neuralmonkey.encoders.pooling module

class neuralmonkey.encoders.pooling.SequenceAveragePooling(name: str, input_sequence: neuralmonkey.model.stateful.TemporalStateful, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

Bases: neuralmonkey.encoders.pooling.SequencePooling

An average pooling layer over a sequence.

Averages a sequence over time to produce a single state.

output

Return the object output.

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

class neuralmonkey.encoders.pooling.SequenceMaxPooling(name: str, input_sequence: neuralmonkey.model.stateful.TemporalStateful, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

Bases: neuralmonkey.encoders.pooling.SequencePooling

A max pooling layer over a sequence.

Takes the maximum of a sequence over time to produce a single state.

output

Return the object output.

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

class neuralmonkey.encoders.pooling.SequencePooling(name: str, input_sequence: neuralmonkey.model.stateful.TemporalStateful, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

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

An abstract pooling layer over a sequence.

__init__(name: str, input_sequence: neuralmonkey.model.stateful.TemporalStateful, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

Initialize an instance of the pooling layer.

get_dependencies() → Set[neuralmonkey.model.model_part.ModelPart]

Collect recusively all encoders and decoders.