AdamWeightDecay

Instance Constructors

new AdamWeightDecay(lr: Double = 1e-3, warmupPortion: Double = 1, total: Int = 1, schedule: String = "linear", beta1: Double = 0.9, beta2: Double = 0.999, epsilon: Double = 1e-6, weightDecay: Double = 0.01)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

lr
learning rate
warmupPortion
portion of total for the warmup, -1 means no warmup. Default: -1
total
total number of training steps for the learning rate schedule, -1 means constant learning rate. Default: -1
schedule
schedule to use for the warmup. Default: 'linear'
beta1
first moment coefficient
beta2
second moment coefficient
epsilon
for numerical stability
weightDecay
weight decay

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
var beta1: Double

first moment coefficient
var beta2: Double

second moment coefficient
def clearHistory(): Unit

Definition Classes
AdamWeightDecay → SGD → OptimMethod
def clone(): OptimMethod[T]

Definition Classes
OptimMethod → AnyRef
var dampening: Double

Definition Classes
SGD
var epsilon: Double

for numerical stability
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getHyperParameter(config: Table): String

Definition Classes
SGD → OptimMethod
def getHyperParameter(): String

Definition Classes
SGD → OptimMethod
def getLearningRate(): Double

Definition Classes
AdamWeightDecay → SGD → OptimMethod
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
var learningRate: Double

Definition Classes
SGD
var learningRateDecay: Double

Definition Classes
SGD
var learningRateSchedule: LearningRateSchedule

Definition Classes
SGD
var learningRates: Tensor[T]

Definition Classes
SGD
def loadFromTable(config: Table): AdamWeightDecay.this.type

Definition Classes
AdamWeightDecay → SGD → OptimMethod
var lr: Double

learning rate
var momentum: Double

Definition Classes
SGD
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
var nesterov: Boolean

Definition Classes
SGD
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T]): (Tensor[T], Array[T])

feval
a function that takes a single input (X), the point of a evaluation, and returns f(X) and df/dX
parameter
the initial point
returns
the new x vector and the function list {fx}, evaluated before the update

Definition Classes
AdamWeightDecay → SGD → OptimMethod
def save(path: String, overWrite: Boolean): AdamWeightDecay.this.type

Definition Classes
OptimMethod
var schedule: String

schedule to use for the warmup.
schedule to use for the warmup. Default: 'linear'
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
var total: Int

total number of training steps for the learning rate schedule, -1 means constant learning rate.
total number of training steps for the learning rate schedule, -1 means constant learning rate. Default: -1
def updateHyperParameter(timeStep: Double): Double
def updateHyperParameter(config: Table, state: Table): Unit

Definition Classes
SGD → OptimMethod
def updateHyperParameter(): Unit

Definition Classes
SGD → OptimMethod
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
def warmupMethod(x: Double, warmup: Double = 0.002): Double
var warmupPortion: Double

portion of total for the warmup, -1 means no warmup.
portion of total for the warmup, -1 means no warmup. Default: -1
var weightDecay: Double

weight decay
weight decay

Definition Classes
SGD
var weightDecays: Tensor[T]

Definition Classes
SGD

Deprecated Value Members

def clearHistory(state: Table): Table

Definition Classes
OptimMethod
Annotations
@deprecated
Deprecated
(Since version 0.2.0) Please use clearHistory() instead
def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T], config: Table, state: Table): (Tensor[T], Array[T])

Definition Classes
OptimMethod
Annotations
@deprecated
Deprecated
(Since version 0.2.0) Please initialize OptimMethod with parameters when creating it instead of importing table

Related Doc: package optimizers

class AdamWeightDecay[T] extends SGD[T]

Instance Constructors

new AdamWeightDecay(lr: Double = 1e-3, warmupPortion: Double = 1, total: Int = 1, schedule: String = "linear", beta1: Double = 0.9, beta2: Double = 0.999, epsilon: Double = 1e-6, weightDecay: Double = 0.01)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

var beta1: Double

var beta2: Double

def clearHistory(): Unit

def clone(): OptimMethod[T]

var dampening: Double

var epsilon: Double

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def getHyperParameter(config: Table): String

def getHyperParameter(): String

def getLearningRate(): Double

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

var learningRate: Double

var learningRateDecay: Double

var learningRateSchedule: LearningRateSchedule

var learningRates: Tensor[T]

def loadFromTable(config: Table): AdamWeightDecay.this.type

var lr: Double

var momentum: Double

final def ne(arg0: AnyRef): Boolean

var nesterov: Boolean

final def notify(): Unit

final def notifyAll(): Unit

def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T]): (Tensor[T], Array[T])

def save(path: String, overWrite: Boolean): AdamWeightDecay.this.type

var schedule: String

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

var total: Int

def updateHyperParameter(timeStep: Double): Double

def updateHyperParameter(config: Table, state: Table): Unit

def updateHyperParameter(): Unit

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

def warmupMethod(x: Double, warmup: Double = 0.002): Double

var warmupPortion: Double

var weightDecay: Double

var weightDecays: Tensor[T]

Deprecated Value Members

def clearHistory(state: Table): Table

def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T], config: Table, state: Table): (Tensor[T], Array[T])

Inherited from SGD[T]

Inherited from OptimMethod[T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped