Have a question? Connect with the community at the TensorFlow Forum Visit Forum

ReluGrad

public final class ReluGrad

Computes rectified linear gradients for a Relu operation.

Constants

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

Public Methods

Output <T>
asOutput ()
Returns the symbolic handle of the tensor.
Output <T>
backprops ()
`gradients * (features > 0)`.
static <T extends TNumber > ReluGrad <T>
create ( Scope scope, Operand <T> gradients, Operand <T> features)
Factory method to create a class wrapping a new ReluGrad operation.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "ReluGrad"

Public Methods

public Output <T> asOutput ()

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.

public Output <T> backprops ()

`gradients * (features > 0)`.

public static ReluGrad <T> create ( Scope scope, Operand <T> gradients, Operand <T> features)

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

Parameters
scope current scope
gradients The backpropagated gradients to the corresponding Relu operation.
features The features passed as input to the corresponding Relu operation, OR the outputs of that operation (both work equivalently).
Returns
  • a new instance of ReluGrad