opennn::ConvolutionReluOp Struct Reference

Fused 2D convolution + ReLU activation (uses cuDNN fused epilogue on GPU). More...

#include <operators.h>

Inheritance diagram for opennn::ConvolutionReluOp:

Public Member Functions
void	set (Index input_h, Index input_w, Index kernels_n, Index kernel_h, Index kernel_w, Index kernel_c, Index row_stride, Index column_stride, Index padding_h, Index padding_w, Type compute_dtype)
	Configures the underlying ConvolutionOp; ReLU is fixed.
vector< TensorSpec >	parameter_specs () const override
	Returns the tensor specs of trainable parameters owned by this operator.
void	link_parameters (span< const TensorView > views) override
	Binds parameter views provided by the hosting layer.
void	link_gradients (span< const TensorView > views) override
	Binds gradient views provided by the hosting layer.
void	set_parameters_random () override
	Initializes parameters with random values.
void	set_parameters_glorot () override
	Initializes parameters using Glorot (Xavier) initialization.
void	destroy_cuda () override
	Releases CUDA resources owned by the operator; called from destructors.
	~ConvolutionReluOp () override
	ConvolutionReluOp ()=default
	ConvolutionReluOp (const ConvolutionReluOp &)=delete
ConvolutionReluOp &	operator= (const ConvolutionReluOp &)=delete
void	forward_propagate (ForwardPropagation &fp, size_t layer, bool is_training) noexcept override
	Runs the operator's forward computation.
void	back_propagate (ForwardPropagation &fp, BackPropagation &bp, size_t layer) const noexcept override
	Runs the operator's backward computation, accumulating into gradient/delta buffers.
Public Member Functions inherited from opennn::Operator
virtual	~Operator ()=default
virtual vector< TensorSpec >	state_specs () const
	Returns the tensor specs of persistent state owned by this operator.
virtual void	link_states (span< const TensorView >)
	Binds state views provided by the hosting layer.
virtual void	to_JSON (JsonWriter &) const
	Serializes the operator configuration to a JSON writer.
virtual void	from_JSON (const Json *)
	Restores the operator configuration from a JSON node.
virtual void	load_state_from_JSON (const Json *)
	Restores persistent state (e.g. running statistics) from a JSON node.
TensorView &	get_input (ForwardPropagation &fp, size_t layer, size_t i=0) const noexcept
vector< TensorView > &	get_inputs (ForwardPropagation &fp, size_t layer, size_t i=0) const noexcept
TensorView &	get_output (ForwardPropagation &fp, size_t layer, size_t i=0) const noexcept
TensorView &	get_output_delta (BackPropagation &bp, size_t layer, size_t i=0) const noexcept
TensorView &	get_input_delta (BackPropagation &bp, size_t layer, size_t i=0) const noexcept

Public Attributes
ConvolutionOp	convolution
ActivationOp	activation
Public Attributes inherited from opennn::Operator
vector< size_t >	input_slots = {0}
vector< size_t >	output_slots = {1}
vector< size_t >	input_delta_slots = {1}
vector< size_t >	output_delta_slots = {0}

Detailed Description

Fused 2D convolution + ReLU activation (uses cuDNN fused epilogue on GPU).

Constructor & Destructor Documentation

~ConvolutionReluOp()

opennn::ConvolutionReluOp::~ConvolutionReluOp ( )

inlineoverride

ConvolutionReluOp() [1/2]

opennn::ConvolutionReluOp::ConvolutionReluOp ( )

default

ConvolutionReluOp() [2/2]

opennn::ConvolutionReluOp::ConvolutionReluOp ( const ConvolutionReluOp & )

delete

Member Function Documentation

back_propagate()

void opennn::ConvolutionReluOp::back_propagate ( ForwardPropagation & fp, BackPropagation & bp, size_t layer ) const

overridevirtualnoexcept

Runs the operator's backward computation, accumulating into gradient/delta buffers.

Parameters

fp	Forward propagation workspace (read-only).
bp	Back propagation workspace receiving gradients and deltas.
layer	Index of the hosting layer in the workspace.

Reimplemented from opennn::Operator.

destroy_cuda()

void opennn::ConvolutionReluOp::destroy_cuda ( )

inlineoverridevirtual

Releases CUDA resources owned by the operator; called from destructors.

Reimplemented from opennn::Operator.

forward_propagate()

void opennn::ConvolutionReluOp::forward_propagate ( ForwardPropagation & fp, size_t layer, bool is_training )

overridevirtualnoexcept

Runs the operator's forward computation.

Parameters

fp	Forward propagation workspace.
layer	Index of the hosting layer in the workspace.
is_training	If true, enables training-only behavior (e.g. dropout sampling).

Reimplemented from opennn::Operator.

link_gradients()

void opennn::ConvolutionReluOp::link_gradients ( span< const TensorView > )

inlineoverridevirtual

Binds gradient views provided by the hosting layer.

Reimplemented from opennn::Operator.

link_parameters()

void opennn::ConvolutionReluOp::link_parameters ( span< const TensorView > )

inlineoverridevirtual

Binds parameter views provided by the hosting layer.

Reimplemented from opennn::Operator.

operator=()

ConvolutionReluOp & opennn::ConvolutionReluOp::operator= ( const ConvolutionReluOp & )

delete

parameter_specs()

vector< TensorSpec > opennn::ConvolutionReluOp::parameter_specs ( ) const

inlineoverridevirtual

Returns the tensor specs of trainable parameters owned by this operator.

Reimplemented from opennn::Operator.

set()

void opennn::ConvolutionReluOp::set	(	Index	input_h,
		Index	input_w,
		Index	kernels_n,
		Index	kernel_h,
		Index	kernel_w,
		Index	kernel_c,
		Index	row_stride,
		Index	column_stride,
		Index	padding_h,
		Index	padding_w,
		Type	compute_dtype )

Configures the underlying ConvolutionOp; ReLU is fixed.

set_parameters_glorot()

void opennn::ConvolutionReluOp::set_parameters_glorot ( )

inlineoverridevirtual

Initializes parameters using Glorot (Xavier) initialization.

Reimplemented from opennn::Operator.

set_parameters_random()

void opennn::ConvolutionReluOp::set_parameters_random ( )

inlineoverridevirtual

Initializes parameters with random values.

Reimplemented from opennn::Operator.

Member Data Documentation

activation

ActivationOp opennn::ConvolutionReluOp::activation

convolution

ConvolutionOp opennn::ConvolutionReluOp::convolution