LeakyReluGrad

public final class LeakyReluGrad

Computes rectified linear gradients for a LeakyRelu operation.

Nested Classes

class LeakyReluGrad.Options Optional attributes for LeakyReluGrad

Constants

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

Public Methods

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

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "LeakyReluGrad"

Public Methods

public static LeakyReluGrad.Options alpha (Float alpha)

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) + alpha * gradients * (features <= 0)`.

public static LeakyReluGrad <T> create ( Scope scope, Operand <T> gradients, Operand <T> features, Options... options)

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

Parameters
scope current scope
gradients The backpropagated gradients to the corresponding LeakyRelu operation.
features The features passed as input to the corresponding LeakyRelu operation, OR the outputs of that operation (both work equivalently).
options carries optional attributes values
Returns
  • a new instance of LeakyReluGrad