T - data type for output() output@Operator public final class StopGradient<T> extends PrimitiveOp implements Operand<T>
When executed in a graph, this op outputs its input tensor as-is.
When building ops to compute gradients, this op prevents the contribution of its inputs to be taken into account. Normally, the gradient generator adds ops to a graph to compute the derivatives of a specified 'loss' by recursively finding out inputs that contributed to its computation. If you insert this op in the graph it inputs are masked from the gradient generator. They are not taken into account for computing gradients.
This is useful any time you want to compute a value with TensorFlow but need to pretend that the value was a constant. Some examples include:
operation| Modifier and Type | Method and Description |
|---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T> StopGradient<T> |
create(Scope scope,
Operand<T> input)
Factory method to create a class to wrap a new StopGradient operation to the graph.
|
Output<T> |
output() |
equals, hashCode, toStringpublic static <T> StopGradient<T> create(Scope scope, Operand<T> input)
scope - current graph scopeinput - 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>OperationBuilder.addInput(Output)Copyright © 2015–2019. All rights reserved.