Warning: This API is deprecated and will be removed in a future
version of TensorFlow after
the replacement is stable.
CTCLossV2.Options
Stay organized with collections
Save and categorize content based on your preferences.
Inherited Methods
From class
java.lang.Object
boolean
|
equals(Object arg0)
|
final
Class<?>
|
getClass()
|
int
|
hashCode()
|
final
void
|
notify()
|
final
void
|
notifyAll()
|
String
|
toString()
|
final
void
|
wait(long arg0, int arg1)
|
final
void
|
wait(long arg0)
|
final
void
|
wait()
|
Public Methods
public
CTCLossV2.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.
|
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.
|
public
CTCLossV2.Options
preprocessCollapseRepeated
(Boolean preprocessCollapseRepeated)
Parameters
preprocessCollapseRepeated |
Scalar, if true then repeated labels are
collapsed prior to the CTC calculation.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2022-02-12 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2022-02-12 UTC."],[],[],null,["# CTCLossV2.Options\n\npublic static class **CTCLossV2.Options** \nOptional attributes for [CTCLossV2](/api_docs/java/org/tensorflow/op/core/CTCLossV2) \n\n### Public Methods\n\n|------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options) | [ctcMergeRepeated](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options#ctcMergeRepeated(java.lang.Boolean))(Boolean ctcMergeRepeated) |\n| [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options) | [ignoreLongerOutputsThanInputs](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options#ignoreLongerOutputsThanInputs(java.lang.Boolean))(Boolean ignoreLongerOutputsThanInputs) |\n| [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options) | [preprocessCollapseRepeated](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options#preprocessCollapseRepeated(java.lang.Boolean))(Boolean preprocessCollapseRepeated) |\n\n### Inherited Methods\n\nFrom class java.lang.Object \n\n|------------------|---------------------------|\n| boolean | equals(Object arg0) |\n| final Class\\\u003c?\\\u003e | getClass() |\n| int | hashCode() |\n| final void | notify() |\n| final void | notifyAll() |\n| String | toString() |\n| final void | wait(long arg0, int arg1) |\n| final void | wait(long arg0) |\n| final void | wait() |\n\nPublic Methods\n--------------\n\n#### public [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options)\n**ctcMergeRepeated**\n(Boolean ctcMergeRepeated)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| 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. |\n|------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n\n#### public [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options)\n**ignoreLongerOutputsThanInputs**\n(Boolean ignoreLongerOutputsThanInputs)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| 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. |\n|-------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n\n#### public [CTCLossV2.Options](/api_docs/java/org/tensorflow/op/core/CTCLossV2.Options)\n**preprocessCollapseRepeated**\n(Boolean preprocessCollapseRepeated)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| preprocessCollapseRepeated | Scalar, if true then repeated labels are collapsed prior to the CTC calculation. |\n|----------------------------|----------------------------------------------------------------------------------|"]]