base class of all kind of NN layers More...

#include <layer.h>

Inheritance diagram for tiny_dnn::layer:

[legend]

Collaboration diagram for tiny_dnn::layer:

[legend]

Public Member Functions
	layer (const std::vector< vector_type > &in_type, const std::vector< vector_type > &out_type)
	Defaul layer constructor that instantiates a N-input, M-output layer.

	layer (const layer &)=default

layer &	operator= (const layer &)=default

void	set_parallelize (bool parallelize)

void	set_backend (std::shared_ptr< core::backend > backend)

void	set_backend_type (core::backend_t backend_type)

bool	parallelize () const

core::backend_t	backend_type () const

core::backend_t	engine () const

virtual std::string	kernel_file () const

virtual std::string	kernel_header () const

virtual void	createOp ()

void	setDevice (const Device &device)

Device *	device () const

std::shared_ptr< core::backend >	backend ()
	number of incoming edges in this layer

serial_size_t	in_channels () const
	number of outgoing edges in this layer

serial_size_t	out_channels () const

serial_size_t	in_data_size () const

serial_size_t	out_data_size () const

std::vector< shape3d >	in_data_shape ()

std::vector< shape3d >	out_data_shape ()

serial_size_t	in_size () const
	!

serial_size_t	out_size () const
	!

std::vector< const vec_t * >	weights () const

std::vector< vec_t * >	weights ()

std::vector< tensor_t * >	weights_grads ()

std::vector< edgeptr_t >	inputs ()

std::vector< edgeptr_t >	outputs ()

std::vector< edgeptr_t >	outputs () const

void	set_out_grads (const std::vector< tensor_t > &grad)

void	set_in_data (const std::vector< tensor_t > &data)

std::vector< tensor_t >	output () const

std::vector< vector_type >	in_types () const

std::vector< vector_type >	out_types () const

void	set_trainable (bool trainable)

bool	trainable () const

virtual std::pair< float_t, float_t >	out_value_range () const
	return output value range used only for calculating target value from label-id in final(output) layer override properly if the layer is intended to be used as output layer

virtual std::vector< shape3d >	in_shape () const =0
	array of input shapes (width x height x depth)

virtual std::vector< shape3d >	out_shape () const =0
	array of output shapes (width x height x depth)

virtual std::string	layer_type () const =0
	name of layer, should be unique for each concrete class

virtual serial_size_t	fan_in_size () const
	number of incoming connections for each output unit used only for weight/bias initialization methods which require fan-in size (e.g.

virtual serial_size_t	fan_out_size () const
	number of outgoing connections for each input unit used only for weight/bias initialization methods which require fan-out size (e.g.

template<typename WeightInit >
layer &	weight_init (const WeightInit &f)

template<typename BiasInit >
layer &	bias_init (const BiasInit &f)

template<typename WeightInit >
layer &	weight_init (std::shared_ptr< WeightInit > f)

template<typename BiasInit >
layer &	bias_init (std::shared_ptr< BiasInit > f)

template<typename Archive >
void	serialize (Archive &ar)

virtual void	save (std::ostream &os) const

virtual void	load (std::istream &is)

virtual void	load (const std::vector< float_t > &src, int &idx)

virtual image	output_to_image (size_t channel=0) const
	< visualize latest output of this layer default implementation interpret output as 1d-vector, so "visual" layer(like convolutional layer) should override this for better visualization.

virtual void	forward_propagation (const std::vector< tensor_t * > &in_data, std::vector< tensor_t * > &out_data)=0

virtual void	back_propagation (const std::vector< tensor_t * > &in_data, const std::vector< tensor_t * > &out_data, std::vector< tensor_t * > &out_grad, std::vector< tensor_t * > &in_grad)=0
	return delta of previous layer (delta=\frac{dE}{da}, a=wx in fully-connected layer)

virtual void	post_update ()
	return delta2 of previous layer (delta2=\frac{d^2E}{da^2}, diagonal of hessian matrix) it is never called if optimizer is hessian-free

virtual void	set_context (net_phase ctx)
	notify changing context (train <=> test)

std::vector< tensor_t >	forward (const std::vector< tensor_t > &input)

std::vector< tensor_t >	backward (const std::vector< tensor_t > &out_grads)

void	forward ()

void	backward ()

void	setup (bool reset_weight)

void	init_weight ()

void	clear_grads ()

void	update_weight (optimizer *o, serial_size_t batch_size)

bool	has_same_weights (const layer &rhs, float_t eps) const

virtual void	set_sample_count (serial_size_t sample_count)

template<class Archive >
void	serialize_prolog (Archive &ar)

Public Member Functions inherited from tiny_dnn::node
	node (serial_size_t in_size, serial_size_t out_size)

const std::vector< edgeptr_t > &	prev () const

const std::vector< edgeptr_t > &	next () const

serial_size_t	prev_port (const edge &e) const

serial_size_t	next_port (const edge &e) const

std::vector< node * >	prev_nodes () const

std::vector< node * >	next_nodes () const

Static Public Member Functions
template<typename InputArchive >
static std::shared_ptr< layer >	load_layer (InputArchive &ia)
	generate layer from cereal's Archive

template<typename OutputArchive >
static void	save_layer (OutputArchive &oa, const layer &l)

Protected Attributes
bool	initialized_
	Flag indication whether the layer/node is initialized.

bool	parallelize_
	Flag indicating whether the layer/node operations ara paralellized.

serial_size_t	in_channels_
	The number of input vectors/edges.

serial_size_t	out_channels_
	The number of output vectors/edges.

std::vector< vector_type >	in_type_
	Vector containing the type of data for inputs.

std::vector< vector_type >	out_type_
	Vector containing the type of data for outputs.

core::backend_t	backend_type_
	The current backend type for operations.

std::shared_ptr< core::backend >	backend_
	The backend instance (deprecated)

Device *	device_ptr_ = nullptr
	Pointer to the device on which the layer/node will run.

Protected Attributes inherited from tiny_dnn::node
std::vector< edgeptr_t >	prev_

std::vector< edgeptr_t >	next_

Friends
void	connection_mismatch (const layer &from, const layer &to)

Detailed Description

base class of all kind of NN layers

sub-class should override these methods:

forward_propagation ... body of forward-pass calculation
back_propagation ... body of backward-pass calculation
in_shape ... specify input data shapes
out_shape ... specify output data shapes
layer_type ... name of layer

Constructor & Destructor Documentation

◆ layer()

tiny_dnn::layer::layer	(	const std::vector< vector_type > &	in_type,
		const std::vector< vector_type > &	out_type
	)

inline

Defaul layer constructor that instantiates a N-input, M-output layer.

Parameters

in_type[N]	type of input vector (data, weight, bias...)
out_type[M]	type of output vector

Member Function Documentation

◆ back_propagation()

virtual void tiny_dnn::layer::back_propagation	(	const std::vector< tensor_t * > &	in_data,
		const std::vector< tensor_t * > &	out_data,
		std::vector< tensor_t * > &	out_grad,
		std::vector< tensor_t * > &	in_grad
	)

pure virtual

return delta of previous layer (delta=\frac{dE}{da}, a=wx in fully-connected layer)

Parameters

in_data	input vectors (same vectors as forward_propagation)
out_data	output vectors (same vectors as forward_propagation)
out_grad	gradient of output vectors (i-th vector correspond with out_data[i])
in_grad	gradient of input vectors (i-th vector correspond with in_data[i])

◆ fan_in_size()

virtual serial_size_t tiny_dnn::layer::fan_in_size ( ) const

inlinevirtual

number of incoming connections for each output unit used only for weight/bias initialization methods which require fan-in size (e.g.

xavier) override if the layer has trainable weights, and scale of initialization is important

◆ fan_out_size()

virtual serial_size_t tiny_dnn::layer::fan_out_size ( ) const

inlinevirtual

number of outgoing connections for each input unit used only for weight/bias initialization methods which require fan-out size (e.g.

xavier) override if the layer has trainable weights, and scale of initialization is important

◆ forward_propagation()

virtual void tiny_dnn::layer::forward_propagation	(	const std::vector< tensor_t * > &	in_data,
		std::vector< tensor_t * > &	out_data
	)

pure virtual

Parameters

in_data	input vectors of this layer (data, weight, bias)
out_data	output vectors

◆ in_shape()

virtual std::vector< shape3d > tiny_dnn::layer::in_shape ( ) const

pure virtual

array of input shapes (width x height x depth)

◆ in_size()

serial_size_t tiny_dnn::layer::in_size ( ) const

inline

!

Deprecated:: use in_data_size() instead

◆ layer_type()

virtual std::string tiny_dnn::layer::layer_type ( ) const

pure virtual

name of layer, should be unique for each concrete class

◆ out_shape()

virtual std::vector< shape3d > tiny_dnn::layer::out_shape ( ) const

pure virtual

array of output shapes (width x height x depth)

◆ out_size()

serial_size_t tiny_dnn::layer::out_size ( ) const

inline

!

Deprecated:: use out_data_size() instead

◆ out_value_range()

virtual std::pair< float_t, float_t > tiny_dnn::layer::out_value_range ( ) const

inlinevirtual

return output value range used only for calculating target value from label-id in final(output) layer override properly if the layer is intended to be used as output layer

Reimplemented in tiny_dnn::feedforward_layer< Activation >, and tiny_dnn::feedforward_layer< activation::identity >.

◆ post_update()

virtual void tiny_dnn::layer::post_update ( )

inlinevirtual

return delta2 of previous layer (delta2=\frac{d^2E}{da^2}, diagonal of hessian matrix) it is never called if optimizer is hessian-free

Reimplemented in tiny_dnn::batch_normalization_layer.

◆ set_context()

virtual void tiny_dnn::layer::set_context ( net_phase ctx )

inlinevirtual

notify changing context (train <=> test)

Reimplemented in tiny_dnn::batch_normalization_layer, and tiny_dnn::dropout_layer.

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

tiny_dnn/layers/layer.h
tiny_dnn/util/deserialization_helper.h
tiny_dnn/util/serialization_helper.h

Public Member Functions

Static Public Member Functions

Protected Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

◆ layer()

Member Function Documentation

◆ back_propagation()

◆ fan_in_size()

◆ fan_out_size()

◆ forward_propagation()

◆ in_shape()

◆ in_size()

◆ layer_type()

◆ out_shape()

◆ out_size()

◆ out_value_range()

◆ post_update()

◆ set_context()