ngraph.opset7.ctc_loss

ngraph.opset7.ctc_loss(logits: Union[_pyngraph.Node, int, float, numpy.ndarray], logit_length: Union[_pyngraph.Node, int, float, numpy.ndarray], labels: Union[_pyngraph.Node, int, float, numpy.ndarray], label_length: Union[_pyngraph.Node, int, float, numpy.ndarray], blank_index: Optional[Union[_pyngraph.Node, int, float, numpy.ndarray]] = None, preprocess_collapse_repeated: bool = False, ctc_merge_repeated: bool = True, unique: bool = False, name: Optional[str] = None) _pyngraph.Node

Return a node which performs CTCLoss.

Parameters
  • logits – 3-D tensor of logits.

  • logit_length – 1-D tensor of lengths for each object from a batch.

  • labels – 2-D tensor of labels for which likelihood is estimated using logits.

  • label_length – 1-D tensor of length for each label sequence.

  • blank_index – Scalar used to mark a blank index.

  • preprocess_collapse_repeated – Flag for preprocessing labels before loss calculation.

  • ctc_merge_repeated – Flag for merging repeated characters in a potential alignment.

  • unique – Flag to find unique elements in a target.

Returns

The new node which performs CTCLoss