org.tensorflow.op.core

Class QuantizedReluX<U>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.QuantizedReluX<U>

Type Parameters:

U - data type for activations() output

All Implemented Interfaces:

Op

@Operator
public final class QuantizedReluX<U>
extends PrimitiveOp

Computes Quantized Rectified Linear X: `min(max(features, 0), max_value)`

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<U>	activations() Has the same output shape as "features".
static <U,T> QuantizedReluX<U>	create(Scope scope, Operand<T> features, Operand<Float> maxValue, Operand<Float> minFeatures, Operand<Float> maxFeatures, Class<U> outType) Factory method to create a class to wrap a new QuantizedReluX operation to the graph.
Output<Float>	maxActivations() The float value that the highest quantized value represents.
Output<Float>	minActivations() The float value that the lowest quantized value represents.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <U,T> QuantizedReluX<U> create(Scope scope,
                                             Operand<T> features,
                                             Operand<Float> maxValue,
                                             Operand<Float> minFeatures,
                                             Operand<Float> maxFeatures,
                                             Class<U> outType)

Factory method to create a class to wrap a new QuantizedReluX operation to the graph.

Parameters:

scope - current graph scope

features -

maxValue -

minFeatures - The float value that the lowest quantized value represents.

maxFeatures - The float value that the highest quantized value represents.

outType -

Returns:

a new instance of QuantizedReluX

activations

public Output<U> activations()

Has the same output shape as "features".

minActivations

public Output<Float> minActivations()

The float value that the lowest quantized value represents.

maxActivations

public Output<Float> maxActivations()

The float value that the highest quantized value represents.