neuralmonkey.encoders.sequence_cnn_encoder module

Encoder for sentence classification with 1D convolutions and max-pooling.

class neuralmonkey.encoders.sequence_cnn_encoder.SequenceCNNEncoder(name: str, vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, embedding_size: int, filters: List[Tuple[int, int]], 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.Stateful

Encoder processing a sequence using a CNN.

__init__(name: str, vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, embedding_size: int, filters: List[Tuple[int, int]], 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 CNN sequence encoder.

Based on: Yoon Kim: Convolutional Neural Networks for Sentence Classification (http://emnlp2014.org/papers/pdf/EMNLP2014181.pdf)

Parameters:
  • vocabulary – Input vocabulary
  • data_id – Identifier of the data series fed to this encoder
  • name – An unique identifier for this encoder
  • max_input_len – Maximum length of an encoded sequence
  • embedding_size – The size of the embedding vector assigned to each word
  • filters – Specification of CNN filters. It is a list of tuples specifying the filter size and number of channels.
  • dropout_keep_prob – The dropout keep probability (default 1.0)
embedded_inputs
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.