The BaseConvolutionLayer is an abstract base class that factors out BLAS code common to ConvolutionLayer and DeconvolutionLayer More...

Inheritance diagram for MyCaffe.layers.BaseConvolutionLayer< T >:

Public Member Functions
	BaseConvolutionLayer (CudaDnn< T > cuda, Log log, LayerParameter p)
	The BaseConvolutionLayer constructor. More...

override bool	ReInitializeParameters (WEIGHT_TARGET target)
	Re-initialize the parameters of the layer. More...

override void	LayerSetUp (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Setup the layer. More...

override void	Reshape (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Reshape the bottom (input) and top (output) blobs. More...

Public Member Functions inherited from MyCaffe.layers.Layer< T >
	Layer (CudaDnn< T > cuda, Log log, LayerParameter p)
	The Layer constructor. More...

void	Dispose ()
	Releases all GPU and host resources used by the Layer. More...

virtual void	ConnectLoss (LossLayer< T > layer)
	Called to connect the loss OnLoss event to a specified layer (typically the data layer). More...

virtual BlobCollection< T >	PreProcessInput (PropertySet customInput, out int nSeqLen, BlobCollection< T > colBottom=null)
	The PreprocessInput allows derivative data layers to convert a property set of input data into the bottom blob collection used as intput. More...

virtual bool	PreProcessInput (string strEncInput, int? nDecInput, BlobCollection< T > colBottom)
	Preprocess the input data for the RUN phase. More...

virtual List< Tuple< string, int, double > >	PostProcessOutput (Blob< T > blobSofmtax, int nK=1)
	The PostProcessOutput allows derivative data layers to post-process the results, converting them back into text results (e.g., detokenizing). More...

virtual List< Tuple< string, int, double > >	PostProcessLogitsOutput (int nCurIdx, Blob< T > blobLogits, Layer< T > softmax, int nAxis, int nK=1)
	The PostProcessLogitsOutput allows derivative data layers to post-process the results, converting them back into text results (e.g., detokenizing). More...

virtual string	PostProcessFullOutput (Blob< T > blobSoftmax)
	The PostProcessFullOutput allows derivative data layers to post-process the results, usually be detokenizing the data in the blobSoftmax. More...

virtual string	PostProcessOutput (int nIdx)
	Convert the index to the word. More...

virtual void	SetOnDebug (EventHandler< GetWorkBlobArgs< T > > fn)
	Set the OnDebug event. More...

virtual void	ResetOnDebug (EventHandler< GetWorkBlobArgs< T > > fn)
	Reset the OnDebug event, disabling it. More...

void	SetNetReshapeRequest ()
	Called by the Net when requesting a reshape. More...

void	SetPhase (Phase phase)
	Changes the layer's Phase to the one specified. More...

void	Setup (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Implements common Layer setup functionality. More...

virtual void	SetNetParameterUsed (NetParameter np)
	This function allows other layers to gather needed information from the NetParameters if any, and is called when initialzing the Net. More...

void	ConvertToBase (BlobCollection< T > col)
	ConvertToBase converts any blobs in a collection that are in half size to the base size. More...

double	Forward (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Given the bottom (input) Blobs, this function computes the top (output) Blobs and the loss. More...

void	Backward (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
	Given the top Blob error gradients, compute the bottom Blob error gradients. More...

double	loss (int nTopIdx)
	Returns the scalar loss associated with the top Blob at a given index. More...

void	set_loss (int nTopIdx, double dfLoss)
	Sets the loss associated with a top Blob at a given index. More...

virtual bool	AllowForceBackward (int nBottomIdx)
	Return whether to allow More...

bool	param_propagate_down (int nParamIdx)
	Returns whether or not the Layer should compute gradients w.r.t. a parameter at a particular index given by a parameter index. More...

void	set_param_propagate_down (int nParamIdx, bool bPropagate)
	Sets whether or not the Layer should compute gradients w.r.t. a parameter at a particular index given by a parameter index. More...

void	SetEnablePassthrough (bool bEnable)
	Enables/disables the pass-through mode. More...

Protected Member Functions
override void	dispose ()
	Releases all GPU and host resources used by the Layer. More...

ulong	getWorkspaceLimitInBytes (bool bUseTensorCores=false)
	Returns the workspace limit in bytes based on the cudnn_workspace_limit setting. More...

override void	setup_internal_blobs (BlobCollection< T > col)
	Derivative layers should add all internal blobws to the 'col' provided. More...

override WorkspaceArgs	getWorkspace ()
	Retruns the WorkspaceArgs containing the workspace used by this Layer. More...

override bool	setWorkspace (ulong lSizeInBytes)
	If not already set, allocates the workspace needed in GPU memory. More...

void	forward_gemm (long hInput, int nInputOffset, long hWeights, long hOutput, int nOutputOffset, bool bSkipIm2Col=false)
	Helper function that abstract away the column buffer and gemm arguments. More...

void	forward_bias (long hOutput, int nOutputOffset, long hBias)
	Helper function that abstracts away the column buffer and gemm arguments. More...

void	backward_gemm (long hOutput, int nOutputOffset, long hWeights, long hInput, int nInputOffset)
	Helper function that abstract away the column buffer and gemm arguments. More...

void	weight_gemm (long hInput, int nInputOffset, long hOutput, int nOutputOffset, long hWeights)
	Helper function that abstract away the column buffer and gemm arguments. More...

void	backward_bias (long hBias, long hInput, int nInputOffset)
	Helper function that abstracts away the column buffer and gemm arguments. More...

int	input_shape (int i)
	Returns the spatial dimensions of the input. More...

abstract bool	reverse_dimensions ()
	reverse_dimensions should return true iff we are implementing deconv, so that conv helpers know which dimensions to use. More...

abstract void	compute_output_shape ()
	Compute height_out and width_out from other parameters. More...

Protected Member Functions inherited from MyCaffe.layers.Layer< T >
void	dispose (ref Layer< T > l)
	Helper method used to dispose internal layers. More...

void	dispose (ref Blob< T > b)
	Helper method used to dispose internal blobs. More...

void	dispose (ref BlobCollection< T > rg, bool bSetToNull=true)
	Dispose the blob collection. More...

GetIterationArgs	getCurrentIteration ()
	Fires the OnGetIteration event to query the current iteration. More...

long	convert_to_full (int nCount, long hMem)
	Convert half memory to full memory. More...

void	convert (BlobCollection< T > col)
	Convert a collection of blobs from / to half size. More...

virtual bool	reshapeNeeded (BlobCollection< T > colBottom, BlobCollection< T > colTop, bool bReset=true)
	Tests the shapes of both the bottom and top blobs and if they are the same as the previous sizing, returns false indicating that no reshape is needed. More...

bool	compareShapes (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Compare the shapes of the top and bottom and if the same, return true, otherwise false. More...

void	setShapes (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Set the internal shape sizes - used when determining if a Reshape is necessary. More...

abstract void	forward (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	This forward abstract function must be overriden by each derived Layer class to compute the top (output) Blobs for this layer. More...

abstract void	backward (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
	This backward abstract function must be overriden by each derived Layer class to compute the bottom (intput) Blob diffs for this Layer. More...

void	CheckBlobCounts (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Called by the Layer::Setup function to check the number of bottom (input) and top (output) Blobs provided match the expected number of blobs expected via the {EactNum,Min,Max}{Bottom,Top}Blobs functions. More...

void	SetLossWeights (BlobCollection< T > colTop)
	Called by Layer::Setup to initialize the weights associated with any top (output) Blobs in the loss function ans store non-zero loss weights in the diff Blob. More...

LayerParameter	convertLayerParam (LayerParameter pChild, LayerParameter pParent)
	Called to convert a parent LayerParameterEx, used in blob sharing, with a child layer parameter. More...

bool	shareParameter (Blob< T > b, List< int > rgMinShape, bool bAllowEndsWithComparison=false)
	Attempts to share a parameter Blob if another parameter Blob with the same name and accpetable size is found. More...

bool	shareLayerBlob (Blob< T > b, List< int > rgMinShape)
	Attempts to share a Layer Blob if another parameter Blob with the same name and acceptable size is found. More...

bool	shareLayerBlobs (Layer< T > layer)
	Attempts to share the Layer blobs and internal_blobs with matching names and sizes with those in another matching layer. More...

void	check_nan (Blob< T > b)
	Checks a Blob for NaNs and throws an exception if found. More...

T	convert (double df)
	Converts a double to a generic. More...

T	convert (float f)
	Converts a float to a generic. More...

double	convertD (T df)
	Converts a generic to a double value. More...

float	convertF (T df)
	Converts a generic to a float value. More...

double[]	convertD (T[] rg)
	Converts an array of generic values into an array of double values. More...

T[]	convert (double[] rg)
	Converts an array of double values into an array of generic values. More...

float[]	convertF (T[] rg)
	Converts an array of float values into an array of generic values. More...

T[]	convert (float[] rg)
	Converts an array of float values into an array of generic values. More...

int	val_at (T[] rg, int nIdx)
	Returns the integer value at a given index in a generic array. More...

Size	size_at (Blob< T > b)
	Returns the Size of a given two element Blob, such as one that stores Blob size information. More...

Protected Attributes
Blob< T >	m_blobKernelShape
	The spatial dimensions of the filter kernel. More...

Blob< T >	m_blobStride
	The spatial dimensions of the stride. More...

Blob< T >	m_blobPad
	The spatial dimensions of the padding. More...

Blob< T >	m_blobDilation
	The spatial dimentions of the dilation. More...

Blob< T >	m_blobConvInputShape
	The spatial dimensions of the convolution input. More...

List< int >	m_rgColBufferShape
	The spatial dimensionss of the col_buffer. More...

List< int >	m_rgOutputShape = new List<int>()
	The spatial dimensions of the output. More...

List< int >	m_rgBottomShape = new List<int>()
	The buttom shape. More...

int	m_nNumSpatialAxes
	The number of spatial axes. More...

int	m_nBottomDim
	The bottom dimension. More...

int	m_nTopDim
	The top dimension. More...

int	m_nChannelAxis
	The channel axis. More...

int	m_nNum
	The number of items in the batch. More...

int	m_nChannels
	The number of channels in each item. More...

int	m_nGroup
	The group. More...

int	m_nOutSpatialDim
	The output spatial dimension. More...

int	m_nWeightOffset
	The weight offset used. More...

int	m_nNumOutput
	The number of outputs. More...

bool	m_bBiasTerm
	Whether or not to use bias. More...

bool	m_bIs1x1
	Whether or not the kernel is 1x1. More...

bool	m_bForceNDim2col
	Whether or not to force n-dim 2 column. More...

Protected Attributes inherited from MyCaffe.layers.Layer< T >
LayerParameter.LayerType	m_type = LayerParameter.LayerType._MAX
	Specifies the Layer type. More...

CudaDnn< T >	m_cuda
	Specifies the CudaDnn connection to Cuda. More...

Log	m_log
	Specifies the Log for output. More...

LayerParameter	m_param
	Specifies the LayerParameter describing the Layer. More...

Phase	m_phase
	Specifies the Phase under which the Layer is run. More...

BlobCollection< T >	m_colBlobs
	Specifies the learnable parameter Blobs of the Layer. More...

BlobCollection< T >	m_colInternalBlobs = new BlobCollection<T>()
	Specifies internal blobs used by the layer. More...

DictionaryMap< bool >	m_rgbParamPropagateDown
	Specifies whether or not to compute the learnable diff of each parameter Blob. More...

DictionaryMap< double >	m_rgLoss
	Specifies the loss values that indeicate whether each top (output) Blob has a non-zero weight in the objective function.. More...

T	m_tOne
	Specifies a generic type equal to 1.0. More...

T	m_tZero
	Specifies a generic type equal to 0.0. More...

bool	m_bEnablePassthrough = false
	Enables/disables the pass-through mode for the layer. Default = false. More...

bool	m_bUseHalfSize = false
	Specifies that the half size of the top (if any) should be converted to the base size. More...

bool	m_bConvertTopOnFwd = false
	Specifies whether or not the layer should convert the top on the forward pass when using half sized memory (typically only done with input data). More...

bool	m_bConvertTopOnBwd = true
	Specifies whether or not to convert the top on the backward pass when using half sized memory (typically not done on loss layers). More...

bool	m_bConvertBottom = true
	Specifies whether or not the layer should convert the bottom when using half sized memory. More...

bool	m_bReshapeOnForwardNeeded = true
	Specifies whether or not the reshape on forward is needed or not. More...

bool	m_bNetReshapeRequest = false
	Specifies whether the reshape is requested from a Net.Reshape call or not. More...

LayerParameter.? LayerType	m_parentLayerType = null
	Specifies the layer type of the parent. More...

Properties
override int	MinBottomBlobs `[get]`
	Returns the minimum number of required bottom Blobs: input More...

override int	MinTopBlobs `[get]`
	Returns the minimum number of required top (output) Blobs: output More...

override bool	EqualNumBottomTopBlobs `[get]`
	Returns that there are an equal number of top and bottom Blobs. More...

Properties inherited from MyCaffe.layers.Layer< T >
LayerParameter.? LayerType	parent_layer_type `[get]`
	Optionally, specifies the parent layer type (e.g. LOSS, etc.) More...

virtual bool	SupportsPreProcessing `[get]`
	Should return true when PreProcessing methods are overriden. More...

virtual bool	SupportsPostProcessing `[get]`
	Should return true when pre PostProcessing methods are overriden. More...

virtual bool	SupportsPostProcessingLogits `[get]`
	Should return true when pre PostProcessingLogits methods are overriden. More...

virtual bool	SupportsPostProcessingFullOutput `[get]`
	Should return true when PostProcessingFullOutput is supported. More...

BlobCollection< T >	blobs `[get]`
	Returns the collection of learnable parameter Blobs for the Layer. More...

BlobCollection< T >	internal_blobs `[get]`
	Returns the collection of internal Blobs used by the Layer. More...

LayerParameter	layer_param `[get]`
	Returns the LayerParameter for this Layer. More...

LayerParameter.LayerType	type `[get]`
	Returns the LayerType of this Layer. More...

virtual int	ExactNumBottomBlobs `[get]`
	Returns the exact number of bottom (input) Blobs required by the Layer, or -1 if no exact number is required. More...

virtual int	MinBottomBlobs `[get]`
	Returns the minimum number of bottom (input) Blobs required by the Layer, or -1 if no minimum number is required. More...

virtual int	MaxBottomBlobs `[get]`
	Returns the maximum number of bottom (input) Blobs required by the Layer, or -1 if no maximum number is required. More...

virtual int	ExactNumTopBlobs `[get]`
	Returns the exact number of top (output) Blobs required by the Layer, or -1 if no exact number is required. More...

virtual int	MinTopBlobs `[get]`
	Returns the minimum number of top (output) Blobs required by the Layer, or -1 if no minimum number is required. More...

virtual int	MaxTopBlobs `[get]`
	Returns the maximum number of top (output) Blobs required by the Layer, or -1 if no maximum number is required. More...

virtual bool	EqualNumBottomTopBlobs `[get]`
	Returns true if the Layer requires and equal number of bottom (input) and top (output) Blobs. More...

virtual bool	AutoTopBlobs `[get]`
	Return whether "anonymous" top (output) Blobs are created automatically by the Layer. More...

double	forward_timing `[get]`
	Returns the timing of the last forward pass in milliseconds. More...

double	forward_timing_average `[get]`
	Returns the average timing of the forward passes in milliseconds. More...

double	backward_timing `[get]`
	Returns the timing of the last backward pass in milliseconds. More...

double	backward_timing_average `[get]`
	Returns the average timing of the backward passes in milliseconds. More...

Additional Inherited Members
Static Public Member Functions inherited from MyCaffe.layers.Layer< T >
static Layer< T >	Create (CudaDnn< T > cuda, Log log, LayerParameter p, CancelEvent evtCancel, IXDatabaseBase db=null, TransferInput trxinput=null)
	Create a new Layer based on the LayerParameter. More...

Events inherited from MyCaffe.layers.Layer< T >
EventHandler< WorkspaceArgs >	OnGetWorkspace
	Specifies the OnGetWorkspace event that fires when the getWorkspace() function is called by a layer to get a shareable workspace to conserve GPU memory. More...

EventHandler< WorkspaceArgs >	OnSetWorkspace
	Specifies the OnSetWorkspace event that fires when the setWorkspace() function is called by a layer to get a shareable workspace to conserve GPU memory. More...

EventHandler< GetIterationArgs >	OnGetIteration
	Specifies the OnGetIteration event that fires when a layer needs to get the current iteration from the solver. More...

EventHandler< GetWorkBlobArgs< T > >	OnDebug
	Specifies the OnGetWorkBlob event that is only supported when debugging to get a work blob from the primary Net holding this layer. More...

Detailed Description

The BaseConvolutionLayer is an abstract base class that factors out BLAS code common to ConvolutionLayer and DeconvolutionLayer

Template Parameters

T	Specifies the base type float or double. Using float is recommended to conserve GPU memory.

Definition at line 17 of file BaseConvolutionLayer.cs.

Constructor & Destructor Documentation

◆ BaseConvolutionLayer()

MyCaffe.layers.BaseConvolutionLayer< T >.BaseConvolutionLayer	(	CudaDnn< T >	cuda,
		Log	log,
		LayerParameter	p
	)

The BaseConvolutionLayer constructor.

Parameters

cuda	Specifies the CudaDnn connection to Cuda.
log	Specifies the Log for output.
p	Specifies the LayerParameter.

Definition at line 127 of file BaseConvolutionLayer.cs.

Member Function Documentation

◆ backward_bias()

void MyCaffe.layers.BaseConvolutionLayer< T >.backward_bias	(	long	hBias,
		long	hInput,
		int	nInputOffset
	)

protected

Helper function that abstracts away the column buffer and gemm arguments.

This function is only used when performing the Caffe version of convolution.

Parameters

hBias	Specifies a handle to the bias data in GPU memory.
hInput	Specifies a handle to the input data in GPU memory.
nInputOffset	Specifies an offset (in items) into the input data.

Definition at line 840 of file BaseConvolutionLayer.cs.

◆ backward_gemm()

void MyCaffe.layers.BaseConvolutionLayer< T >.backward_gemm	(	long	hOutput,
		int	nOutputOffset,
		long	hWeights,
		long	hInput,
		int	nInputOffset
	)

protected

Helper function that abstract away the column buffer and gemm arguments.

This function is only used when performing the Caffe version of convolution.

Parameters

hOutput	Specifies a handle to the output data in GPU memory.
nOutputOffset	Specifies an offset (in items) into the output data.
hWeights	Specifies a handle to the weight data in GPU memory.
hInput	Specifies a handle to the input data in GPU memory.
nInputOffset	Specifies an offset (in items) into the input data.

Definition at line 778 of file BaseConvolutionLayer.cs.

◆ compute_output_shape()

abstract void MyCaffe.layers.BaseConvolutionLayer< T >.compute_output_shape ( )

protectedpure virtual

Compute height_out and width_out from other parameters.

Implemented in MyCaffe.layers.ConvolutionLayer< T >, and MyCaffe.layers.DeconvolutionLayer< T >.

◆ dispose()

override void MyCaffe.layers.BaseConvolutionLayer< T >.dispose ( )

protectedvirtual

Releases all GPU and host resources used by the Layer.

Reimplemented from MyCaffe.layers.Layer< T >.

Reimplemented in MyCaffe.layers.ConvolutionLayer< T >, and MyCaffe.layers.DeconvolutionLayer< T >.

Definition at line 153 of file BaseConvolutionLayer.cs.

◆ forward_bias()

void MyCaffe.layers.BaseConvolutionLayer< T >.forward_bias	(	long	hOutput,
		int	nOutputOffset,
		long	hBias
	)

protected

Helper function that abstracts away the column buffer and gemm arguments.

This function is only used when performing the Caffe version of convolution.

Parameters

hOutput	Specifies a handle to the output data in GPU memory.
nOutputOffset	Specifies an offset (in items) into the output data.
hBias	Specifies a handle to the bias data in GPU memory.

Definition at line 762 of file BaseConvolutionLayer.cs.

◆ forward_gemm()

void MyCaffe.layers.BaseConvolutionLayer< T >.forward_gemm	(	long	hInput,
		int	nInputOffset,
		long	hWeights,
		long	hOutput,
		int	nOutputOffset,
		bool	bSkipIm2Col = `false`
	)

protected

Helper function that abstract away the column buffer and gemm arguments.

This function is only used when performing the Caffe version of convolution.

Parameters

hInput	Specifies a handle to the input data in GPU memory.
nInputOffset	Specifies an offset (in items) into the input data.
hWeights	Specifies a handle to the weight data in GPU memory.
hOutput	Specifies a handle to the output data in GPU memory.
nOutputOffset	Specifies an offset (in items) into the output data.
bSkipIm2Col	Specifies whether or not to skip the im2coll function call for it was already computed.

Definition at line 735 of file BaseConvolutionLayer.cs.

◆ getWorkspace()

override WorkspaceArgs MyCaffe.layers.BaseConvolutionLayer< T >.getWorkspace ( )

protectedvirtual

Retruns the WorkspaceArgs containing the workspace used by this Layer.

Returns

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 230 of file BaseConvolutionLayer.cs.

◆ getWorkspaceLimitInBytes()

ulong MyCaffe.layers.BaseConvolutionLayer< T >.getWorkspaceLimitInBytes ( bool bUseTensorCores = false )

protected

Returns the workspace limit in bytes based on the cudnn_workspace_limit setting.

Parameters

bUseTensorCores Specifies whether or not tensor cores are to be used and when they are we let cuDNN determine the workspace size.

The following cudnn_workspace_limits are used as follows: 0 = no workspace used. -1 = let CUDA choose fastest algorithm and workspace size. value = use the value specified * 16.

Returns: The workspace limit in bytes is returned.

Definition at line 187 of file BaseConvolutionLayer.cs.

◆ input_shape()

int MyCaffe.layers.BaseConvolutionLayer< T >.input_shape ( int i )

protected

Returns the spatial dimensions of the input.

Parameters

i	Specifies the index to add to the channel index.

Returns: The spatial dimension at the index is returned.

Definition at line 850 of file BaseConvolutionLayer.cs.

◆ LayerSetUp()

override void MyCaffe.layers.BaseConvolutionLayer< T >.LayerSetUp	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop
	)

virtual

Setup the layer.

Parameters

colBottom	Specifies the collection of bottom (input) Blobs.
colTop	Specifies the collection of top (output) Blobs.

Implements MyCaffe.layers.Layer< T >.

Reimplemented in MyCaffe.layers.ConvolutionLayer< T >, and MyCaffe.layers.DeconvolutionLayer< T >.

Definition at line 299 of file BaseConvolutionLayer.cs.

◆ ReInitializeParameters()

override bool MyCaffe.layers.BaseConvolutionLayer< T >.ReInitializeParameters ( WEIGHT_TARGET target )

virtual

Re-initialize the parameters of the layer.

Parameters

target Specifies the weights to target (e.g. weights, bias or both).

Returns: When handled, this method returns true, otherwise false.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 275 of file BaseConvolutionLayer.cs.

◆ Reshape()

override void MyCaffe.layers.BaseConvolutionLayer< T >.Reshape	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop
	)

virtual

Reshape the bottom (input) and top (output) blobs.

Parameters

colBottom	Specifies the collection of bottom (input) Blobs.
colTop	Specifies the collection of top (output) Blobs.

Implements MyCaffe.layers.Layer< T >.

Reimplemented in MyCaffe.layers.ConvolutionLayer< T >, and MyCaffe.layers.DeconvolutionLayer< T >.

Definition at line 597 of file BaseConvolutionLayer.cs.

◆ reverse_dimensions()

abstract bool MyCaffe.layers.BaseConvolutionLayer< T >.reverse_dimensions ( )

protectedpure virtual

reverse_dimensions should return true iff we are implementing deconv, so that conv helpers know which dimensions to use.

Returns: If the dimensions are to be reversed (e.g. when deconvolving), true is returned, otherwise false is returned.

Implemented in MyCaffe.layers.ConvolutionLayer< T >, and MyCaffe.layers.DeconvolutionLayer< T >.

◆ setup_internal_blobs()

override void MyCaffe.layers.BaseConvolutionLayer< T >.setup_internal_blobs ( BlobCollection< T > col )

protectedvirtual

Derivative layers should add all internal blobws to the 'col' provided.

Parameters

col	Specifies the blob collection where internal blobs are added.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 214 of file BaseConvolutionLayer.cs.

◆ setWorkspace()

override bool MyCaffe.layers.BaseConvolutionLayer< T >.setWorkspace ( ulong lSizeInBytes )

protectedvirtual

If not already set, allocates the workspace needed in GPU memory.

Parameters

lSizeInBytes Specifies the size (in bytes) of workspace needed.

Returns: This method always returns true.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 246 of file BaseConvolutionLayer.cs.

◆ weight_gemm()

void MyCaffe.layers.BaseConvolutionLayer< T >.weight_gemm	(	long	hInput,
		int	nInputOffset,
		long	hOutput,
		int	nOutputOffset,
		long	hWeights
	)

protected

Helper function that abstract away the column buffer and gemm arguments.

This function is only used when performing the Caffe version of convolution.

Parameters

hInput	Specifies a handle to the input data in GPU memory.
nInputOffset	Specifies an offset (in items) into the input data.
hOutput	Specifies a handle to the output data in GPU memory.
nOutputOffset	Specifies an offset (in items) into the output data.
hWeights	Specifies a handle to the weight data in GPU memory.

Definition at line 811 of file BaseConvolutionLayer.cs.

Member Data Documentation

◆ m_bBiasTerm

bool MyCaffe.layers.BaseConvolutionLayer< T >.m_bBiasTerm

protected

Whether or not to use bias.

Definition at line 94 of file BaseConvolutionLayer.cs.

◆ m_bForceNDim2col

bool MyCaffe.layers.BaseConvolutionLayer< T >.m_bForceNDim2col

protected

Whether or not to force n-dim 2 column.

Definition at line 102 of file BaseConvolutionLayer.cs.

◆ m_bIs1x1

bool MyCaffe.layers.BaseConvolutionLayer< T >.m_bIs1x1

protected

Whether or not the kernel is 1x1.

Definition at line 98 of file BaseConvolutionLayer.cs.

◆ m_blobConvInputShape

Blob<T> MyCaffe.layers.BaseConvolutionLayer< T >.m_blobConvInputShape

protected

The spatial dimensions of the convolution input.

Definition at line 38 of file BaseConvolutionLayer.cs.

◆ m_blobDilation

Blob<T> MyCaffe.layers.BaseConvolutionLayer< T >.m_blobDilation

protected

The spatial dimentions of the dilation.

Definition at line 34 of file BaseConvolutionLayer.cs.

◆ m_blobKernelShape

Blob<T> MyCaffe.layers.BaseConvolutionLayer< T >.m_blobKernelShape

protected

The spatial dimensions of the filter kernel.

Definition at line 22 of file BaseConvolutionLayer.cs.

◆ m_blobPad

Blob<T> MyCaffe.layers.BaseConvolutionLayer< T >.m_blobPad

protected

The spatial dimensions of the padding.

Definition at line 30 of file BaseConvolutionLayer.cs.

◆ m_blobStride

Blob<T> MyCaffe.layers.BaseConvolutionLayer< T >.m_blobStride

protected

The spatial dimensions of the stride.

Definition at line 26 of file BaseConvolutionLayer.cs.

◆ m_nBottomDim

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nBottomDim

protected

The bottom dimension.

Definition at line 58 of file BaseConvolutionLayer.cs.

◆ m_nChannelAxis

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nChannelAxis

protected

The channel axis.

Definition at line 66 of file BaseConvolutionLayer.cs.

◆ m_nChannels

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nChannels

protected

The number of channels in each item.

Definition at line 74 of file BaseConvolutionLayer.cs.

◆ m_nGroup

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nGroup

protected

The group.

Definition at line 78 of file BaseConvolutionLayer.cs.

◆ m_nNum

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nNum

protected

The number of items in the batch.

Definition at line 70 of file BaseConvolutionLayer.cs.

◆ m_nNumOutput

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nNumOutput

protected

The number of outputs.

Definition at line 90 of file BaseConvolutionLayer.cs.

◆ m_nNumSpatialAxes

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nNumSpatialAxes

protected

The number of spatial axes.

Definition at line 54 of file BaseConvolutionLayer.cs.

◆ m_nOutSpatialDim

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nOutSpatialDim

protected

The output spatial dimension.

Definition at line 82 of file BaseConvolutionLayer.cs.

◆ m_nTopDim

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nTopDim

protected

The top dimension.

Definition at line 62 of file BaseConvolutionLayer.cs.

◆ m_nWeightOffset

int MyCaffe.layers.BaseConvolutionLayer< T >.m_nWeightOffset

protected

The weight offset used.

Definition at line 86 of file BaseConvolutionLayer.cs.

◆ m_rgBottomShape

List<int> MyCaffe.layers.BaseConvolutionLayer< T >.m_rgBottomShape = new List<int>()

protected

The buttom shape.

Definition at line 50 of file BaseConvolutionLayer.cs.

◆ m_rgColBufferShape

List<int> MyCaffe.layers.BaseConvolutionLayer< T >.m_rgColBufferShape

protected

The spatial dimensionss of the col_buffer.

Definition at line 42 of file BaseConvolutionLayer.cs.

◆ m_rgOutputShape

List<int> MyCaffe.layers.BaseConvolutionLayer< T >.m_rgOutputShape = new List<int>()

protected

The spatial dimensions of the output.

Definition at line 46 of file BaseConvolutionLayer.cs.

Property Documentation

◆ EqualNumBottomTopBlobs

override bool MyCaffe.layers.BaseConvolutionLayer< T >.EqualNumBottomTopBlobs

get

Returns that there are an equal number of top and bottom Blobs.

Definition at line 718 of file BaseConvolutionLayer.cs.

◆ MinBottomBlobs

override int MyCaffe.layers.BaseConvolutionLayer< T >.MinBottomBlobs

get

Returns the minimum number of required bottom Blobs: input

Definition at line 702 of file BaseConvolutionLayer.cs.

◆ MinTopBlobs

override int MyCaffe.layers.BaseConvolutionLayer< T >.MinTopBlobs

get

Returns the minimum number of required top (output) Blobs: output

Definition at line 710 of file BaseConvolutionLayer.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/layers/BaseConvolutionLayer.cs

Public Member Functions

Protected Member Functions

Protected Attributes

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ BaseConvolutionLayer()

Member Function Documentation

◆ backward_bias()

◆ backward_gemm()

◆ compute_output_shape()

◆ dispose()

◆ forward_bias()

◆ forward_gemm()

◆ getWorkspace()

◆ getWorkspaceLimitInBytes()

◆ input_shape()

◆ LayerSetUp()

◆ ReInitializeParameters()

◆ Reshape()

◆ reverse_dimensions()

◆ setup_internal_blobs()

◆ setWorkspace()

◆ weight_gemm()

Member Data Documentation

◆ m_bBiasTerm

◆ m_bForceNDim2col

◆ m_bIs1x1

◆ m_blobConvInputShape

◆ m_blobDilation

◆ m_blobKernelShape

◆ m_blobPad

◆ m_blobStride

◆ m_nBottomDim

◆ m_nChannelAxis

◆ m_nChannels

◆ m_nGroup

◆ m_nNum

◆ m_nNumOutput

◆ m_nNumSpatialAxes

◆ m_nOutSpatialDim

◆ m_nTopDim

◆ m_nWeightOffset

◆ m_rgBottomShape

◆ m_rgColBufferShape

◆ m_rgOutputShape

Property Documentation

◆ EqualNumBottomTopBlobs

◆ MinBottomBlobs

◆ MinTopBlobs