MyCaffe
1.12.2.41
Deep learning software for Windows C# programmers.
|
Specifies the parameters for the TokenizedDataLayer. More...
Public Types | |
enum | VOCABULARY_TYPE { CHARACTER , WORD , SENTENCEPIECE , CUSTOM } |
Defines the vocabulary type to use. More... | |
enum | SAMPLE_METHOD { ARGMAX , PROBABILITY } |
Defines the sampling method used. More... | |
enum | INPUT_TYPE { TEXT_FILE , CUSTOM } |
Defines the input type used. More... | |
Public Types inherited from MyCaffe.param.LayerParameterBase | |
enum | LABEL_TYPE { NONE , SINGLE , MULTIPLE , ONLY_ONE } |
Defines the label type. More... | |
Public Member Functions | |
TokenizedDataParameter () | |
Constructor for the parameter. More... | |
override object | Load (System.IO.BinaryReader br, bool bNewInstance=true) |
Load the parameter from a binary reader. More... | |
override void | Copy (LayerParameterBase src) |
Copy on parameter to another. More... | |
override LayerParameterBase | Clone () |
Creates a new copy of this instance of the parameter. More... | |
override RawProto | ToProto (string strName) |
Convert the parameter into a RawProto. 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... | |
abstract object | Load (BinaryReader br, bool bNewInstance=true) |
Load the parameter from a binary reader. 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 TokenizedDataParameter | 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... | |
Protected Attributes | |
PythonParameter | m_pythonParam = new PythonParameter() |
Python layer implementations use this parameter for Python specific settings such as the location of the runtime. More... | |
Properties | |
PythonParameter | python_param [getset] |
Specifies the PythonParameter used by the python implementation of the TokenizedDataPairsLayer, otherwise this is null. More... | |
int? | seed [getset] |
Specifies the seed used to initialize the random number generator (normally only for testing). More... | |
INPUT_TYPE | input_type [getset] |
Specifies data source input type. More... | |
VOCABULARY_TYPE | vocabulary_type [getset] |
Specifies the vocabulary type to use. More... | |
SAMPLE_METHOD | sample_method [getset] |
Specifies the sampling method used when post processing logits (default = ARGMAX). More... | |
string | source [getset] |
Specifies the data source based on the INPUT_TYPE used. Each dataset has both a training and testing data source. More... | |
string | debug_index_file [getset] |
Specifies an optional data index file used for debugging only. More... | |
uint | batch_size [getset] |
The number of heads used. More... | |
uint | block_size [getset] |
Specifies size of the block. More... | |
Specifies the parameters for the TokenizedDataLayer.
Definition at line 16 of file TokenizedDataParameter.cs.
Defines the input type used.
Definition at line 74 of file TokenizedDataParameter.cs.
Defines the sampling method used.
Enumerator | |
---|---|
ARGMAX | Specifies to use the argmax method. |
PROBABILITY | Specifies to use the probability sampling method where the probabilities are totaled until the sum >= a random number. |
Definition at line 58 of file TokenizedDataParameter.cs.
Defines the vocabulary type to use.
Definition at line 35 of file TokenizedDataParameter.cs.
MyCaffe.param.gpt.TokenizedDataParameter.TokenizedDataParameter | ( | ) |
Constructor for the parameter.
Definition at line 87 of file TokenizedDataParameter.cs.
|
virtual |
Creates a new copy of this instance of the parameter.
Implements MyCaffe.param.LayerParameterBase.
Definition at line 207 of file TokenizedDataParameter.cs.
|
virtual |
Copy on parameter to another.
src | Specifies the parameter to copy. |
Implements MyCaffe.param.LayerParameterBase.
Definition at line 191 of file TokenizedDataParameter.cs.
|
static |
Parses the parameter from a RawProto.
rp | Specifies the RawProto to parse. |
Definition at line 247 of file TokenizedDataParameter.cs.
override object MyCaffe.param.gpt.TokenizedDataParameter.Load | ( | System.IO.BinaryReader | br, |
bool | bNewInstance = true |
||
) |
Load the parameter from a binary reader.
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. |
Definition at line 179 of file TokenizedDataParameter.cs.
|
virtual |
Convert the parameter into a RawProto.
strName | Specifies the name to associate with the RawProto. |
Implements MyCaffe.basecode.BaseParameter.
Definition at line 219 of file TokenizedDataParameter.cs.
|
protected |
Python layer implementations use this parameter for Python specific settings such as the location of the runtime.
Definition at line 21 of file TokenizedDataParameter.cs.
|
getset |
The number of heads used.
Definition at line 163 of file TokenizedDataParameter.cs.
|
getset |
Specifies size of the block.
Definition at line 172 of file TokenizedDataParameter.cs.
|
getset |
Specifies an optional data index file used for debugging only.
Definition at line 153 of file TokenizedDataParameter.cs.
|
getset |
Specifies data source input type.
Definition at line 113 of file TokenizedDataParameter.cs.
|
getset |
Specifies the PythonParameter used by the python implementation of the TokenizedDataPairsLayer, otherwise this is null.
Definition at line 94 of file TokenizedDataParameter.cs.
|
getset |
Specifies the sampling method used when post processing logits (default = ARGMAX).
Definition at line 133 of file TokenizedDataParameter.cs.
|
getset |
Specifies the seed used to initialize the random number generator (normally only for testing).
Definition at line 103 of file TokenizedDataParameter.cs.
|
getset |
Specifies the data source based on the INPUT_TYPE used. Each dataset has both a training and testing data source.
Definition at line 143 of file TokenizedDataParameter.cs.
|
getset |
Specifies the vocabulary type to use.
Definition at line 123 of file TokenizedDataParameter.cs.