RNN_Sent140_LITE#

class fl_sim.models.RNN_Sent140_LITE(latent_size: int = 100, num_classes: int = 2, num_layers: int = 2, embed_dim: int = 50)[source]#

Bases: Module, CLFMixin, SizeMixin, DiffMixin

Stacked LSTM model for sentiment analysis on the Sent140 dataset.

The same as RNN_Sent140 but without the GloVe embedding layer. Hence the inputs of this model are embedd vectors.

Parameters:

  • latent_size (int, default 100) – The number of features in the hidden state h.

  • num_classes (int, default 2) – The number of output classes.

  • num_layers (int, default 2) – The number of recurrent layers (torch.nn.LSTM).

  • embed_dim (int, default 50) – The dimension of the input embeddings.

forward(embeds: Tensor) → Tensor[source]#

Forward pass.

Parameters:

embeds (torch.Tensor) – Shape (batch_size, seq_len, embedding_dim).

Returns:

Shape (batch_size, num_classes).

Return type:

torch.Tensor