neuralmonkey.encoders.raw_rnn_encoder module

class neuralmonkey.encoders.raw_rnn_encoder.RawRNNEncoder(name: str, data_id: str, input_size: int, rnn_layers: List[Union[Tuple[int], Tuple[int, str], Tuple[int, str, str]]], max_input_len: Union[int, NoneType] = None, dropout_keep_prob: float = 1.0, save_checkpoint: Union[str, NoneType] = None, load_checkpoint: Union[str, NoneType] = None, initializers: List[Tuple[str, Callable]] = None) → None

Bases: neuralmonkey.model.model_part.ModelPart, neuralmonkey.model.stateful.TemporalStatefulWithOutput

A raw RNN encoder that gets input as a tensor.

__init__(name: str, data_id: str, input_size: int, rnn_layers: List[Union[Tuple[int], Tuple[int, str], Tuple[int, str, str]]], max_input_len: Union[int, NoneType] = None, dropout_keep_prob: float = 1.0, save_checkpoint: Union[str, NoneType] = None, load_checkpoint: Union[str, NoneType] = None, initializers: List[Tuple[str, Callable]] = None) → None

Create a new instance of the encoder.

Parameters:
  • data_id – Identifier of the data series fed to this encoder
  • name – An unique identifier for this encoder
  • rnn_layers – A list of tuples specifying the size and, optionally, the direction (‘forward’, ‘backward’ or ‘bidirectional’) and cell type (‘GRU’ or ‘LSTM’) of each RNN layer.
Keyword Arguments:
 

dropout_keep_prob – The dropout keep probability (default 1.0)

feed_dict(dataset: neuralmonkey.dataset.dataset.Dataset, train: bool = False) → Dict[tensorflow.python.framework.ops.Tensor, Any]

Populate the feed dictionary with the encoder inputs.

Parameters:
  • dataset – The dataset to use
  • train – Boolean flag telling whether it is training time
output

Return the object output.

A 2D Tensor of shape (batch, state_size) which contains the resulting state of the object.

temporal_mask

Return mask for the temporal_states.

A 2D Tensor of shape (batch, time) of type float32 which masks the temporal states so each sequence can have a different length. It should only contain ones or zeros.

temporal_states

Return object states in time.

A 3D Tensor of shape (batch, time, state_size) which contains the states of the object in time (e.g. hidden states of a recurrent encoder.