neuralmonkey.decoders.sequence_labeler module

class neuralmonkey.decoders.sequence_labeler.SequenceLabeler(name: str, encoder: Union[neuralmonkey.encoders.recurrent.RecurrentEncoder, neuralmonkey.encoders.facebook_conv.SentenceEncoder], vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, 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

Classifier assing a label to each encoder’s state.

__init__(name: str, encoder: Union[neuralmonkey.encoders.recurrent.RecurrentEncoder, neuralmonkey.encoders.facebook_conv.SentenceEncoder], vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, 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

Initialize self. See help(type(self)) for accurate signature.

cost

decoded

decoding_b

decoding_residual_w

decoding_w

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

logits

logprobs

runtime_loss

train_loss