Specifies the parameters used by the RecurrentLayer. More...

Inheritance diagram for MyCaffe.param.RecurrentParameter:

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

string	useCaffeReason ()
	Returns the reason that Caffe version was used instead of NVIDIA's cuDnn. More...

bool	useCudnn ()
	Queries whether or not to use NVIDIA's cuDnn. More...

override object	Load (BinaryReader br, bool bNewInstance=true)
	Load the parameter from a binary reader. More...

override LayerParameterBase	Clone ()
	Creates a new copy of this instance of the parameter. More...

override void	Copy (LayerParameterBase src)
	Copy on parameter to another. More...

override RawProto	ToProto (string strName)
	Convert the parameter into a RawProto. More...

Public Member Functions inherited from MyCaffe.param.EngineParameter
	EngineParameter ()
	Constructor for the parameter. More...

override object	Load (System.IO.BinaryReader br, bool bNewInstance=true)
	Load the parameter from a binary reader. More...

Public Member Functions inherited from MyCaffe.param.LayerParameterBase
	LayerParameterBase ()
	Constructor for the parameter. More...

virtual string	PrepareRunModelInputs ()
	This method gives derivative classes a chance specify model inputs required by the run model. More...

virtual void	PrepareRunModel (LayerParameter p)
	This method gives derivative classes a chance to prepare the layer for a run-model. More...

void	Save (BinaryWriter bw)
	Save this parameter to a binary writer. 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 new RecurrentParameter	FromProto (RawProto rp)
	Parses the parameter from a RawProto. More...

Static Public Member Functions inherited from MyCaffe.param.EngineParameter
static EngineParameter	FromProto (RawProto rp)
	Parses the parameter from a 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
bool	use_cudnn_rnn8_if_supported `[getset]`
	Specifies to use cuDnn RNN8 if supported (requires cuDnn 8.0 or higher), (default = false). More...

bool	auto_repeat_hidden_states_across_layers `[getset]`
	Auto repeat the hidden and cell states so that a separate state is fed to each layer. More...

bool	batch_first `[getset]`
	The input and outputs are shaped with the batch in the first dimension. More...

bool	bidirectional `[getset]`
	Specifies whether the network is bidirectional (true) or unidirectional (false - default). More...

uint	num_output `[getset]`
	The dimension of the output (and usually hidden state) representation – must be explicitly set to non-zero. More...

FillerParameter	weight_filler `[getset]`
	The filler for the weights. More...

FillerParameter	bias_filler `[getset]`
	The filler for the bias. More...

bool	debug_info `[getset]`
	Whether to enable displaying debug info in the unrolled recurrent net. More...

bool	expose_hidden_input `[getset]`
	Whether to add as additional inputs (bottoms) the initial hidden state blobss. The number of additional bottom/top blobs required depends on the recurrent architecture – e.g., 1 for RNN's, 2 for LSTM's. More...

bool	expose_hidden_output `[getset]`
	Whether to add as additional outputs (tops) the final timestep hidden state blobs. The number of additional bottom/top blobs required depends on the recurrent architecture – e.g., 1 for RNN's, 2 for LSTM's. More...

uint	num_layers `[getset]`
	The number of LSTM layers to implement. More...

double	dropout_ratio `[getset]`
	Specifies the dropout ratio. (e.g. the probability that values will be dropped out and set to zero. A value of 0.25 = 25% chance that a value is set to 0, and dropped out.) More...

long	dropout_seed `[getset]`
	Specifies the seed used by cuDnn for random number generation. More...

bool	cudnn_enable_tensor_cores `[getset]`
	Specifies to enable the CUDA tensor cores when performing the rnn operations which is faster but not supported by all GPU's. More...

Properties inherited from MyCaffe.param.EngineParameter
Engine	engine `[getset]`
	Specifies the Engine in use. More...

Additional Inherited Members
Public Types inherited from MyCaffe.param.EngineParameter
enum	Engine { DEFAULT = 0 , CAFFE = 1 , CUDNN = 2 }
	Defines the type of engine to use. More...

Public Types inherited from MyCaffe.param.LayerParameterBase
enum	LABEL_TYPE { NONE , SINGLE , MULTIPLE , ONLY_ONE }
	Defines the label type. More...

Detailed Description

Specifies the parameters used by the RecurrentLayer.

Definition at line 17 of file RecurrentParameter.cs.

Constructor & Destructor Documentation

◆ RecurrentParameter()

MyCaffe.param.RecurrentParameter.RecurrentParameter ( )

Constructor for the parameter.

Definition at line 35 of file RecurrentParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.RecurrentParameter.Clone ( )

virtual

Creates a new copy of this instance of the parameter.

Returns: A new instance of this parameter is returned.

Reimplemented from MyCaffe.param.EngineParameter.

Definition at line 229 of file RecurrentParameter.cs.

◆ Copy()

override void MyCaffe.param.RecurrentParameter.Copy ( LayerParameterBase src )

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Reimplemented from MyCaffe.param.EngineParameter.

Definition at line 237 of file RecurrentParameter.cs.

◆ FromProto()

static new RecurrentParameter MyCaffe.param.RecurrentParameter.FromProto ( RawProto rp )

static

Parses the parameter from a RawProto.

Parameters

rp	Specifies the RawProto to parse.

Returns: A new instance of the parameter is returned.

Definition at line 306 of file RecurrentParameter.cs.

◆ Load()

override object MyCaffe.param.RecurrentParameter.Load	(	BinaryReader	br,
		bool	bNewInstance = `true`
	)

virtual

Load the parameter from a binary reader.

Parameters

br	Specifies the binary reader.
bNewInstance	When true a new instance is created (the default), otherwise the existing instance is loaded from the binary reader.

Returns: Returns an instance of the parameter.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 217 of file RecurrentParameter.cs.

◆ ToProto()

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

virtual

Convert the parameter into a RawProto.

Parameters

strName Specifies the name to associate with the RawProto.

Returns: The new RawProto is returned.

Reimplemented from MyCaffe.param.EngineParameter.

Definition at line 266 of file RecurrentParameter.cs.

◆ useCaffeReason()

string MyCaffe.param.RecurrentParameter.useCaffeReason ( )

Returns the reason that Caffe version was used instead of NVIDIA's cuDnn.

Returns

Definition at line 43 of file RecurrentParameter.cs.

◆ useCudnn()

bool MyCaffe.param.RecurrentParameter.useCudnn ( )

Queries whether or not to use NVIDIA's cuDnn.

CAFFE is the DEFAULT engine.

Returns: Returns true when cuDnn is to be used, false otherwise.

Definition at line 87 of file RecurrentParameter.cs.

Property Documentation

◆ auto_repeat_hidden_states_across_layers

bool MyCaffe.param.RecurrentParameter.auto_repeat_hidden_states_across_layers

getset

Auto repeat the hidden and cell states so that a separate state is fed to each layer.

Definition at line 64 of file RecurrentParameter.cs.

◆ batch_first

bool MyCaffe.param.RecurrentParameter.batch_first

getset

The input and outputs are shaped with the batch in the first dimension.

Definition at line 74 of file RecurrentParameter.cs.

◆ bias_filler

FillerParameter MyCaffe.param.RecurrentParameter.bias_filler

getset

The filler for the bias.

Definition at line 130 of file RecurrentParameter.cs.

◆ bidirectional

bool MyCaffe.param.RecurrentParameter.bidirectional

getset

Specifies whether the network is bidirectional (true) or unidirectional (false - default).

Definition at line 99 of file RecurrentParameter.cs.

◆ cudnn_enable_tensor_cores

bool MyCaffe.param.RecurrentParameter.cudnn_enable_tensor_cores

getset

Specifies to enable the CUDA tensor cores when performing the rnn operations which is faster but not supported by all GPU's.

When run on GPU's that do not support Tensor cores, the default math (non-tensor core) is used.

Definition at line 210 of file RecurrentParameter.cs.

◆ debug_info

bool MyCaffe.param.RecurrentParameter.debug_info

getset

Whether to enable displaying debug info in the unrolled recurrent net.

Definition at line 140 of file RecurrentParameter.cs.

◆ dropout_ratio

double MyCaffe.param.RecurrentParameter.dropout_ratio

getset

Specifies the dropout ratio. (e.g. the probability that values will be dropped out and set to zero. A value of 0.25 = 25% chance that a value is set to 0, and dropped out.)

The drop-out layer is only used with cuDnn when more than one layer are used.

Definition at line 186 of file RecurrentParameter.cs.

◆ dropout_seed

long MyCaffe.param.RecurrentParameter.dropout_seed

getset

Specifies the seed used by cuDnn for random number generation.

The drop-out layer is only used with cuDnn when more than one layer are used.

Definition at line 197 of file RecurrentParameter.cs.

◆ expose_hidden_input

bool MyCaffe.param.RecurrentParameter.expose_hidden_input

getset

Whether to add as additional inputs (bottoms) the initial hidden state blobss. The number of additional bottom/top blobs required depends on the recurrent architecture – e.g., 1 for RNN's, 2 for LSTM's.

Definition at line 152 of file RecurrentParameter.cs.

◆ expose_hidden_output

bool MyCaffe.param.RecurrentParameter.expose_hidden_output

getset

Whether to add as additional outputs (tops) the final timestep hidden state blobs. The number of additional bottom/top blobs required depends on the recurrent architecture – e.g., 1 for RNN's, 2 for LSTM's.

Definition at line 164 of file RecurrentParameter.cs.

◆ num_layers

uint MyCaffe.param.RecurrentParameter.num_layers

getset

The number of LSTM layers to implement.

This parameter only applies to cuDnn.

Definition at line 175 of file RecurrentParameter.cs.

◆ num_output

uint MyCaffe.param.RecurrentParameter.num_output

getset

The dimension of the output (and usually hidden state) representation – must be explicitly set to non-zero.

Definition at line 110 of file RecurrentParameter.cs.

◆ use_cudnn_rnn8_if_supported

bool MyCaffe.param.RecurrentParameter.use_cudnn_rnn8_if_supported

getset

Specifies to use cuDnn RNN8 if supported (requires cuDnn 8.0 or higher), (default = false).

Definition at line 54 of file RecurrentParameter.cs.

◆ weight_filler

FillerParameter MyCaffe.param.RecurrentParameter.weight_filler

getset

The filler for the weights.

Definition at line 120 of file RecurrentParameter.cs.

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

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

Public Member Functions

Static Public Member Functions

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ RecurrentParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

◆ useCaffeReason()

◆ useCudnn()

Property Documentation

◆ auto_repeat_hidden_states_across_layers

◆ batch_first

◆ bias_filler

◆ bidirectional

◆ cudnn_enable_tensor_cores

◆ debug_info

◆ dropout_ratio

◆ dropout_seed

◆ expose_hidden_input

◆ expose_hidden_output

◆ num_layers

◆ num_output

◆ use_cudnn_rnn8_if_supported

◆ weight_filler