neuralmonkey.model package¶
Submodules¶
neuralmonkey.model.model_part module¶
Basic functionality of all model parts.
-
class
neuralmonkey.model.model_part.
ModelPart
(name: str, save_checkpoint: typing.Union[str, NoneType] = None, load_checkpoint: typing.Union[str, NoneType] = None) → None¶ Bases:
object
Base class of all model parts.
-
feed_dict
(dataset: neuralmonkey.dataset.Dataset, train: bool) → typing.Dict[tensorflow.python.framework.ops.Tensor, typing.Any]¶ Prepare feed dicts for part’s placeholders from a dataset.
-
load
(session: tensorflow.python.client.session.Session) → None¶ Load model part from a checkpoint file.
-
name
¶ Name of the model part and its variable scope.
-
save
(session: tensorflow.python.client.session.Session) → None¶ Save model part to a checkpoint file.
-
use_scope
()¶ Return a context manager that (re)opens the model part’s variable and name scope.
-
neuralmonkey.model.sequence module¶
This module impements the sequence class and a few of its subclasses
-
class
neuralmonkey.model.sequence.
EmbeddedFactorSequence
(name: str, vocabularies: typing.List[neuralmonkey.vocabulary.Vocabulary], data_ids: typing.List[str], embedding_sizes: typing.List[int], max_length: int = None, save_checkpoint: str = None, load_checkpoint: str = None) → None¶ Bases:
neuralmonkey.model.sequence.Sequence
A Sequence that stores one or more embedded inputs (factors).
-
data
¶ The sequence data. A 3D Tensor of shape (batch, time, dimension), where dimension is the sum of the embedding sizes supplied to the constructor.
-
dimension
¶ The sequence dimension. The sum of the embedding sizes supplied to the constructor.
-
embedding_matrices
¶ A list of embedding matrices for each factor
-
feed_dict
(dataset: neuralmonkey.dataset.Dataset, train: bool = False) → typing.Dict[tensorflow.python.framework.ops.Tensor, typing.Any]¶ Feed the placholders with the data.
Parameters: - dataset – The dataset.
- train – A flag whether the train mode is enabled.
Returns: The constructed feed dictionary that contains the factor data and the mask.
-
input_factors
¶ A list of 2D placeholders for each factor. Each placeholder has shape (batch size, time).
-
mask
¶ A 2D placeholder for the sequence mask. This is shared across factors and must be the same for each of them.
-
tb_embedding_visualization
(logdir: str, prj: <module 'tensorflow.contrib.tensorboard.plugins.projector' from '/home/docs/checkouts/readthedocs.org/user_builds/neural-monkey/envs/0.2.2/lib/python3.5/site-packages/tensorflow/contrib/tensorboard/plugins/projector/__init__.py'>)¶ Links embeddings with vocabulary wordlist for tensorboard visualization
Parameters: - logdir – directory where model is stored
- projector – TensorBoard projector for storing linking info.
-
-
class
neuralmonkey.model.sequence.
EmbeddedSequence
(name: str, vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, embedding_size: int, max_length: int = None, save_checkpoint: str = None, load_checkpoint: str = None) → None¶ Bases:
neuralmonkey.model.sequence.EmbeddedFactorSequence
A sequence of embedded inputs (for a single factor)
-
data_id
¶ The input data series indentifier
-
embedding_matrix
¶ The embedding matrix for the sequence
-
inputs
¶ A 2D placeholder for the sequence inputs.
-
vocabulary
¶ The input vocabulary
-
-
class
neuralmonkey.model.sequence.
Sequence
(name: str, max_length: int = None, save_checkpoint: str = None, load_checkpoint: str = None) → None¶ Bases:
neuralmonkey.model.model_part.ModelPart
Base class for a data sequence.
This class represents a batch of sequences of Tensors of possibly different lengths.
-
data
¶ A Tensor representing the data in the sequence. The first and second dimension correspond to batch size and time respectively.
-
dimension
¶ The dimension of the sequence. For 3D sequences, this is the size of the last dimension of the data tensor.
-
lengths
¶ A 1D Tensor of type int32 that stores the lengths of the sequences in the batch
-
mask
¶ A 2D Tensor of type float32 and shape (batch size, time) that masks the sequences in the batch.
-
max_length
¶ The maximum length of sequences in the data tensor.
-