IdentityN

public final class IdentityN

Returns a list of tensors with the same shapes and contents as the input

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,

{@code
 with tf.get_default_graph().gradient_override_map(
     {'IdentityN': 'OverrideGradientWithG'}):
   y, _ = identity_n([f(x), x])

Public Methods

static IdentityN
create(Scope scope, Iterable<Operand<?>> input)
Factory method to create a class wrapping a new IdentityN operation.
Iterator<Operand<Object>>
List<Output<?>>
output()

Inherited Methods

Public Methods

public static IdentityN create (Scope scope, Iterable<Operand<?>> input)

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

Parameters
scope current scope
Returns
  • a new instance of IdentityN

public Iterator<Operand<Object>> iterator ()

public List<Output<?>> output ()