to extract multiscale temporal features which enhance the intra-class compactness and improve the inter-class separability with the joint supervision of the center loss andcenter loss.
MTCNN	Multi-Task Convolutional Neural Network (MT-CNN).
STNet	Spatio-temporal Network (STNet).
TSCeption	TSCeption.
CCNN	Continuous Convolutional Neural Network (CCNN).
SSTEmotionNet	Spatial-Spectral-Temporal based Attention 3D Dense Network (SST-EmotionNet) for EEG emotion recognition.
TinySleepNet	An efficient deep learning model for automatic sleep stage scoring based on raw single-channel EEG.
DeepSleepNet	A deep learning model for automatic sleep stage scoring based on raw single-channel EEG.
USleep	A publicly available, ready-to-use deep-learning-based system for automated sleep staging.
TSLANet	A time series lightweight adaptive network for EEG classification.
CSPNet	CSP-empowered neural network (CSP-Net).

Recurrent Neural Networks

GRU	A simple but effective gate recurrent unit (GRU) network structure from the book of Zhang et al. For more details, please refer to the following information.
LSTM	A simple but effective long-short term memory (LSTM) network structure from the book of Zhang et al. For more details, please refer to the following information.

Graph Neural Networks

DGCNN	Dynamical Graph Convolutional Neural Networks (DGCNN).
LGGNet	DLocal-Global-Graph Networks (LGGNet).
RGNN	Regularized Graph Neural Networks (RGNN).
GIN	A simple but effective graph isomorphism network (GIN) structure from the book of Zhang et al. For more details, please refer to the following information.

Transformer

SimpleViT	A Simple and Effective Vision Transformer (SimpleViT).
ArjunViT	Arjun et al. employ a variation of the Transformer, the Vision Transformer to process EEG signals for emotion recognition.
VanillaTransformer	A vanilla version of the transformer adapted on EEG analysis.
ViT	The Vision Transformer.
ATCNet	ATCNet: An attention-based temporal convolutional network for EEG-based motor imagery classification.
Conformer	The EEG Conformer model is based on the paper "EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization".
LaBraM	Implementation of Large Brain Model (LaBraM) for EEG signal processing.
TCNet	A temporal convolutional network.
MHANet	The MHANet model is based on the paper "MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection".
DARNet	The DARNet model is based on the paper "DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection".

Generative Adversarial Network

BGenerator	TorchEEG provides an EEG feature generator based on CNN architecture and GAN for generating EEG grid representations of different frequency bands based on a given class label.
BDiscriminator	TorchEEG provides an EEG feature generator based on CNN architecture and GAN for generating EEG grid representations of different frequency bands based on a given class label.
BCGenerator	GAN-based methods formulate a zero-sum game between the generator and the discriminator.
BCDiscriminator	GAN-based methods formulate a zero-sum game between the generator and the discriminator.
EEGfuseNet	EEGFuseNet: A hybrid unsupervised network which can fuse high-dimensional EEG to obtain deep feature characterization and generate similar signals.
EFDiscriminator	EFDiscriminator: the discriminator that comes with EEGFuseNet is to distinguish whether the input EEG signals is a fake one generated by the eegfusenet or a real one collected from human brain.

Variational Auto Encoder

BEncoder	The variational autoencoder consists of two parts, an encoder, and a decoder.
BDecoder	The variational autoencoder consists of two parts, an encoder, and a decoder.
BCEncoder	TorchEEG provides an EEG feature encoder based on CNN architecture and CVAE for generating EEG grid representations of different frequency bands based on a given class label.
BCDecoder	TorchEEG provides an EEG feature decoder based on CNN architecture and CVAE for generating EEG grid representations of different frequency bands based on a given class label.

Normalization Flow

BGlow	This class implements the normalized flow model, allowing to generate samples close to the true distribution.
BCGlow	This class implements a conditional normalized flow model that allows generating samples of specified classes.

Diffusion Models

BUNet	The diffusion model consists of two processes, the forward process, and the backward process.
BCUNet	The diffusion model consists of two processes, the forward process, and the backward process.