PyTorch Blocks

Here can be found all blocks implemented in PyTorch for the architecture’s implementation in that framework.

TSFEDL.blocks_pytorch.ConvBlockYiboGao(...)

Convolutional block of YiboGao's model

TSFEDL.blocks_pytorch.AttentionBranchYiboGao(...)

Attention branch of YiboGao's model

TSFEDL.blocks_pytorch.RTABlock(in_features, ...)

Residual-based Temporal Attention (RTA) block.

TSFEDL.blocks_pytorch.SqueezeAndExcitationModule(...)

Squeeze-and-Excitation Module.

TSFEDL.blocks_pytorch.DenseNetTransitionBlock(...)

Densenet Transition Block for CaiWenjuan model.

TSFEDL.blocks_pytorch.DenseNetConvBlock(...)

Densenet convolution block.

TSFEDL.blocks_pytorch.DenseNetDenseBlock(...)

Densenet dense block.

TSFEDL.blocks_pytorch.SpatialAttentionBlockZhangJin(...)

Spatial Attention module of ZhangJin's model.

TSFEDL.blocks_pytorch.TemporalAttentionBlockZhangJin()

Temporal attention module of ZhangJin's Model.
TSFEDL.blocks_pytorch.ConvBlockYiboGao(in_features, nb_filter, kernel_size)[source]

Convolutional block of YiboGao’s model

Parameters:

  • in_features (int) – Number of input features.

  • nb_filter (int) – Number of filters for the convolution.

  • kernel_size (int) – Size of the convolution kernel.

TSFEDL.blocks_pytorch.AttentionBranchYiboGao(in_features, nb_filter, kernel_size)[source]

Attention branch of YiboGao’s model

Parameters:

  • in_features (int) – Number of input features.

  • nb_filter (int) – Number of filters for the convolution.

  • kernel_size (int) – Size of the convolution kernel.

TSFEDL.blocks_pytorch.RTABlock(in_features, nb_filter, kernel_size)[source]

Residual-based Temporal Attention (RTA) block.

References

Gao, Y., Wang, H., & Liu, Z. (2021). An end-to-end atrial fibrillation detection by a novel residual-based temporal attention convolutional neural network with exponential nonlinearity loss. Knowledge-Based Systems, 212, 106589.

Parameters:

  • in_features (int) – Number of input features.

  • nb_filter (int) – Number of filters for the convolution.

  • kernel_size (int) – Size of the convolution kernel.

TSFEDL.blocks_pytorch.SqueezeAndExcitationModule(in_features: int, dense_units: int)[source]

Squeeze-and-Excitation Module.

References

Squeeze-and-Excitation Networks, Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu (arXiv:1709.01507v4)

Parameters:

  • in_features (int) – The number of input features (channels)

  • dense_units (int) – The number units on each dense layer.

Returns:

se – Output tensor for the block.

Return type:

torch.Tensor

TSFEDL.blocks_pytorch.DenseNetTransitionBlock(in_features, reduction)[source]

Densenet Transition Block for CaiWenjuan model.

Parameters:

  • in_features (int) – The number of input features (channels)

  • reduction (float) – Number between 0 and 1 representing the percentage reduction on the number of units.

TSFEDL.blocks_pytorch.DenseNetConvBlock(in_features, growth_rate)[source]

Densenet convolution block.

Parameters:

  • in_features (int) – The number of input features (channels)

  • growth_rate (int) – Growth rate of the number of units in the layers.

TSFEDL.blocks_pytorch.DenseNetDenseBlock(in_features, layers, growth_rate)[source]

Densenet dense block.

Parameters:

  • in_features (int) – The number of input features (channels)

  • layers (int) – Number of layers of the block.

  • growth_rate (int) – Growth rate of the number of units in the layers.

TSFEDL.blocks_pytorch.SpatialAttentionBlockZhangJin(in_features, decrease_ratio)[source]

Spatial Attention module of ZhangJin’s model.

Parameters:

  • in_features (int) – The number of input features (channels).

  • decrease_ratio (int) – Decrease rate of the number of units in the layers.

TSFEDL.blocks_pytorch.TemporalAttentionBlockZhangJin()[source]

Temporal attention module of ZhangJin’s Model.