tensorflow::ops::PreventGradient

An identity op that triggers an error if a gradient is requested.

Summary

When executed in a graph, this op outputs its input tensor as-is.

When building ops to compute gradients, the TensorFlow gradient system will return an error when trying to lookup the gradient of this op, because no gradient must ever be registered for this function. This op exists to prevent subtle bugs from silently returning unimplemented gradients in some corner cases.

Arguments:

• scope: A Scope object
• input: any tensor.

Optional attributes (see Attrs):

• message: Will be printed in the error when anyone tries to differentiate this operation.

Returns:

• Output: the same input tensor.

Public attributes

Operation operation

::tensorflow::Output output

 PreventGradient(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input
)

 PreventGradient(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  const PreventGradient::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Attrs Message(
  StringPiece x
)