org.tensorflow.op.core

Class CTCLoss.Options

java.lang.Object

org.tensorflow.op.core.CTCLoss.Options

Enclosing class:

CTCLoss

public static class CTCLoss.Options
extends Object

Optional attributes for CTCLoss

Method Summary

Modifier and Type	Method and Description
CTCLoss.Options	ctcMergeRepeated(Boolean ctcMergeRepeated)
CTCLoss.Options	ignoreLongerOutputsThanInputs(Boolean ignoreLongerOutputsThanInputs)
CTCLoss.Options	preprocessCollapseRepeated(Boolean preprocessCollapseRepeated)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

preprocessCollapseRepeated

public CTCLoss.Options preprocessCollapseRepeated(Boolean preprocessCollapseRepeated)

Parameters:

preprocessCollapseRepeated - Scalar, if true then repeated labels are collapsed prior to the CTC calculation.

ctcMergeRepeated

public CTCLoss.Options ctcMergeRepeated(Boolean ctcMergeRepeated)

Parameters:

ctcMergeRepeated - Scalar. If set to false, during CTC calculation repeated non-blank labels will not be merged and are interpreted as individual labels. This is a simplified version of CTC.

ignoreLongerOutputsThanInputs

public CTCLoss.Options ignoreLongerOutputsThanInputs(Boolean ignoreLongerOutputsThanInputs)

Parameters:

ignoreLongerOutputsThanInputs - Scalar. If set to true, during CTC calculation, items that have longer output sequences than input sequences are skipped: they don't contribute to the loss term and have zero-gradient.