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

tf.no_gradient

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

Specifies that ops of type op_type is not differentiable.

View aliases

Compat aliases for migration

tf.compat.v1.NoGradient, tf.compat.v1.NotDifferentiable, tf.compat.v1.no_gradient

tf.no_gradient(
    op_type: str
) -> None

This function should not be used for operations that have a well-defined gradient that is not yet implemented.

This function is only used when defining a new op type. It may be used for ops such as tf.size() that are not differentiable. For example:

tf.no_gradient("Size")

The gradient computed for 'op_type' will then propagate zeros.

For ops that have a well-defined gradient but are not yet implemented, no declaration should be made, and an error must be thrown if an attempt to request its gradient is made.

Args
op_type	The string type of an operation. This corresponds to theOpDef.name field for the proto that defines the operation.

Raises
TypeError	If op_type is not a string.