Warning: This API is deprecated and will be removed in a future
version of TensorFlow after
the replacement is stable.
QuantizeAndDequantizeV4.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
Parameters
| axis |
If specified, this axis is treated as a channel or slice axis, and a separate
quantization range is used for each channel or slice along this axis.
|
Parameters
| narrowRange |
If True, then the absolute value of the quantized minimum value is the same as
the quantized maximum value, instead of 1 greater.
i.e. for 8 bit quantization, the minimum value is -127 instead of -128.
|
Parameters
| numBits |
The bitwidth of the quantization.
|
Parameters
| rangeGiven |
Whether the range is given or should be determined from the `input` tensor.
|
Parameters
| roundMode |
The 'round_mode' attribute controls which rounding tie-breaking algorithm is
used when rounding float values to their quantized equivalents. The following
rounding modes are currently supported:
-
HALF_TO_EVEN: this is the default round_mode.
-
HALF_UP: round towards positive. In this mode 7.5 rounds up to 8 and -7.5
rounds up to -7.
|
Parameters
| signedInput |
Whether the quantization is signed or unsigned. (actually this parameter should
have been called `signed_output`)
|
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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2022-02-12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,["# QuantizeAndDequantizeV4.Options\n\npublic static class **QuantizeAndDequantizeV4.Options** \nOptional attributes for [QuantizeAndDequantizeV4](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4) \n\n### Public Methods\n\n|----------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [axis](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#axis(java.lang.Long))(Long axis) |\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [narrowRange](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#narrowRange(java.lang.Boolean))(Boolean narrowRange) |\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [numBits](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#numBits(java.lang.Long))(Long numBits) |\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [rangeGiven](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#rangeGiven(java.lang.Boolean))(Boolean rangeGiven) |\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [roundMode](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#roundMode(java.lang.String))(String roundMode) |\n| [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options) | [signedInput](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options#signedInput(java.lang.Boolean))(Boolean signedInput) |\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 [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**axis**\n(Long axis)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| axis | If specified, this axis is treated as a channel or slice axis, and a separate quantization range is used for each channel or slice along this axis. |\n|------|-----------------------------------------------------------------------------------------------------------------------------------------------------|\n\n#### public [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**narrowRange**\n(Boolean narrowRange)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| narrowRange | If True, then the absolute value of the quantized minimum value is the same as the quantized maximum value, instead of 1 greater. i.e. for 8 bit quantization, the minimum value is -127 instead of -128. |\n|-------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n\n#### public [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**numBits**\n(Long numBits)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| numBits | The bitwidth of the quantization. |\n|---------|-----------------------------------|\n\n#### public [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**rangeGiven**\n(Boolean rangeGiven)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| rangeGiven | Whether the range is given or should be determined from the \\`input\\` tensor. |\n|------------|-------------------------------------------------------------------------------|\n\n#### public [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**roundMode**\n(String roundMode)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| roundMode | The 'round_mode' attribute controls which rounding tie-breaking algorithm is used when rounding float values to their quantized equivalents. The following rounding modes are currently supported: - HALF_TO_EVEN: this is the default round_mode. - HALF_UP: round towards positive. In this mode 7.5 rounds up to 8 and -7.5 rounds up to -7. |\n|-----------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n\n#### public [QuantizeAndDequantizeV4.Options](/api_docs/java/org/tensorflow/op/core/QuantizeAndDequantizeV4.Options)\n**signedInput**\n(Boolean signedInput)\n\n\u003cbr /\u003e\n\n##### Parameters\n\n| signedInput | Whether the quantization is signed or unsigned. (actually this parameter should have been called **\\`signed_output\\`**) |\n|-------------|-------------------------------------------------------------------------------------------------------------------------|"]]
