org.tensorflow.op.train

Class ApplyAdam<T>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.train.ApplyAdam<T>

Type Parameters:

T - data type for out() output

All Implemented Interfaces:

Op, Operand<T>

@Operator(group="train")
public final class ApplyAdam<T>
extends PrimitiveOp
implements Operand<T>

Update '*var' according to the Adam algorithm.

$$lr_t := \text{learning\_rate} * \sqrt{1 - beta_2^t} / (1 - beta_1^t)$$ $$m_t := beta_1 * m_{t-1} + (1 - beta_1) * g$$ $$v_t := beta_2 * v_{t-1} + (1 - beta_2) * g * g$$ $$variable := variable - lr_t * m_t / (\sqrt{v_t} + \epsilon)$$

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ApplyAdam.Options Optional attributes for ApplyAdam

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<T>	asOutput() Returns the symbolic handle of a tensor.
static <T> ApplyAdam<T>	create(Scope scope, Operand<T> var, Operand<T> m, Operand<T> v, Operand<T> beta1Power, Operand<T> beta2Power, Operand<T> lr, Operand<T> beta1, Operand<T> beta2, Operand<T> epsilon, Operand<T> grad, ApplyAdam.Options... options) Factory method to create a class wrapping a new ApplyAdam operation.
Output<T>	out() Same as "var".
static ApplyAdam.Options	useLocking(Boolean useLocking)
static ApplyAdam.Options	useNesterov(Boolean useNesterov)

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <T> ApplyAdam<T> create(Scope scope,
                                      Operand<T> var,
                                      Operand<T> m,
                                      Operand<T> v,
                                      Operand<T> beta1Power,
                                      Operand<T> beta2Power,
                                      Operand<T> lr,
                                      Operand<T> beta1,
                                      Operand<T> beta2,
                                      Operand<T> epsilon,
                                      Operand<T> grad,
                                      ApplyAdam.Options... options)

Factory method to create a class wrapping a new ApplyAdam operation.

Parameters:

scope - current scope

var - Should be from a Variable().

m - Should be from a Variable().

v - Should be from a Variable().

beta1Power - Must be a scalar.

beta2Power - 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.

options - carries optional attributes values

Returns:

a new instance of ApplyAdam

useLocking

public static ApplyAdam.Options useLocking(Boolean useLocking)

Parameters:

useLocking - 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.

useNesterov

public static ApplyAdam.Options useNesterov(Boolean useNesterov)

Parameters:

useNesterov - If `True`, uses the nesterov update.

out

public Output<T> out()

Same as "var".

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

Specified by:

asOutput in interface Operand<T>

See Also:

OperationBuilder.addInput(Output)