LSTMBlock¶
-
class
maze.perception.blocks.recurrent.lstm.
LSTMBlock
(*args: Any, **kwargs: Any)¶ A block containing multiple subsequent LSTM layers followed by a final time-distributed dense layer with explicit non-linearity.
The block expects the input tensors to have the from (batch-dim, time-dim, feature-dim).
- Parameters
in_keys – One key identifying the input tensors.
out_keys – One key identifying the output tensors.
in_shapes – List of input shapes.
hidden_size – The number of features in the hidden state.
num_layers – Number of recurrent layers.
bidirectional – If True, becomes a bidirectional LSTM.
non_lin – The non-linearity to apply after the final layer.
-
normalized_forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ (overrides
ShapeNormalizationBlock
)implementation of
ShapeNormalizationBlock
interface