T - data type for output() output@Operator public final class QuantizeAndDequantizeV3<T extends Number> extends PrimitiveOp implements Operand<T>
This is almost identical to QuantizeAndDequantizeV2, except that num_bits is a tensor, so its value can change during training.
| Modifier and Type | Class and Description |
|---|---|
static class |
QuantizeAndDequantizeV3.Options
Optional attributes for
QuantizeAndDequantizeV3 |
operation| Modifier and Type | Method and Description |
|---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T extends Number> |
create(Scope scope,
Operand<T> input,
Operand<T> inputMin,
Operand<T> inputMax,
Operand<Integer> numBits,
QuantizeAndDequantizeV3.Options... options)
Factory method to create a class to wrap a new QuantizeAndDequantizeV3 operation to the graph.
|
Output<T> |
output() |
static QuantizeAndDequantizeV3.Options |
rangeGiven(Boolean rangeGiven) |
static QuantizeAndDequantizeV3.Options |
signedInput(Boolean signedInput) |
equals, hashCode, toStringpublic static <T extends Number> QuantizeAndDequantizeV3<T> create(Scope scope, Operand<T> input, Operand<T> inputMin, Operand<T> inputMax, Operand<Integer> numBits, QuantizeAndDequantizeV3.Options... options)
scope - current graph scopeinput - inputMin - inputMax - numBits - options - carries optional attributes valuespublic static QuantizeAndDequantizeV3.Options signedInput(Boolean signedInput)
signedInput - public static QuantizeAndDequantizeV3.Options rangeGiven(Boolean rangeGiven)
rangeGiven - public Output<T> asOutput()
OperandInputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
asOutput in interface Operand<T extends Number>OperationBuilder.addInput(Output)Copyright © 2015–2019. All rights reserved.