tf.identity_n  |  TensorFlow v2.16.1 (original) (raw)

tf.identity_n

Stay organized with collections Save and categorize content based on your preferences.

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

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.identity_n

tf.identity_n(
    input, name=None
)

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])

@tf.RegisterGradient('OverrideGradientWithG')
def ApplyG(op, dy, _):
  return [None, g(dy)]  # Do not backprop to f(x).
Args
input A list of Tensor objects.
name A name for the operation (optional).
Returns
A list of Tensor objects. Has the same type as input.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.