MyCaffe.fillers.BilinearFiller< T > Class Template Reference

Fills a Blob with coefficients for bilinear interpolation. More...

Inheritance diagram for MyCaffe.fillers.BilinearFiller< T >:

Public Member Functions
	BilinearFiller (CudaDnn< T > cuda, Log log, FillerParameter p)
	Constructor. More...
override void	Fill (int nCount, long hMem, int nNumAxes=1, int nNumOutputs=1, int nNumChannels=1, int nHeight=1, int nWidth=1)
	Fill a memory with bilinear values. More...
Public Member Functions inherited from MyCaffe.fillers.Filler< T >
	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...

Additional Inherited Members
Static Public Member Functions inherited from MyCaffe.fillers.Filler< T >
static Filler< T >	Create (CudaDnn< T > cuda, Log log, FillerParameter p)
	Create a new Filler instance. More...
Protected Attributes inherited from MyCaffe.fillers.Filler< T >
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

Fills a Blob with coefficients for bilinear interpolation.

A common use case is with the DeconvolutionLayer acting as unsampling. You can upsample a feature amp with shape of (B, C, H, W) by any integer factor using the following proto:

layer {
  name: "upsample", type: "Deconvolution"
  bottom: "{{bottom_name}}" top: "{{top_name}}"
  convolution_param {
    kernel_size: {{2 * factor - factor % 2}} stride: {{factor}}
    num_output: {{C}} group: {{C}}
    pad: {{ceil((factor - 1) / 2.0)}}
    weight_filler: { type: "bilinear" } bias_term: false
  }
  param { lr_mult: 0 decay_mult: 0 }
}

Please use this by replacing '{{}}' with your values. By specifying 'num_output: {{C}} group: {{C}}', it behaves as channel-wise convolution. The filter shape of this deconvolution layer will be (C, 1, K, K) where K is 'kernel_size', and this filler will set a (K, K) interpolation kernel for every channel of the filter identically. The resulting shape of the top featur emap will be (B, C, factor * H, factory * W).

Note, that the learning rate and the weight decay are set to 0 in order to keep coefficient values of bilinear interpolation uncahnged during training. If you apply this to an image, this operation is equivalent to the following call in Python with Scikit.Image:

out = skimage.transform.rescale(img, factor, mode='constant', cval=0)

Template Parameters

T	The base type float or double.

Definition at line 50 of file BilinearFiller.cs.

Constructor & Destructor Documentation

BilinearFiller()

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

Constructor.

Parameters

cuda	Instance of CudaDnn - connection to cuda.
log	Log used for output.
p	Filler parameter that defines the filler settings.

Definition at line 58 of file BilinearFiller.cs.

Member Function Documentation

Fill()

override void MyCaffe.fillers.BilinearFiller< T >.Fill ( int  nCount, long  hMem, int  nNumAxes = 1, int  nNumOutputs = 1, int  nNumChannels = 1, int  nHeight = 1, int  nWidth = 1  )

virtual

Fill a memory with bilinear values.

Parameters

nCount	Specifies the number of items to fill.
hMem	Specifies the handle to GPU memory to fill.
nNumAxes	Optionally, specifies the number of axes (default = 1).
nNumOutputs	Optionally, specifies the number of outputs (default = 1).
nNumChannels	Optionally, specifies the number of channels (default = 1).
nHeight	Optionally, specifies the height (default = 1).
nWidth	Optionally, specifies the width (default = 1).

Implements MyCaffe.fillers.Filler< T >.

Definition at line 73 of file BilinearFiller.cs.

---

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

• C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/fillers/BilinearFiller.cs