Specifies the parameters use to create a Net More...

Inheritance diagram for MyCaffe.param.NetParameter:

Public Member Functions
	NetParameter ()
	Constructor for the parameter. More...

void	Save (BinaryWriter bw)
	Save the parameter to a binary writer. More...

override RawProto	ToProto (string strName)
	Constructor for the parameter. More...

RawProto	ToProto (string strName, bool bIncludeState)
	Save the parameter settings to a RawProto. More...

NetParameter	Clone (bool bCloneLayers=true, int? nSolverCount=null, int? nSolverRank=null)
	Creates a new copy of this instance of the parameter. More...

string	DebugString ()
	Returns a debug string for the network. More...

LayerParameter	FindLayer (LayerParameter.LayerType type, Phase phase=Phase.NONE)
	Locates a layer based on a layer type and phase. More...

int	FindLayerIndex (string strName)
	Locates the index of a layer based on a given layer name. More...

void	SetPoolingReshapeAlgorithm (PoolingParameter.PoolingReshapeAlgorithm alg)
	Sets all pooling layers to use the specified reshape algorithm. More...

Public Member Functions inherited from MyCaffe.basecode.BaseParameter
	BaseParameter ()
	Constructor for the parameter. More...

virtual bool	Compare (BaseParameter p)
	Compare this parameter to another parameter. More...

Static Public Member Functions
static NetParameter	Load (BinaryReader br)
	Load a new instance of the parameter from a binary reader. More...

static NetParameter	FromProto (RawProto rp)
	Parse a RawProto into a new instance of the parameter. More...

static Dictionary< string, BlobShape >	InputFromProto (RawProto rp)
	Collect the inputs from the RawProto. More...

Static Public Member Functions inherited from MyCaffe.basecode.BaseParameter
static double	ParseDouble (string strVal)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out double df)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static float	ParseFloat (string strVal)
	Parse float values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out float f)
	Parse doufloatble values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

Properties
int	ProjectID `[getset]`
	Specifies the ID of the project that created this net param (if any). More...

string	name `[getset]`
	The name of the network. More...

List< string >	input `[getset]`
	The input blobs to the network. More...

List< BlobShape >	input_shape `[getset]`
	The shape of the input blobs. More...

List< int >	input_dim `[getset]`
	DEPRECIATED - 4D input dimensions - use 'input_shape' instead. If specified, for each input blob there should be four values specifying the num, channels, height and width of the input blob. Thus, there should be a total of (4 * input) numbers. More...

bool	force_backward `[getset]`
	Whether the network will force every layer to carry out backward operation. If set False, then whether to carry out backward is determined automatically according to the net structure and learning rates. More...

NetState	state `[getset]`
	The current 'state' of the network, including the phase, level and stage. Some layers may be included/excluded depending on this state and the states specified in the layers' include and exclude fields. More...

bool	debug_info `[getset]`
	Print debugging information about results while running Net::Forward, Net::Backward and Net::Update. More...

List< LayerParameter >	layer `[getset]`
	The layers that make up the net. Each of their configurations, including connectivity and behavior, is specified as a LayerParameter. More...

int	solver_count `[getset]`
	Specifies the number of solvers used in a multi-gpu training session. More...

int	solver_rank `[getset]`
	Specifies the rank of the solver using this network. More...

Detailed Description

Specifies the parameters use to create a Net

Definition at line 17 of file NetParameter.cs.

Constructor & Destructor Documentation

◆ NetParameter()

MyCaffe.param.NetParameter.NetParameter ( )

Constructor for the parameter.

Definition at line 32 of file NetParameter.cs.

Member Function Documentation

◆ Clone()

NetParameter MyCaffe.param.NetParameter.Clone	(	bool	bCloneLayers = `true`,
		int?	nSolverCount = `null`,
		int?	nSolverRank = `null`
	)

Creates a new copy of this instance of the parameter.

Parameters

bCloneLayers	When true, each layer is cloned as well.
nSolverCount	Optionally, specifies a solver count for the clone.
nSolverRank	Optionally, specifies a solver rank for the clone.

Returns: A new instance of this parameter is returned.

Definition at line 314 of file NetParameter.cs.

◆ DebugString()

string MyCaffe.param.NetParameter.DebugString ( )

Returns a debug string for the network.

Returns: The debug string is returned.

Definition at line 346 of file NetParameter.cs.

◆ FindLayer()

LayerParameter MyCaffe.param.NetParameter.FindLayer	(	LayerParameter.LayerType	type,
		Phase	phase = `Phase.NONE`
	)

Locates a layer based on a layer type and phase.

Parameters

type	Specifies the LayerParameter.LayerType to look for.
phase	Optionally, specifies a phase to look for.

Returns

Definition at line 368 of file NetParameter.cs.

◆ FindLayerIndex()

int MyCaffe.param.NetParameter.FindLayerIndex ( string strName )

Locates the index of a layer based on a given layer name.

Parameters

strName Specifies the layer name to look for.

Returns: The index of the layer is returned.

Definition at line 387 of file NetParameter.cs.

◆ FromProto()

static NetParameter MyCaffe.param.NetParameter.FromProto ( RawProto rp )

static

Parse a RawProto into a new instance of the parameter.

Parameters

rp	Specifies the RawProto to parse.

Returns: A new instance of the parameter is returned.

Definition at line 242 of file NetParameter.cs.

◆ InputFromProto()

static Dictionary< string, BlobShape > MyCaffe.param.NetParameter.InputFromProto ( RawProto rp )

static

Collect the inputs from the RawProto.

Parameters

rp	Specifies the raw proto.

Returns: A dictionary of the inputs and their shapes is returned.

Definition at line 284 of file NetParameter.cs.

◆ Load()

static NetParameter MyCaffe.param.NetParameter.Load ( BinaryReader br )

static

Load a new instance of the parameter from a binary reader.

Parameters

br	Specifies the binary reader.

Returns: The new instance is returned.

Definition at line 58 of file NetParameter.cs.

◆ Save()

void MyCaffe.param.NetParameter.Save ( BinaryWriter bw )

Save the parameter to a binary writer.

Parameters

bw	Specifies the binary writer to use.

Definition at line 41 of file NetParameter.cs.

◆ SetPoolingReshapeAlgorithm()

void MyCaffe.param.NetParameter.SetPoolingReshapeAlgorithm ( PoolingParameter.PoolingReshapeAlgorithm alg )

Sets all pooling layers to use the specified reshape algorithm.

Parameters

alg	Specifies the reshape algorithm to use (DEFAULT, CAFFE or ONNX).

Definition at line 402 of file NetParameter.cs.

◆ ToProto() [1/2]

override RawProto MyCaffe.param.NetParameter.ToProto ( string strName )

virtual

Constructor for the parameter.

Implements MyCaffe.basecode.BaseParameter.

Definition at line 195 of file NetParameter.cs.

◆ ToProto() [2/2]

RawProto MyCaffe.param.NetParameter.ToProto	(	string	strName,
		bool	bIncludeState
	)

Save the parameter settings to a RawProto.

Parameters

strName	Specifies the name, typically 'root'.
bIncludeState	Specifies whether or not to also include the state when saving.

Returns: The RawProto representing the settings is returned.

Definition at line 206 of file NetParameter.cs.

Property Documentation

◆ debug_info

bool MyCaffe.param.NetParameter.debug_info

getset

Print debugging information about results while running Net::Forward, Net::Backward and Net::Update.

Definition at line 157 of file NetParameter.cs.

◆ force_backward

bool MyCaffe.param.NetParameter.force_backward

getset

Whether the network will force every layer to carry out backward operation. If set False, then whether to carry out backward is determined automatically according to the net structure and learning rates.

Definition at line 134 of file NetParameter.cs.

◆ input

List<string> MyCaffe.param.NetParameter.input

getset

The input blobs to the network.

Definition at line 99 of file NetParameter.cs.

◆ input_dim

List<int> MyCaffe.param.NetParameter.input_dim

getset

DEPRECIATED - 4D input dimensions - use 'input_shape' instead. If specified, for each input blob there should be four values specifying the num, channels, height and width of the input blob. Thus, there should be a total of (4 * input) numbers.

Definition at line 122 of file NetParameter.cs.

◆ input_shape

List<BlobShape> MyCaffe.param.NetParameter.input_shape

getset

The shape of the input blobs.

Definition at line 109 of file NetParameter.cs.

◆ layer

List<LayerParameter> MyCaffe.param.NetParameter.layer

getset

The layers that make up the net. Each of their configurations, including connectivity and behavior, is specified as a LayerParameter.

Definition at line 168 of file NetParameter.cs.

◆ name

string MyCaffe.param.NetParameter.name

getset

The name of the network.

Definition at line 89 of file NetParameter.cs.

◆ ProjectID

int MyCaffe.param.NetParameter.ProjectID

getset

Specifies the ID of the project that created this net param (if any).

Definition at line 79 of file NetParameter.cs.

◆ solver_count

int MyCaffe.param.NetParameter.solver_count

getset

Specifies the number of solvers used in a multi-gpu training session.

Definition at line 178 of file NetParameter.cs.

◆ solver_rank

int MyCaffe.param.NetParameter.solver_rank

getset

Specifies the rank of the solver using this network.

Definition at line 188 of file NetParameter.cs.

◆ state

NetState MyCaffe.param.NetParameter.state

getset

The current 'state' of the network, including the phase, level and stage. Some layers may be included/excluded depending on this state and the states specified in the layers' include and exclude fields.

Definition at line 146 of file NetParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param/NetParameter.cs

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Constructor & Destructor Documentation

◆ NetParameter()

Member Function Documentation

◆ Clone()

◆ DebugString()

◆ FindLayer()

◆ FindLayerIndex()

◆ FromProto()

◆ InputFromProto()

◆ Load()

◆ Save()

◆ SetPoolingReshapeAlgorithm()

◆ ToProto() [1/2]

◆ ToProto() [2/2]

Property Documentation

◆ debug_info

◆ force_backward

◆ input

◆ input_dim

◆ input_shape

◆ layer

◆ name

◆ ProjectID

◆ solver_count

◆ solver_rank

◆ state