T - data type for backprops() outputpublic final class LeakyReluGrad<T extends Number> extends PrimitiveOp implements Operand<T>
| Modifier and Type | Class and Description |
|---|---|
static class |
LeakyReluGrad.Options
Optional attributes for
LeakyReluGrad |
operation| Modifier and Type | Method and Description |
|---|---|
static LeakyReluGrad.Options |
alpha(Float alpha) |
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
Output<T> |
backprops()
`gradients * (features > 0) + alpha * gradients * (featurs <= 0)`.
|
static <T extends Number> |
create(Scope scope,
Operand<T> gradients,
Operand<T> features,
LeakyReluGrad.Options... options)
Factory method to create a class to wrap a new LeakyReluGrad operation to the graph.
|
equals, hashCode, toStringpublic static <T extends Number> LeakyReluGrad<T> create(Scope scope, Operand<T> gradients, Operand<T> features, LeakyReluGrad.Options... options)
scope - current graph scopegradients - 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 valuespublic static LeakyReluGrad.Options alpha(Float alpha)
alpha - public Output<T> backprops()
public Output<T> asOutput()
OperandInputs 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.
asOutput in interface Operand<T extends Number>OperationBuilder.addInput(Output)Copyright © 2015–2019. All rights reserved.