lisbet.modeling.backbones#

class lisbet.modeling.backbones.BackboneInterface(*args, **kwargs)[source]#

Abstract base class for all backbone models.

This interface defines the required methods that all backbone implementations must provide.

abstractmethod forward(x)[source]#

Forward pass through the backbone.

Parameters:: x (Tensor) – Input tensor of shape (batch_size, sequence_length, input_dim).
Returns:: Output tensor of shape (batch_size, sequence_length, output_dim).
Return type:: Tensor

abstractmethod get_config()[source]#

Get the configuration dictionary for this backbone.

Returns:: Configuration dictionary containing all parameters needed to recreate this backbone instance.
Return type:: dict[str, Any]

abstractmethod classmethod from_config(config)[source]#

Create a backbone instance from a configuration dictionary.

Parameters:: config (dict[str, Any]) – Configuration dictionary containing all parameters needed to create the backbone instance.
Returns:: New backbone instance created from the configuration.
Return type:: BackboneInterface

class lisbet.modeling.backbones.TransformerBackbone(feature_dim, embedding_dim, hidden_dim, num_heads, num_layers, max_length)[source]#

Transformer backbone for sequence modeling.

A transformer-based backbone that processes input sequences using self-attention mechanisms. The backbone includes frame embedding, positional embedding, transformer encoder layers, and layer normalization.

Parameters:

feature_dim (int) – Dimension of the input features.
embedding_dim (int) – Dimension of the output embeddings.
hidden_dim (int) – Dimension of the feedforward network inside transformer layers.
num_heads (int) – Number of attention heads in the multi-head attention mechanism.
num_layers (int) – Number of transformer encoder layers.
max_length (int) – Maximum sequence length for positional embeddings.

frame_embedder#

Linear layer for embedding input frames.

Type:: nn.Linear

pos_embedder#

Positional embedding module.

Type:: PosEmbedding

transformer_encoder#

Stack of transformer encoder layers.

Type:: nn.TransformerEncoder

layer_norm#

Layer normalization applied to the output.

Type:: nn.LayerNorm

__init__(feature_dim, embedding_dim, hidden_dim, num_heads, num_layers, max_length)[source]#: Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]#

Forward pass through the transformer backbone.

Parameters:: x (Tensor) – Input tensor of shape (batch_size, sequence_length, feature_dim).
Returns:: Output tensor of shape (batch_size, sequence_length, embedding_dim).
Return type:: Tensor

get_config()[source]#

Get the configuration dictionary for this backbone.

Returns:: Configuration dictionary containing all parameters needed to recreate this backbone instance.
Return type:: dict[str, Any]

classmethod from_config(config)[source]#

Create a TransformerBackbone instance from a configuration dictionary.

Parameters:: config (dict[str, Any]) – Configuration dictionary containing all parameters needed to create the backbone instance.
Returns:: New TransformerBackbone instance created from the configuration.
Return type:: TransformerBackbone

class lisbet.modeling.backbones.LSTMBackbone(feature_dim, embedding_dim, hidden_dim, num_layers)[source]#

LSTM backbone for sequence modeling.

Parameters:

feature_dim (int) – Dimension of the input features.
embedding_dim (int) – Dimension of the output embeddings.
hidden_dim (int) – Dimension of the LSTM hidden state.
num_layers (int) – Number of LSTM layers.

__init__(feature_dim, embedding_dim, hidden_dim, num_layers)[source]#: Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]#

Forward pass through the LSTM backbone.

Parameters:: x (Tensor) – Input tensor of shape (batch_size, sequence_length, feature_dim).
Returns:: Output tensor of shape (batch_size, sequence_length, embedding_dim).
Return type:: Tensor

get_config()[source]#

Get the configuration dictionary for this backbone.

Return type:: dict[str, Any]

classmethod from_config(config)[source]#

Create an LSTMBackbone instance from a configuration dictionary.

Return type:: LSTMBackbone

class lisbet.modeling.backbones.TCNBackbone(feature_dim, embedding_dim, hidden_dim, num_layers, kernel_size=3, dilation_base=2, dropout=0.0)[source]#

Temporal Convolutional Network (TCN) backbone for sequence modeling.

Parameters:

feature_dim (int) – Dimension of the input features.
embedding_dim (int) – Dimension of the output embeddings.
hidden_dim (int) – Number of channels in the hidden layers.
num_layers (int) – Number of temporal blocks (layers).
kernel_size (int) – Size of the convolutional kernel. Default: 3
dilation_base (int) – Base for the dilation factor. Default: 2
dropout (float) – Dropout rate. Default: 0.0

__init__(feature_dim, embedding_dim, hidden_dim, num_layers, kernel_size=3, dilation_base=2, dropout=0.0)[source]#: Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]#

Forward pass through the TCN backbone.

Parameters:: x (Tensor) – Input tensor of shape (batch_size, sequence_length, feature_dim).
Returns:: Output tensor of shape (batch_size, sequence_length, embedding_dim).
Return type:: Tensor

get_config()[source]#

Get the configuration dictionary for this backbone.

Return type:: dict[str, Any]

classmethod from_config(config)[source]#

Create a TCNBackbone instance from a configuration dictionary.

Return type:: TCNBackbone

Modules

`base`	Abstract base class for backbone models.
`lstm`	LSTM Backbone for LISBET.
`tcn`	TCN Backbone for LISBET.
`transformer`	Transformer Backbone for Lisbet.