org.bytedeco.tensorflow

Class QuantizedMatMulWithBiasAndRelu

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.tensorflow.QuantizedMatMulWithBiasAndRelu

All Implemented Interfaces:

AutoCloseable

@Namespace(value="tensorflow::ops::internal")
 @NoOffset
 @Properties(inherit=tensorflow.class)
public class QuantizedMatMulWithBiasAndRelu
extends Pointer

Perform a quantized matrix multiplication of a by the matrix b with bias add and relu fusion. The inputs must be two-dimensional matrices and 1D bias vector. And the inner dimension of a (after being transposed if transpose_a is non-zero) must match the outer dimension of b (after being transposed if transposed_b is non-zero). Then do broadcast add operation with bias values on the matrix mulplication result. The bias size must match inner dimension of b. Then do relu activation to get non-negative result. Arguments: * scope: A Scope object * a: A matrix to be multiplied. Must be a two-dimensional tensor of type quint8. * b: A matrix to be multiplied and must be a two-dimensional tensor of type qint8. * bias: A 1D bias tensor with size matching with inner dimension of b (after being transposed if transposed_b is non-zero). * min_a: The float value that the lowest quantized a value represents. * max_a: The float value that the highest quantized a value represents. * min_b: The float value that the lowest quantized b value represents. * max_b: The float value that the highest quantized b value represents. Optional attributes (see Attrs): * transpose_a: If true, a is transposed before multiplication. * transpose_b: If true, b is transposed before multiplication. * input_quant_mode: Input data quantization mode. Either MIN_FIRST(default) or SCALED. Returns: * Output out * Output min_out: The float value that the lowest quantized output value represents. * Output max_out: The float value that the highest quantized output value represents.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	QuantizedMatMulWithBiasAndRelu.Attrs Optional attribute setters for QuantizedMatMulWithBiasAndRelu

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
QuantizedMatMulWithBiasAndRelu(Pointer p) Pointer cast constructor.
QuantizedMatMulWithBiasAndRelu(Scope scope, Input a, Input b, Input bias, Input min_a, Input max_a, Input min_b, Input max_b)
QuantizedMatMulWithBiasAndRelu(Scope scope, Input a, Input b, Input bias, Input min_a, Input max_a, Input min_b, Input max_b, QuantizedMatMulWithBiasAndRelu.Attrs attrs)

Method Summary

Modifier and Type	Method and Description
static QuantizedMatMulWithBiasAndRelu.Attrs	InputQuantMode(BytePointer x)
static QuantizedMatMulWithBiasAndRelu.Attrs	InputQuantMode(String x)
Output	max_out()
QuantizedMatMulWithBiasAndRelu	max_out(Output setter)
Output	min_out()
QuantizedMatMulWithBiasAndRelu	min_out(Output setter)
Operation	operation()
QuantizedMatMulWithBiasAndRelu	operation(Operation setter)
Output	out()
QuantizedMatMulWithBiasAndRelu	out(Output setter)
static QuantizedMatMulWithBiasAndRelu.Attrs	Toutput(int x)
static QuantizedMatMulWithBiasAndRelu.Attrs	TransposeA(boolean x)
static QuantizedMatMulWithBiasAndRelu.Attrs	TransposeB(boolean x)

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

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

Constructor Detail

QuantizedMatMulWithBiasAndRelu

public QuantizedMatMulWithBiasAndRelu(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

QuantizedMatMulWithBiasAndRelu

public QuantizedMatMulWithBiasAndRelu(@Const @ByRef
                                      Scope scope,
                                      @ByVal
                                      Input a,
                                      @ByVal
                                      Input b,
                                      @ByVal
                                      Input bias,
                                      @ByVal
                                      Input min_a,
                                      @ByVal
                                      Input max_a,
                                      @ByVal
                                      Input min_b,
                                      @ByVal
                                      Input max_b)

QuantizedMatMulWithBiasAndRelu

public QuantizedMatMulWithBiasAndRelu(@Const @ByRef
                                      Scope scope,
                                      @ByVal
                                      Input a,
                                      @ByVal
                                      Input b,
                                      @ByVal
                                      Input bias,
                                      @ByVal
                                      Input min_a,
                                      @ByVal
                                      Input max_a,
                                      @ByVal
                                      Input min_b,
                                      @ByVal
                                      Input max_b,
                                      @Const @ByRef
                                      QuantizedMatMulWithBiasAndRelu.Attrs attrs)

Method Detail

Toutput

@ByVal
public static QuantizedMatMulWithBiasAndRelu.Attrs Toutput(@Cast(value="tensorflow::DataType")
                                                                   int x)

TransposeA

@ByVal
public static QuantizedMatMulWithBiasAndRelu.Attrs TransposeA(@Cast(value="bool")
                                                                      boolean x)

TransposeB

@ByVal
public static QuantizedMatMulWithBiasAndRelu.Attrs TransposeB(@Cast(value="bool")
                                                                      boolean x)

InputQuantMode

@ByVal
public static QuantizedMatMulWithBiasAndRelu.Attrs InputQuantMode(@tensorflow.StringPiece
                                                                          BytePointer x)

InputQuantMode

@ByVal
public static QuantizedMatMulWithBiasAndRelu.Attrs InputQuantMode(@tensorflow.StringPiece
                                                                          String x)

operation

@ByRef
public Operation operation()

operation

public QuantizedMatMulWithBiasAndRelu operation(Operation setter)

out

@ByRef
public Output out()

out

public QuantizedMatMulWithBiasAndRelu out(Output setter)

min_out

@ByRef
public Output min_out()

min_out

public QuantizedMatMulWithBiasAndRelu min_out(Output setter)

max_out

@ByRef
public Output max_out()

max_out

public QuantizedMatMulWithBiasAndRelu max_out(Output setter)