MyCaffe  1.12.2.41
Deep learning software for Windows C# programmers.
MyCaffe.param.nt.OneHotParameter Class Reference

Specifies the parameters used by the OneHotLayer More...

Inheritance diagram for MyCaffe.param.nt.OneHotParameter:
MyCaffe.param.LayerParameterBase MyCaffe.basecode.BaseParameter MyCaffe.basecode.IBinaryPersist

Public Member Functions

 OneHotParameter ()
 The constructor. 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 OneHotParameter 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

int axis [getset]
 Specifies the axis over which to apply the one-hot vectoring. More...
 
int min_axes [getset]
 Specifies the minimum number of axes. Axes of size 1 are added to the current axis count up to the minimum. More...
 
uint num_output [getset]
 Specifies the number of items within the one-hot vector output. More...
 
double min [getset]
 Specifies the minimum data range over which to bucketize for the one-hot vector input. More...
 
double max [getset]
 Specifies the maximum data range over which to bucketize for the one-hot vector input. More...
 

Additional Inherited Members

- 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 OneHotLayer

The OneHotLayer converts each single input into 'num_output' vector items each containing a 1 or 0 if the input falls within the range of the given vector item.

For example, when using a min/max range of -1,1 spread across 8 vector items (num_output), inputs less than or equal to -1 go in the first bucket, inputs greater than or equal to 1 go in the last bucket and values in between -1 and 1 go into their repsective buckets (e.g input -0.12 goes into bucket index 3 and input 0.12 goes into bucket 4)

8 inputs span across -1 to 1 range creates the following buckets:

index: 0 1 2 3 4 5 6 7 bucket: [-1.00,-0.75][-0.75,-0.50][-0.50,-0.25][-0.25, 0.00][0.00, 0.25][0.25, 0.50][0.50, 0.75][0.75, 1.00]

input: -0.75 or less set bucket #0 = 1 input: 0.75 or greater set bucket #7 = 1

Except for end buckets, inputs are placed in bucket where: bucket min <= input < bucket max.

Definition at line 35 of file OneHotParameter.cs.

Constructor & Destructor Documentation

◆ OneHotParameter()

MyCaffe.param.nt.OneHotParameter.OneHotParameter ( )

The constructor.

Definition at line 46 of file OneHotParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.nt.OneHotParameter.Clone ( )
virtual

Creates a new copy of this instance of the parameter.

Returns
A new instance of this parameter is returned.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 136 of file OneHotParameter.cs.

◆ Copy()

override void MyCaffe.param.nt.OneHotParameter.Copy ( LayerParameterBase  src)
virtual

Copy on parameter to another.

Parameters
srcSpecifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 121 of file OneHotParameter.cs.

◆ FromProto()

static OneHotParameter MyCaffe.param.nt.OneHotParameter.FromProto ( RawProto  rp)
static

Parses the parameter from a RawProto.

Parameters
rpSpecifies the RawProto to parse.
Returns
A new instance of the parameter is returned.

Definition at line 166 of file OneHotParameter.cs.

◆ Load()

override object MyCaffe.param.nt.OneHotParameter.Load ( System.IO.BinaryReader  br,
bool  bNewInstance = true 
)

Load the parameter from a binary reader.

Parameters
brSpecifies the binary reader.
bNewInstanceWhen 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.

Definition at line 106 of file OneHotParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.nt.OneHotParameter.ToProto ( string  strName)
virtual

Convert the parameter into a RawProto.

Parameters
strNameSpecifies the name to associate with the RawProto.
Returns
The new RawProto is returned.

Implements MyCaffe.basecode.BaseParameter.

Definition at line 148 of file OneHotParameter.cs.

Property Documentation

◆ axis

int MyCaffe.param.nt.OneHotParameter.axis
getset

Specifies the axis over which to apply the one-hot vectoring.

Definition at line 54 of file OneHotParameter.cs.

◆ max

double MyCaffe.param.nt.OneHotParameter.max
getset

Specifies the maximum data range over which to bucketize for the one-hot vector input.

Definition at line 94 of file OneHotParameter.cs.

◆ min

double MyCaffe.param.nt.OneHotParameter.min
getset

Specifies the minimum data range over which to bucketize for the one-hot vector input.

Definition at line 84 of file OneHotParameter.cs.

◆ min_axes

int MyCaffe.param.nt.OneHotParameter.min_axes
getset

Specifies the minimum number of axes. Axes of size 1 are added to the current axis count up to the minimum.

Definition at line 64 of file OneHotParameter.cs.

◆ num_output

uint MyCaffe.param.nt.OneHotParameter.num_output
getset

Specifies the number of items within the one-hot vector output.

Definition at line 74 of file OneHotParameter.cs.


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