Deep learning software for Windows C# programmers.
1using System;
2using System.Collections.Generic;
3using System.Linq;
4using System.Text;
5using MyCaffe.basecode;
6using MyCaffe.param;
7using MyCaffe.common;
9namespace MyCaffe.fillers
18 public class UniformFiller<T> : Filler<T>
19 {
27 : base(cuda, log, p)
28 {
29 }
41 public override void Fill(int nCount, long hMem, int nNumAxes = 1, int nNumOutputs = 1, int nNumChannels = 1, int nHeight = 1, int nWidth = 1)
42 {
43 m_log.CHECK(nCount > 0, "There is no data to fill!");
44 m_log.CHECK_LT(m_param.min, m_param.max, "The min must be less than the max for the uniform filler!");
45 m_cuda.rng_uniform(nCount, m_param.min, m_param.max, hMem);
46 }
47 }
The Log class provides general output in text form.
Definition: Log.cs:13
void CHECK(bool b, string str)
Test a flag for true.
Definition: Log.cs:227
void CHECK_LT(double df1, double df2, string str)
Test whether one number is less than another.
Definition: Log.cs:275
The CudaDnn object is the main interface to the Low-Level Cuda C++ DLL.
Definition: CudaDnn.cs:969
Abstract Filler class used to fill blobs with values.
Definition: Filler.cs:19
FillerParameter m_param
Specifies the filler parameters.
Definition: Filler.cs:31
CudaDnn< T > m_cuda
Specifies the CudaDnn instance used to communicate to the low-level Cuda Dnn DLL.
Definition: Filler.cs:23
Log m_log
Specifies the output log.
Definition: Filler.cs:27
Fills a Blob with uniformly distributed values
override 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 random numbers from a uniform distribution.
UniformFiller(CudaDnn< T > cuda, Log log, FillerParameter p)
Specifies the filler parameters used to create each Filler.
double min
Specifies the minimum value to use with the 'uniform' filler.
double max
Specifies the maximum value to use with the 'uniform' filler.
The MyCaffe.basecode contains all generic types used throughout MyCaffe.
Definition: Annotation.cs:12
The MyCaffe.common namespace contains common MyCaffe classes.
Definition: BatchInput.cs:8
The MyCaffe.fillers namespace contains all fillers including the Filler class.
The MyCaffe.param namespace contains parameters used to create models.
The MyCaffe namespace contains the main body of MyCaffe code that closesly tracks the C++ Caffe open-...
Definition: Annotation.cs:12