org.tensorflow.op.quantization

Class QuantizedMatMulWithBiasAndDequantize<W extends TNumber>

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.quantization.QuantizedMatMulWithBiasAndDequantize<W>

Type Parameters:

W - data type for out output

All Implemented Interfaces:

org.tensorflow.ndarray.Shaped, Op, Operand<W>

public final class QuantizedMatMulWithBiasAndDequantize<W extends TNumber>
extends RawOp
implements Operand<W>

The QuantizedMatMulWithBiasAndDequantize operation

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	QuantizedMatMulWithBiasAndDequantize.Inputs
static class	QuantizedMatMulWithBiasAndDequantize.Options Optional attributes for QuantizedMatMulWithBiasAndDequantize

Field Summary

Fields

Modifier and Type	Field and Description
static String	OP_NAME The name of this op, as known by TensorFlow core engine

Fields inherited from class org.tensorflow.op.RawOp

operation

Constructor Summary

Constructors

Constructor and Description
QuantizedMatMulWithBiasAndDequantize(Operation operation)

Method Summary

Modifier and Type	Method and Description
Output<W>	asOutput() Returns the symbolic handle of the tensor.
static <W extends TNumber> QuantizedMatMulWithBiasAndDequantize<W>	create(Scope scope, Operand<? extends TNumber> a, Operand<? extends TNumber> b, Operand<? extends TNumber> bias, Operand<TFloat32> minA, Operand<TFloat32> maxA, Operand<TFloat32> minB, Operand<TFloat32> maxB, Operand<TFloat32> minFreezedOutput, Operand<TFloat32> maxFreezedOutput, Class<W> Toutput, QuantizedMatMulWithBiasAndDequantize.Options... options) Factory method to create a class wrapping a new QuantizedMatMulWithBiasAndDequantize operation.
static QuantizedMatMulWithBiasAndDequantize.Options	inputQuantMode(String inputQuantMode) Sets the inputQuantMode option.
Output<W>	out() Gets out.
static QuantizedMatMulWithBiasAndDequantize.Options	transposeA(Boolean transposeA) Sets the transposeA option.
static QuantizedMatMulWithBiasAndDequantize.Options	transposeB(Boolean transposeB) Sets the transposeB option.

Methods inherited from class org.tensorflow.op.RawOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.tensorflow.Operand

asTensor, shape, type

Methods inherited from interface org.tensorflow.op.Op

env, op

Methods inherited from interface org.tensorflow.ndarray.Shaped

rank, size

Field Detail

OP_NAME

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

See Also:

Constant Field Values

Constructor Detail

QuantizedMatMulWithBiasAndDequantize

public QuantizedMatMulWithBiasAndDequantize(Operation operation)

Method Detail

create

@Endpoint(describeByClass=true)
public static <W extends TNumber> QuantizedMatMulWithBiasAndDequantize<W> create(Scope scope,
                                                                                                                 Operand<? extends TNumber> a,
                                                                                                                 Operand<? extends TNumber> b,
                                                                                                                 Operand<? extends TNumber> bias,
                                                                                                                 Operand<TFloat32> minA,
                                                                                                                 Operand<TFloat32> maxA,
                                                                                                                 Operand<TFloat32> minB,
                                                                                                                 Operand<TFloat32> maxB,
                                                                                                                 Operand<TFloat32> minFreezedOutput,
                                                                                                                 Operand<TFloat32> maxFreezedOutput,
                                                                                                                 Class<W> Toutput,
                                                                                                                 QuantizedMatMulWithBiasAndDequantize.Options... options)

Factory method to create a class wrapping a new QuantizedMatMulWithBiasAndDequantize operation.

Type Parameters:

W - data type for QuantizedMatMulWithBiasAndDequantize output and operands

Parameters:

scope - current scope

a - The a value

b - The b value

bias - The bias value

minA - The minA value

maxA - The maxA value

minB - The minB value

maxB - The maxB value

minFreezedOutput - The minFreezedOutput value

maxFreezedOutput - The maxFreezedOutput value

Toutput - The value of the Toutput attribute

options - carries optional attribute values

Returns:

a new instance of QuantizedMatMulWithBiasAndDequantize

transposeA

public static QuantizedMatMulWithBiasAndDequantize.Options transposeA(Boolean transposeA)

Sets the transposeA option.

Parameters:

transposeA - the transposeA option

Returns:

this Options instance.

transposeB

public static QuantizedMatMulWithBiasAndDequantize.Options transposeB(Boolean transposeB)

Sets the transposeB option.

Parameters:

transposeB - the transposeB option

Returns:

this Options instance.

inputQuantMode

public static QuantizedMatMulWithBiasAndDequantize.Options inputQuantMode(String inputQuantMode)

Sets the inputQuantMode option.

Parameters:

inputQuantMode - the inputQuantMode option

Returns:

this Options instance.

out

public Output<W> out()

Gets out.

Returns:

out.

asOutput

public Output<W> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of the tensor.

Inputs 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.

Specified by:

asOutput in interface Operand<W extends TNumber>

See Also:

OperationBuilder.addInput(Output)