@Namespace(value="tensorflow::ops") @NoOffset @Properties(inherit=tensorflow.class) public class FakeQuantWithMinMaxVarsPerChannelGradient extends Pointer
[d]
, [b, d]
, [b, h, w, d]
.
* inputs: Values passed as inputs to the FakeQuantWithMinMaxVars operation, shape
same as gradients
.
min, max: Quantization interval, floats of shape [d]
.
Optional attributes (see Attrs
):
* num_bits: The bitwidth of the quantization; between 2 and 16, inclusive.
* narrow_range: Whether to quantize into 2^num_bits - 1 distinct values.
Returns:
* Output
backprops_wrt_input: Backpropagated gradients w.r.t. inputs, shape same as
inputs
:
gradients * (inputs >= min && inputs <= max)
.
* Output
backprop_wrt_min: Backpropagated gradients w.r.t. min parameter, shape [d]
:
sum_per_d(gradients * (inputs < min))
.
* Output
backprop_wrt_max: Backpropagated gradients w.r.t. max parameter, shape [d]
:
sum_per_d(gradients * (inputs > max))
.Modifier and Type | Class and Description |
---|---|
static class |
FakeQuantWithMinMaxVarsPerChannelGradient.Attrs
Optional attribute setters for FakeQuantWithMinMaxVarsPerChannelGradient
|
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FakeQuantWithMinMaxVarsPerChannelGradient(Pointer p)
Pointer cast constructor.
|
FakeQuantWithMinMaxVarsPerChannelGradient(Scope scope,
Input gradients,
Input inputs,
Input min,
Input max) |
FakeQuantWithMinMaxVarsPerChannelGradient(Scope scope,
Input gradients,
Input inputs,
Input min,
Input max,
FakeQuantWithMinMaxVarsPerChannelGradient.Attrs attrs) |
Modifier and Type | Method and Description |
---|---|
Output |
backprop_wrt_max() |
FakeQuantWithMinMaxVarsPerChannelGradient |
backprop_wrt_max(Output setter) |
Output |
backprop_wrt_min() |
FakeQuantWithMinMaxVarsPerChannelGradient |
backprop_wrt_min(Output setter) |
Output |
backprops_wrt_input() |
FakeQuantWithMinMaxVarsPerChannelGradient |
backprops_wrt_input(Output setter) |
static FakeQuantWithMinMaxVarsPerChannelGradient.Attrs |
NarrowRange(boolean x) |
static FakeQuantWithMinMaxVarsPerChannelGradient.Attrs |
NumBits(long x) |
Operation |
operation() |
FakeQuantWithMinMaxVarsPerChannelGradient |
operation(Operation setter) |
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
public FakeQuantWithMinMaxVarsPerChannelGradient(Pointer p)
Pointer(Pointer)
.public FakeQuantWithMinMaxVarsPerChannelGradient(@Const @ByRef Scope scope, @ByVal Input gradients, @ByVal Input inputs, @ByVal Input min, @ByVal Input max)
@ByVal public static FakeQuantWithMinMaxVarsPerChannelGradient.Attrs NumBits(@Cast(value="tensorflow::int64") long x)
@ByVal public static FakeQuantWithMinMaxVarsPerChannelGradient.Attrs NarrowRange(@Cast(value="bool") boolean x)
public FakeQuantWithMinMaxVarsPerChannelGradient operation(Operation setter)
public FakeQuantWithMinMaxVarsPerChannelGradient backprops_wrt_input(Output setter)
public FakeQuantWithMinMaxVarsPerChannelGradient backprop_wrt_min(Output setter)
public FakeQuantWithMinMaxVarsPerChannelGradient backprop_wrt_max(Output setter)
Copyright © 2022. All rights reserved.