Operator performing Mean Variance Normalization. More...

#include <mvn.hpp>

Inheritance diagram for ngraph::op::v0::MVN:

Collaboration diagram for ngraph::op::v0::MVN:

Public Member Functions
const NodeTypeInfo &	get_type_info () const override

	MVN (const Output< Node > &data, bool across_channels=true, bool normalize_variance=true, double eps=1e-9)
	Constructs an MVN operation. More...

	MVN (const Output< Node > &data, AxisSet reduction_axes, bool normalize_variance=true, double eps=1e-9)
	Constructs an MVN operation. More...

virtual OutputVector	decompose_op () const override

virtual void	validate_and_infer_types () override

virtual bool	visit_attributes (AttributeVisitor &visitor) override

virtual std::shared_ptr< Node >	clone_with_new_inputs (const OutputVector &new_args) const override

double	get_eps () const

bool	get_across_channels () const

bool	get_normalize_variance () const

AxisSet	get_reduction_axes () const

void	set_reduction_axes (AxisSet axes)

Static Public Attributes
static constexpr NodeTypeInfo	type_info {"MVN", 0}

Detailed Description

Operator performing Mean Variance Normalization.

Constructor & Destructor Documentation

Constructs an MVN operation.

Parameters

data	Input tensor with data
normalize_variance	flag that denotes whether to perform variance normalization.
across_channels	flag that denotes if mean values are shared across channels.
eps	the number to be added to the variance to avoid division by zero when normalizing the value

Constructs an MVN operation.

Parameters

data	Input tensor with data
reduction_axes	A list of axes, along which to reduce.
normalize_variance	flag that denotes whether to perform variance normalization.
eps	the number to be added to the variance to avoid division by zero when normalizing the value

The documentation for this class was generated from the following file: