MyCaffe  1.11.8.27
Deep learning software for Windows C# programmers.
MyCaffe.fillers.Filler< T > Class Template Referenceabstract

Abstract Filler class used to fill blobs with values. More...

Inheritance diagram for MyCaffe.fillers.Filler< T >:
MyCaffe.fillers.BilinearFiller< T > MyCaffe.fillers.ConstantFiller< T > MyCaffe.fillers.GaussianFiller< T > MyCaffe.fillers.MsraFiller< T > MyCaffe.fillers.PositiveUnitballFiller< T > MyCaffe.fillers.SequenceFiller< T > MyCaffe.fillers.UniformFiller< T > MyCaffe.fillers.XavierFiller< T >

Public Member Functions

 Filler (CudaDnn< T > cuda, Log log, FillerParameter p)
 Constructor. More...
 
void Fill (Blob< T > b)
 Fill the blob with values based on the actual filler used. More...
 
abstract void Fill (int nCount, long hMem, int nNumAxes=1, int nNumOutputs=1, int nNumChannels=1, int nHeight=1, int nWidth=1)
 Fill the memory with values based on the actual filler used. More...
 

Static Public Member Functions

static Filler< T > Create (CudaDnn< T > cuda, Log log, FillerParameter p)
 Create a new Filler instance. More...
 

Protected Attributes

CudaDnn< T > m_cuda
 Specifies the CudaDnn instance used to communicate to the low-level Cuda Dnn DLL. More...
 
Log m_log
 Specifies the output log. More...
 
FillerParameter m_param
 Specifies the filler parameters. More...
 

Detailed Description

Abstract Filler class used to fill blobs with values.

Template Parameters
TThe base type float or double.

Definition at line 18 of file Filler.cs.

Constructor & Destructor Documentation

◆ Filler()

MyCaffe.fillers.Filler< T >.Filler ( CudaDnn< T >  cuda,
Log  log,
FillerParameter  p 
)

Constructor.

Parameters
cudaInstance of CudaDnn - connection to cuda.
logLog used for output.
pFiller parameter that defines the filler settings.

Definition at line 39 of file Filler.cs.

Member Function Documentation

◆ Create()

static Filler< T > MyCaffe.fillers.Filler< T >.Create ( CudaDnn< T >  cuda,
Log  log,
FillerParameter  p 
)
static

Create a new Filler instance.

Parameters
cudaSpecifies the CudaDnn instance.
logSpecifies the log for output.
pSpecifies the filler parameter.
Returns

Definition at line 79 of file Filler.cs.

◆ Fill() [1/2]

void MyCaffe.fillers.Filler< T >.Fill ( Blob< T >  b)

Fill the blob with values based on the actual filler used.

Parameters
bSpecifies the blob to fill.

Definition at line 50 of file Filler.cs.

◆ Fill() [2/2]

abstract void MyCaffe.fillers.Filler< T >.Fill ( int  nCount,
long  hMem,
int  nNumAxes = 1,
int  nNumOutputs = 1,
int  nNumChannels = 1,
int  nHeight = 1,
int  nWidth = 1 
)
pure virtual

Fill the memory with values based on the actual filler used.

Parameters
nCountSpecifies the number of items to fill.
hMemSpecifies the handle to GPU memory to fill.
nNumAxesOptionally, specifies the number of axes (default = 1).
nNumOutputsOptionally, specifies the number of outputs (default = 1).
nNumChannelsOptionally, specifies the number of channels (default = 1).
nHeightOptionally, specifies the height (default = 1).
nWidthOptionally, specifies the width (default = 1).

Implemented in MyCaffe.fillers.BilinearFiller< T >, MyCaffe.fillers.ConstantFiller< T >, MyCaffe.fillers.GaussianFiller< T >, MyCaffe.fillers.MsraFiller< T >, MyCaffe.fillers.PositiveUnitballFiller< T >, MyCaffe.fillers.SequenceFiller< T >, MyCaffe.fillers.UniformFiller< T >, and MyCaffe.fillers.XavierFiller< T >.

Member Data Documentation

◆ m_cuda

CudaDnn<T> MyCaffe.fillers.Filler< T >.m_cuda
protected

Specifies the CudaDnn instance used to communicate to the low-level Cuda Dnn DLL.

Definition at line 23 of file Filler.cs.

◆ m_log

Log MyCaffe.fillers.Filler< T >.m_log
protected

Specifies the output log.

Definition at line 27 of file Filler.cs.

◆ m_param

FillerParameter MyCaffe.fillers.Filler< T >.m_param
protected

Specifies the filler parameters.

Definition at line 31 of file Filler.cs.


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