keraflow.optimizers.RMSprop Class Reference

RMSProp optimizer. More...

Inheritance diagram for keraflow.optimizers.RMSprop:

Public Member Functions
def	__init__
	It is recommended to leave the parameters of this optimizer at their default values (except the learning rate, which can be freely tuned). More...
Public Member Functions inherited from keraflow.optimizers.Optimizer
def	__init__

Detailed Description

RMSProp optimizer.

This optimizer is usually a good choice for recurrent neural networks.

Constructor & Destructor Documentation

def keraflow.optimizers.RMSprop.__init__	(		self,
			lr = 0.001,
			rho = 0.9,
			epsilon = 1e-8,
			kwargs
	)

It is recommended to leave the parameters of this optimizer at their default values (except the learning rate, which can be freely tuned).

Parameters

lr	float >= 0. Learning rate.
rho	float >= 0.
epsilon	float >= 0. Fuzz factor.
kwargs	see Optimizer.__init__