braindecode.models.SleepStagerChambon2018¶
- class braindecode.models.SleepStagerChambon2018(n_channels, sfreq, n_conv_chs=8, time_conv_size_s=0.5, max_pool_size_s=0.125, pad_size_s=0.25, input_size_s=30, n_classes=5, dropout=0.25, apply_batch_norm=False, return_feats=False)¶
Sleep staging architecture from Chambon et al 2018.
Convolutional neural network for sleep staging described in [Chambon2018].
- Parameters
- n_channelsint
Number of EEG channels.
- sfreqfloat
EEG sampling frequency.
- n_conv_chsint
Number of convolutional channels. Set to 8 in [Chambon2018].
- time_conv_size_sfloat
Size of filters in temporal convolution layers, in seconds. Set to 0.5 in [Chambon2018] (64 samples at sfreq=128).
- max_pool_size_sfloat
Max pooling size, in seconds. Set to 0.125 in [Chambon2018] (16 samples at sfreq=128).
- pad_size_sfloat
Padding size, in seconds. Set to 0.25 in [Chambon2018] (half the temporal convolution kernel size).
- input_size_sfloat
Size of the input, in seconds.
- n_classesint
Number of classes.
- dropoutfloat
Dropout rate before the output dense layer.
- apply_batch_normbool
If True, apply batch normalization after both temporal convolutional layers.
- return_featsbool
If True, return the features, i.e. the output of the feature extractor (before the final linear layer). If False, pass the features through the final linear layer.
References
- Chambon2018(1,2,3,4,5)
Chambon, S., Galtier, M. N., Arnal, P. J., Wainrib, G., & Gramfort, A. (2018). A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4), 758-769.
Methods
- forward(x)¶
Forward pass.
- Parameters
- x: torch.Tensor
Batch of EEG windows of shape (batch_size, n_channels, n_times).
