org.tensorflow.op.core

Class QuantizeAndDequantizeV2.Options

java.lang.Object

org.tensorflow.op.core.QuantizeAndDequantizeV2.Options

Enclosing class:

QuantizeAndDequantizeV2<T extends Number>

public static class QuantizeAndDequantizeV2.Options
extends Object

Optional attributes for QuantizeAndDequantizeV2

Method Summary

Modifier and Type	Method and Description
QuantizeAndDequantizeV2.Options	numBits(Long numBits)
QuantizeAndDequantizeV2.Options	rangeGiven(Boolean rangeGiven)
QuantizeAndDequantizeV2.Options	roundMode(String roundMode)
QuantizeAndDequantizeV2.Options	signedInput(Boolean signedInput)

Methods inherited from class java.lang.Object

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

Method Detail

signedInput

public QuantizeAndDequantizeV2.Options signedInput(Boolean signedInput)

Parameters:

signedInput - Whether the quantization is signed or unsigned. (actually this parameter should have been called `signed_output`)

numBits

public QuantizeAndDequantizeV2.Options numBits(Long numBits)

Parameters:

numBits - The bitwidth of the quantization.

rangeGiven

public QuantizeAndDequantizeV2.Options rangeGiven(Boolean rangeGiven)

Parameters:

rangeGiven - Whether the range is given or should be determined from the `input` tensor.

roundMode

public QuantizeAndDequantizeV2.Options roundMode(String roundMode)

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.