tensorflow::ops::ApplyAdadelta

#include <training_ops.h>

Update '*var' according to the adadelta scheme.

Summary

accum = rho() * accum + (1 - rho()) * grad.square(); update = (update_accum + epsilon).sqrt() * (accum + epsilon()).rsqrt() * grad; update_accum = rho() * update_accum + (1 - rho()) * update.square(); var -= update;

Arguments:

• scope: A Scope object
• var: Should be from a Variable().
• accum: Should be from a Variable().
• accum_update: Should be from a Variable().
• lr: Scaling factor. Must be a scalar.
• rho: Decay factor. Must be a scalar.
• epsilon: Constant factor. Must be a scalar.
• grad: The gradient.

Optional attributes (see Attrs):

• use_locking: If True, updating of the var, accum and update_accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.

Returns:

• Output: Same as "var".

Public attributes

Operation operation

::tensorflow::Output out

Public functions

 ApplyAdadelta(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input accum_update,
  ::tensorflow::Input lr,
  ::tensorflow::Input rho,
  ::tensorflow::Input epsilon,
  ::tensorflow::Input grad
)

 ApplyAdadelta(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input accum_update,
  ::tensorflow::Input lr,
  ::tensorflow::Input rho,
  ::tensorflow::Input epsilon,
  ::tensorflow::Input grad,
  const ApplyAdadelta::Attrs & attrs
)

::tensorflow::Node * node() const 

operator::tensorflow::Input() const 

operator::tensorflow::Output() const 

Public static functions

Attrs UseLocking(
  bool x
)