FakeQuantWithMinMaxVarsGradient

public final class FakeQuantWithMinMaxVarsGradient

Compute gradients for a FakeQuantWithMinMaxVars operation.

class FakeQuantWithMinMaxVarsGradient.Options Optional attributes for FakeQuantWithMinMaxVarsGradient

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 FakeQuantWithMinMaxVarsGradient	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 FakeQuantWithMinMaxVarsGradient operation.
static FakeQuantWithMinMaxVarsGradient.Options	narrowRange(Boolean narrowRange)
static FakeQuantWithMinMaxVarsGradient.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: "FakeQuantWithMinMaxVarsGradient"

Backpropagated gradients w.r.t. max parameter: `sum(gradients * (inputs > max))`.

Backpropagated gradients w.r.t. min parameter: `sum(gradients * (inputs < min))`.

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

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

scope	current scope
gradients	Backpropagated gradients above the FakeQuantWithMinMaxVars operation.
inputs	Values passed as inputs to the FakeQuantWithMinMaxVars operation. min, max: Quantization interval, scalar floats.
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 8, inclusive.