@Operator public final class IdentityN extends PrimitiveOp implements Iterable<Operand<Object>>
tensors.
This op can be used to override the gradient for complicated functions. For example, suppose y = f(x) and we wish to apply a custom function g for backprop such that dx = g(dy). In Python,
with tf.get_default_graph().gradient_override_map( {'IdentityN': 'OverrideGradientWithG'}): y, _ = identity_n([f(x), x])
operation
Modifier and Type | Method and Description |
---|---|
static IdentityN |
create(Scope scope,
Iterable<Operand<?>> input)
Factory method to create a class wrapping a new IdentityN operation.
|
Iterator<Operand<Object>> |
iterator() |
List<Output<?>> |
output() |
equals, hashCode, op, toString
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
forEach, spliterator
Copyright © 2022. All rights reserved.