FakeQuantWithMinMaxVarsPerChannelGradient

public final class FakeQuantWithMinMaxVarsPerChannelGradient

Compute gradients for a FakeQuantWithMinMaxVarsPerChannel operation.

class FakeQuantWithMinMaxVarsPerChannelGradient.Options Optional attributes for FakeQuantWithMinMaxVarsPerChannelGradient

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

Output<TFloat32>	backpropWrtMax() Backpropagated gradients w.r.t.
Output<TFloat32>	backpropWrtMin() Backpropagated gradients w.r.t.
Output<TFloat32>	backpropsWrtInput() Backpropagated gradients w.r.t.
static FakeQuantWithMinMaxVarsPerChannelGradient	create(Scope scope, Operand<TFloat32> gradients, Operand<TFloat32> inputs, Operand<TFloat32> min, Operand<TFloat32> max, Options... options) Factory method to create a class wrapping a new FakeQuantWithMinMaxVarsPerChannelGradient operation.
static FakeQuantWithMinMaxVarsPerChannelGradient.Options	narrowRange(Boolean narrowRange)
static FakeQuantWithMinMaxVarsPerChannelGradient.Options	numBits(Long numBits)

From class org.tensorflow.op.RawOp

final boolean	equals(Object obj)
final int	hashCode()
Operation	op() Return this unit of computation as a single `Operation`.
final String	toString()

From class java.lang.Object

From interface org.tensorflow.op.Op

abstract ExecutionEnvironment	env() Return the execution environment this op was created in.
abstract Operation	op() Return this unit of computation as a single `Operation`.

Constants

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

Constant Value: "FakeQuantWithMinMaxVarsPerChannelGradient"

Backpropagated gradients w.r.t. max parameter, shape `[d]`: `sum_per_d(gradients * (inputs > max))`.

Backpropagated gradients w.r.t. min parameter, shape `[d]`: `sum_per_d(gradients * (inputs < min))`.

Backpropagated gradients w.r.t. inputs, shape same as `inputs`: `gradients * (inputs >= min && inputs <= max)`.

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

scope	current scope
gradients	Backpropagated gradients above the FakeQuantWithMinMaxVars operation, shape one of: `[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]`.
options	carries optional attributes values

narrowRange	Whether to quantize into 2^num_bits - 1 distinct values.

numBits	The bitwidth of the quantization; between 2 and 16, inclusive.