neuralmonkey.runners.word_alignment_runner module

class neuralmonkey.runners.word_alignment_runner.WordAlignmentRunner(output_series: str, attention: neuralmonkey.attention.base_attention.BaseAttention, decoder: neuralmonkey.decoders.decoder.Decoder) → None

Bases: neuralmonkey.runners.base_runner.BaseRunner

__init__(output_series: str, attention: neuralmonkey.attention.base_attention.BaseAttention, decoder: neuralmonkey.decoders.decoder.Decoder) → None

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

get_executable(compute_losses: bool = False, summaries: bool = True, num_sessions: int = 1) → neuralmonkey.runners.word_alignment_runner.WordAlignmentRunnerExecutable

loss_names

class neuralmonkey.runners.word_alignment_runner.WordAlignmentRunnerExecutable(all_coders: Set[neuralmonkey.model.model_part.ModelPart], fetches: Dict[tensorflow.python.framework.ops.Tensor, Union[int, float, numpy.ndarray]]) → None

Bases: neuralmonkey.runners.base_runner.Executable

__init__(all_coders: Set[neuralmonkey.model.model_part.ModelPart], fetches: Dict[tensorflow.python.framework.ops.Tensor, Union[int, float, numpy.ndarray]]) → None

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

collect_results(results: List[Dict]) → None

next_to_execute() → Tuple[Set[neuralmonkey.model.model_part.ModelPart], Union[Dict, List], List[Dict[tensorflow.python.framework.ops.Tensor, Union[int, float, numpy.ndarray]]]]

Get the feedables and tensors to run.