Google I/O is a wrap! Catch up on TensorFlow sessions View sessions

tensorflow::ops::ApplyAdam

#include <training_ops.h>

Update '*var' according to the Adam algorithm.

Summary

$$\text{lr}_t := \mathrm{lr} \cdot \frac{\sqrt{1 - \beta_2^t} }{1 - \beta_1^t}$$ $$m_t := \beta_1 \cdot m_{t-1} + (1 - \beta_1) \cdot g$$ $$v_t := \beta_2 \cdot v_{t-1} + (1 - \beta_2) \cdot g^2$$ $$\text{var} := \begin{cases} \text{var} - (m_t \beta_1 + g \cdot (1 - \beta_1))\cdot\text{lr}_t/(\sqrt{v_t} + \epsilon), &\text{if use_nesterov}\\ \text{var} - m_t \cdot \text{lr}_t /(\sqrt{v_t} + \epsilon), &\text{otherwise} \end{cases}$$

Args:

  • scope: A Scope object
  • var: Should be from a Variable().
  • m: Should be from a Variable().
  • v: Should be from a Variable().
  • beta1_power: Must be a scalar.
  • beta2_power: Must be a scalar.
  • lr: Scaling factor. Must be a scalar.
  • beta1: Momentum factor. Must be a scalar.
  • beta2: Momentum factor. Must be a scalar.
  • epsilon: Ridge term. Must be a scalar.
  • grad: The gradient.

Optional attributes (see Attrs):

  • use_locking: If True, updating of the var, m, and v tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.
  • use_nesterov: If True, uses the nesterov update.

Returns:

Constructors and Destructors

ApplyAdam(const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input m, ::tensorflow::Input v, ::tensorflow::Input beta1_power, ::tensorflow::Input beta2_power, ::tensorflow::Input lr, ::tensorflow::Input beta1, ::tensorflow::Input beta2, ::tensorflow::Input epsilon, ::tensorflow::Input grad)
ApplyAdam(const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input m, ::tensorflow::Input v, ::tensorflow::Input beta1_power, ::tensorflow::Input beta2_power, ::tensorflow::Input lr, ::tensorflow::Input beta1, ::tensorflow::Input beta2, ::tensorflow::Input epsilon, ::tensorflow::Input grad, const ApplyAdam::Attrs & attrs)

Public attributes

operation
out

Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

UseLocking(bool x)
UseNesterov(bool x)

Structs

tensorflow::ops::ApplyAdam::Attrs

Optional attribute setters for ApplyAdam.

Public attributes

operation

Operation operation

out

::tensorflow::Output out

Public functions

ApplyAdam

 ApplyAdam(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input m,
  ::tensorflow::Input v,
  ::tensorflow::Input beta1_power,
  ::tensorflow::Input beta2_power,
  ::tensorflow::Input lr,
  ::tensorflow::Input beta1,
  ::tensorflow::Input beta2,
  ::tensorflow::Input epsilon,
  ::tensorflow::Input grad
)

ApplyAdam

 ApplyAdam(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input m,
  ::tensorflow::Input v,
  ::tensorflow::Input beta1_power,
  ::tensorflow::Input beta2_power,
  ::tensorflow::Input lr,
  ::tensorflow::Input beta1,
  ::tensorflow::Input beta2,
  ::tensorflow::Input epsilon,
  ::tensorflow::Input grad,
  const ApplyAdam::Attrs & attrs
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const 

Public static functions

UseLocking

Attrs UseLocking(
  bool x
)

UseNesterov

Attrs UseNesterov(
  bool x
)