The ConvolutionLayer convolves the input image with a bank of learned filters, and (optionally) adds biases. This layer is initialized with the MyCaffe.param.ConvolutionParameter. More...

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

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

override void	LayerSetUp (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Setup the layer for use with both Engine.CAFFE and Engine.CUDNN modes. 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.BaseConvolutionLayer< T >
	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...

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...

override 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...

override bool	reverse_dimensions ()
	Returns false, for we want convolution, not deconvolution. More...

override void	compute_output_shape ()
	Computes the output shape used by the BaseConvolutionLayer. More...

override void	forward (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Run the Forward computation using either the Engine.CAFFE or Engine.CUDNN mode as specified in the LayerParameter. More...

override void	backward (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
	Run the Backward computation using either the Engine.CAFFE or Engine.CUDNN mode as specified in the LayerParameter. More...

void	forward_cuda (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Run the Forward computation using the Engine.CAFFE mode as specified in the LayerParameter. More...

void	backward_cuda (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
	Run the Backward computation using the Engine.CAFFE mode as specified in the LayerParameter. More...

void	forward_cudnn (BlobCollection< T > colBottom, BlobCollection< T > colTop)
	Run the Forward computation using the Engine CUDNN mode as specified in the LayerParameter. More...

void	backward_cudnn (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
	Run the Backward computation using the Engine CUDNN mode as specified in the LayerParameter. More...

Protected Member Functions inherited from MyCaffe.layers.BaseConvolutionLayer< T >
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...

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...

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...

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...

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...

Protected Attributes inherited from MyCaffe.layers.BaseConvolutionLayer< T >
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 inherited from MyCaffe.layers.BaseConvolutionLayer< T >
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...

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 ConvolutionLayer convolves the input image with a bank of learned filters, and (optionally) adds biases. This layer is initialized with the MyCaffe.param.ConvolutionParameter.

Caffe convolves by reduction to matrix multiplication. This achieves high-throughput and generality of input and filter dimensions but comes at the cost of memory for matrices. This makes use of efficiency in BLAS.

The input is 'im2col' transformed to a channel 'K x H x W' data matrix for multiplication with the 'N x K x H x W' filter matrix to yield a 'N x H x W' output matrix that is then 'col2im' restored. K is the input channel * kernel height * kernel width dimension of the unrolled inputs so that the im2col matrix has a column for each input region to be filtered. col2im restores the output spatial structure by unrulling up the output channel 'N' columns of the output matrix.

Note: cuDNN accelerates convolution through forward kernels for filtering and bias plus backward kernels for gradient w.r.t the filters, biases, and inputs. Caffe + cuDNN further speeds up the computation through forward parallelism across groups and backward parallelism across gradients.

The cuDNN engine does not have memory overhead for the matrix buffers. For many input and filter regimes the cuDNN engien is faster than the CAFFE engine, but for fully-convolutional models and large inputs the CAFFE engine can be faster as long as it fits in memory.

See also: Gradient-Based Learning Applied to Document Recognition by Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner, 1998.; A guide to convolution arithmetic for deep learning by Vincent Dumoulin, and Francesco Visin, 2016.; Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks by Nazrul Haque, N. Dinesh Reddy, and K. Madhava Krishna, 2017.; A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction by Yoonsik Kim, Insung Hwang, and Nam Ik Cho, 2017.; Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, and Trevor Darrell, 2014.; Multi-Scale Context Aggregation by Dilated Convolutions by Fisher Yu, and Vladlen Koltun, 2015.

Template Parameters

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

Definition at line 47 of file ConvolutionLayer.cs.

Constructor & Destructor Documentation

◆ ConvolutionLayer()

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

The ConvolutionLayer constructor.

Parameters

cuda	Specifies the CudaDnn connection to Cuda.
log	Specifies the Log for output.
p	Provides ConvolutionParameter convolution_param with ConvolutionLayer options: num_output. The number of filters. kernel_size / kernel_h / kernel_w. The filter dimensions, given by kernel_size for square filters or kernel_h and kernel-w for rectangular filters. stride / stride_h / stride_w. (optional, default 1). The filter stride, given by stride_size for equal dimensions of stride_h and stride_w for different strides. By default the convolution is dense with stride 1. pad / pad_h / pad_w. (optional, default 0). The zero-padding for convolutions, given by pad for equal dimensions or pad_h and pad_w for different padding. Input padding is computed implicitly instead of actual padding. dilation (optional, default 1). The filter dilation, given by dilation_size for equal dimensions for different dilation. By default the convolution has dilation 1. group (optional, default 1). The number of filter groups. Group convolution is a method for reducing parameterization by selectively connecting input and output channels. The input and output channel dimensions must be divisible by the number of groups. For group = 1, the convolutionjf ilters input and output channels are separeated s.t. each group takes 1/group of the input channels and makes 1/group of the output channels. Concretely 4 input channels, 8 output channels, and 2 groups separate input chanels 1-2 and output channels 1-4 into the first group and input channels 3-4 and output channels 5-8 into the xecond group. bias_term (optional, default, true). Whether to have a bias. engine: convolution has Engine.CAFFE (matrix multiplication) and Engine.CUDNN (library kernels + stream parallelism) engines.

Definition at line 118 of file ConvolutionLayer.cs.

Member Function Documentation

◆ backward()

override void MyCaffe.layers.ConvolutionLayer< T >.backward	(	BlobCollection< T >	colTop,
		List< bool >	rgbPropagateDown,
		BlobCollection< T >	colBottom
	)

protectedvirtual

Run the Backward computation using either the Engine.CAFFE or Engine.CUDNN mode as specified in the LayerParameter.

Parameters

colTop	top output Blob vector (length 1).
rgbPropagateDown	see Layer::Backward
colBottom	bottom input Blob vector (length 1).

Implements MyCaffe.layers.Layer< T >.

Definition at line 421 of file ConvolutionLayer.cs.

◆ backward_cuda()

void MyCaffe.layers.ConvolutionLayer< T >.backward_cuda	(	BlobCollection< T >	colTop,
		List< bool >	rgbPropagateDown,
		BlobCollection< T >	colBottom
	)

protected

Run the Backward computation using the Engine.CAFFE mode as specified in the LayerParameter.

Parameters

colTop	top output Blob vector (length 1).
rgbPropagateDown	see Layer::Backward
colBottom	bottom input Blob vector (length 1).

Definition at line 459 of file ConvolutionLayer.cs.

◆ backward_cudnn()

void MyCaffe.layers.ConvolutionLayer< T >.backward_cudnn	(	BlobCollection< T >	colTop,
		List< bool >	rgbPropagateDown,
		BlobCollection< T >	colBottom
	)

protected

Run the Backward computation using the Engine CUDNN mode as specified in the LayerParameter.

Parameters

colTop	top output Blob vector (length 1).
rgbPropagateDown	see Layer::Backward
colBottom	bottom input Blob vector (length 1).

Definition at line 569 of file ConvolutionLayer.cs.

◆ compute_output_shape()

override void MyCaffe.layers.ConvolutionLayer< T >.compute_output_shape ( )

protectedvirtual

Computes the output shape used by the BaseConvolutionLayer.

Implements MyCaffe.layers.BaseConvolutionLayer< T >.

Definition at line 374 of file ConvolutionLayer.cs.

◆ dispose()

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

protectedvirtual

Releases all GPU and host resources used by the Layer.

Reimplemented from MyCaffe.layers.BaseConvolutionLayer< T >.

Definition at line 125 of file ConvolutionLayer.cs.

◆ forward()

override void MyCaffe.layers.ConvolutionLayer< T >.forward	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop
	)

protectedvirtual

Run the Forward computation using either the Engine.CAFFE or Engine.CUDNN mode as specified in the LayerParameter.

Parameters

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

Implements MyCaffe.layers.Layer< T >.

Definition at line 407 of file ConvolutionLayer.cs.

◆ forward_cuda()

void MyCaffe.layers.ConvolutionLayer< T >.forward_cuda	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop
	)

protected

Run the Forward computation using the Engine.CAFFE mode as specified in the LayerParameter.

Parameters

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

Definition at line 434 of file ConvolutionLayer.cs.

◆ forward_cudnn()

void MyCaffe.layers.ConvolutionLayer< T >.forward_cudnn	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop
	)

protected

Run the Forward computation using the Engine CUDNN mode as specified in the LayerParameter.

Parameters

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

Definition at line 503 of file ConvolutionLayer.cs.

◆ LayerSetUp()

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

virtual

Setup the layer for use with both Engine.CAFFE and Engine.CUDNN modes.

Parameters

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

Reimplemented from MyCaffe.layers.BaseConvolutionLayer< T >.

Definition at line 170 of file ConvolutionLayer.cs.

◆ Reshape()

override void MyCaffe.layers.ConvolutionLayer< 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.

Reimplemented from MyCaffe.layers.BaseConvolutionLayer< T >.

Definition at line 274 of file ConvolutionLayer.cs.

◆ reshapeNeeded()

override bool MyCaffe.layers.ConvolutionLayer< T >.reshapeNeeded	(	BlobCollection< T >	colBottom,
		BlobCollection< T >	colTop,
		bool	bReset = `true`
	)

protectedvirtual

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.

Parameters

colBottom	Specifies the bottom blobs.
colTop	Specifies the top blobs.
bReset	Specifies to reset the test (set to false when using in second derivative classes, e.g. set to true in BaseConvolutionLayer, and false in ConvolutionLayer).

Returns: If a reshape is needed, returns true otherwise returns fasle.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 251 of file ConvolutionLayer.cs.

◆ reverse_dimensions()

override bool MyCaffe.layers.ConvolutionLayer< T >.reverse_dimensions ( )

protectedvirtual

Returns false, for we want convolution, not deconvolution.

Returns: false is returned.

Implements MyCaffe.layers.BaseConvolutionLayer< T >.

Definition at line 366 of file ConvolutionLayer.cs.

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

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

Public Member Functions

Protected Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ ConvolutionLayer()

Member Function Documentation

◆ backward()

◆ backward_cuda()

◆ backward_cudnn()

◆ compute_output_shape()

◆ dispose()

◆ forward()

◆ forward_cuda()

◆ forward_cudnn()

◆ LayerSetUp()

◆ Reshape()

◆ reshapeNeeded()

◆ reverse_dimensions()