Parametrized Relu x < 0 => f(x) = x * slope x >= 0 => f(x) = x. More...

#include <prelu.hpp>

Inheritance diagram for ngraph::op::v0::PRelu:

Collaboration diagram for ngraph::op::v0::PRelu:

Public Member Functions
const NodeTypeInfo &	get_type_info () const override

	PRelu (const Output< Node > &data, const Output< Node > &slope)
	Constructs a PRelu operation. More...

bool	visit_attributes (AttributeVisitor &visitor) override

virtual OutputVector	decompose_op () const override

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

void	pre_validate_and_infer_types () override

bool	evaluate (const HostTensorVector &outputs, const HostTensorVector &inputs) const override

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

Detailed Description

Parametrized Relu x < 0 => f(x) = x * slope x >= 0 => f(x) = x.

Constructor & Destructor Documentation

Constructs a PRelu operation.

Parameters

data	Input tensor
slope	Multipliers for negative values

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