Click or drag to resize

GraphXlaSparseCoreAdagradMomentum Method

https://www.emgu.com/wiki/index.php/Emgu_TF
XlaSparseCoreAdagradMomentum

Namespace:  Emgu.TF
Assembly:  Emgu.TF (in Emgu.TF.dll) Version: 2.16.1.1620+d2904aaafaa66327b642f4fbd5e3c7133dd331e0
Syntax
public Operation XlaSparseCoreAdagradMomentum(
	Output indices,
	Output gradient,
	Output learning_rate,
	Output beta_1,
	Output epsilon,
	Output accumulator,
	Output momentum,
	Output embedding_table,
	long feature_width,
	bool use_nesterov,
	float beta_2,
	float exponent,
	string opName = "XlaSparseCoreAdagradMomentum"
)

Parameters

indices
Type: Emgu.TFOutput
Input to the operation.
gradient
Type: Emgu.TFOutput
Input to the operation.
learning_rate
Type: Emgu.TFOutput
Input to the operation.
beta_1
Type: Emgu.TFOutput
Input to the operation.
epsilon
Type: Emgu.TFOutput
Input to the operation.
accumulator
Type: Emgu.TFOutput
Input to the operation.
momentum
Type: Emgu.TFOutput
Input to the operation.
embedding_table
Type: Emgu.TFOutput
Input to the operation.
feature_width
Type: SystemInt64
feature width
use_nesterov
Type: SystemBoolean
use nesterov
beta_2
Type: SystemSingle
beta 2
exponent
Type: SystemSingle
exponent
opName (Optional)
Type: SystemString
The name of the operation

Return Value

Type: Operation
The operation, where: [0] updated_embedding_table(type: DtFloat). [1] updated_accumulator(type: DtFloat). [2] updated_momentum(type: DtFloat).
See Also