neuralmonkey.runners.beamsearch_runner module

class neuralmonkey.runners.beamsearch_runner.BeamSearchRunner(output_series: str, decoder: neuralmonkey.decoders.beam_search_decoder.BeamSearchDecoder, rank: int = 1, postprocess: Callable[[List[str]], List[str]] = None) → None

Bases: neuralmonkey.runners.base_runner.BaseRunner

A runner which takes the output from a beam search decoder.

The runner and the beam search decoder support ensembling.

class Executable(executor: neuralmonkey.runners.beamsearch_runner.BeamSearchRunner, compute_losses: bool, summaries: bool, num_sessions: int) → None

Bases: neuralmonkey.runners.base_runner.Executable

__init__(executor: neuralmonkey.runners.beamsearch_runner.BeamSearchRunner, compute_losses: bool, summaries: bool, num_sessions: int) → None

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

collect_results(results: List[Dict]) → None
next_to_execute() → Tuple[Union[Dict, List], List[Dict[tensorflow.python.framework.ops.Tensor, Union[int, float, numpy.ndarray]]]]

Get the tensors and additional feed dicts for execution.

prepare_results(output)
__init__(output_series: str, decoder: neuralmonkey.decoders.beam_search_decoder.BeamSearchDecoder, rank: int = 1, postprocess: Callable[[List[str]], List[str]] = None) → None

Initialize the beam search runner.

Parameters:
  • output_series – Name of the series produced by the runner.
  • decoder – The beam search decoder to use.
  • rank – The hypothesis from the beam to select. Setting rank to 1 selects the best hypothesis.
  • postprocess – The postprocessor to apply to the output data.
fetches
loss_names
neuralmonkey.runners.beamsearch_runner.beam_search_runner_range(output_series: str, decoder: neuralmonkey.decoders.beam_search_decoder.BeamSearchDecoder, max_rank: int = None, postprocess: Callable[[List[str]], List[str]] = None) → List[neuralmonkey.runners.beamsearch_runner.BeamSearchRunner]

Return beam search runners for a range of ranks from 1 to max_rank.

This means there is max_rank output series where the n-th series contains the n-th best hypothesis from the beam search.

Parameters:
  • output_series – Prefix of output series.
  • decoder – Beam search decoder shared by all runners.
  • max_rank – Maximum rank of the hypotheses.
  • postprocess – Series-level postprocess applied on output.
Returns:

List of beam search runners getting hypotheses with rank from 1 to max_rank.