MyCaffe  1.12.2.41
Deep learning software for Windows C# programmers.
MyCaffe.layers.TanhLayer< T > Class Template Reference

The TanhLayer is a neuron layer that calculates the tanh function, popular with auto-encoders. This layer is initialized with the MyCaffe.param.TanhParameter. More...

Inheritance diagram for MyCaffe.layers.TanhLayer< T >:
MyCaffe.layers.NeuronLayer< T > MyCaffe.layers.Layer< T >

Public Member Functions

 TanhLayer (CudaDnn< T > cuda, Log log, LayerParameter p)
 The TanhLayer constructor. More...
 
override void LayerSetUp (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Setup the layer to run in either Engine.CAFFE or Engine.CUDNN mode. 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.NeuronLayer< T >
 NeuronLayer (CudaDnn< T > cuda, Log log, LayerParameter p)
 The NeuronLayer constructor. 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...
 
virtual bool ReInitializeParameters (WEIGHT_TARGET target)
 Re-initialize the parameters of the layer. 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 void forward (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Computes the forward calculation using either the Engine.CAFFE or Engine.CUDNN mode. More...
 
override void backward (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Computes the error gradient w.r.t the inputs using either the Engine.CAFFE or Engine.CUDNN mode. More...
 
void forward_cuda (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Computes the forward calculation using the Engine.CAFFE mode. More...
 
void backward_cuda (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Computes the error gradient w.r.t the ganh inputs using the Engine.CAFFE mode. More...
 
void forward_cudnn (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Computes the forward calculation using the Engine.CUDNN mode. More...
 
void backward_cudnn (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Computes the error gradient w.r.t the ganh inputs using the Engine.CUDNN mode. 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...
 
virtual void setup_internal_blobs (BlobCollection< T > col)
 Derivative layers should add all internal blobws to the 'col' provided. 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...
 
virtual WorkspaceArgs getWorkspace ()
 Returns the WorkspaceArgs used to share a workspace between Layers. More...
 
virtual bool setWorkspace (ulong lSizeInBytes)
 Sets the workspace size (in items) and returns true if set, false otherwise. More...
 
void check_nan (Blob< T > b)
 Checks a Blob for NaNs and throws an exception if found. More...
 
convert (double df)
 Converts a double to a generic. More...
 
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.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...
 
m_tOne
 Specifies a generic type equal to 1.0. More...
 
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.NeuronLayer< T >
override int ExactNumBottomBlobs [get]
 Returns the exact number of required bottom (input) Blobs: input. More...
 
override int ExactNumTopBlobs [get]
 Returns the exact number of required top (output) Blobs: output. 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< WorkspaceArgsOnGetWorkspace
 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< WorkspaceArgsOnSetWorkspace
 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< GetIterationArgsOnGetIteration
 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 TanhLayer is a neuron layer that calculates the tanh function, popular with auto-encoders. This layer is initialized with the MyCaffe.param.TanhParameter.

Computation: $ y = \frac{\exp(2x) - 1}{\exp(2x) + 1} $
Note that the gradient vanishes as the values move away from 0. The ReLULayer is often a better choice for this reason.

See also
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks by Francesco Visin, Kyle Kastner, Kyunghyun Cho, Matteo Matteucci, Aaron Courville, and Yoshua Bengio, 2015.
Spatial, Structural and Temporal Feature Learning for Human Interaction Prediction by Qiuhong Ke, Mohammed Bennamoun, Senjian An, Farid Bossaid, and Ferdous Sohel, , 2016.
Applying Deep Learning to Answer Selection: A Study and An Open Task by Minwei Feng, Bing Xiang, Michael R. Glass, Lidan Wang, and Bowen Zhou, 2015.
Template Parameters
TSpecifies the base type float or double. Using float is recommended to conserve GPU memory.

Definition at line 27 of file TanhLayer.cs.

Constructor & Destructor Documentation

◆ TanhLayer()

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

The TanhLayer constructor.

Parameters
cudaSpecifies the CudaDnn connection to Cuda.
logSpecifies the Log for output.
pSpecifies the LayerParameter of type TANH with parameter tanh_param, with options:
  • engine. The engine to use, either Engine.CAFFE, or Engine.CUDNN.

Definition at line 43 of file TanhLayer.cs.

Member Function Documentation

◆ backward()

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

Computes the error gradient w.r.t the inputs using either the Engine.CAFFE or Engine.CUDNN mode.

Parameters
colToptop output Blob vector (Length 1), providing the error gradient with respect to computed outputs.
  1. $ (N \times C \times H \times W) $ containing error gradients $ \frac{\partial E}{\partial y} $ with respect to computed outputs $ y $.
rgbPropagateDownpropagate down see Layer::Backward
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs $ x $; Backward fills their diff with gradients $ \frac{\partial E}{\partial y} = \frac{\partial E}{\partial y} \left(1 - \left[\frac{\exp(2x) - 1}{\exp(2x) + 1} \right]^2 \right) = \frac{\partial E}{\partial y} (1 - y^2) $ if propagate_down[0] == true

Implements MyCaffe.layers.Layer< T >.

Definition at line 153 of file TanhLayer.cs.

◆ backward_cuda()

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

Computes the error gradient w.r.t the ganh inputs using the Engine.CAFFE mode.

Parameters
colToptop output Blob vector (Length 1), providing the error gradient with respect to computed outputs.
  1. $ (N \times C \times H \times W) $ containing error gradients $ \frac{\partial E}{\partial y} $ with respect to computed outputs $ y $.
rgbPropagateDownpropagate down see Layer::Backward
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs $ x $; Backward fills their diff with gradients $ \frac{\partial E}{\partial y} = \frac{\partial E}{\partial y} \left(1 - \left[\frac{\exp(2x) - 1}{\exp(2x) + 1} \right]^2 \right) = \frac{\partial E}{\partial y} (1 - y^2) $ if propagate_down[0] == true

Definition at line 200 of file TanhLayer.cs.

◆ backward_cudnn()

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

Computes the error gradient w.r.t the ganh inputs using the Engine.CUDNN mode.

Parameters
colToptop output Blob vector (Length 1), providing the error gradient with respect to computed outputs.
  1. $ (N \times C \times H \times W) $ containing error gradients $ \frac{\partial E}{\partial y} $ with respect to computed outputs $ y $.
rgbPropagateDownpropagate down see Layer::Backward
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs $ x $; Backward fills their diff with gradients $ \frac{\partial E}{\partial y} = \frac{\partial E}{\partial y} \left(1 - \left[\frac{\exp(2x) - 1}{\exp(2x) + 1} \right]^2 \right) = \frac{\partial E}{\partial y} (1 - y^2) $ if propagate_down[0] == true

Definition at line 248 of file TanhLayer.cs.

◆ dispose()

override void MyCaffe.layers.TanhLayer< T >.dispose ( )
protectedvirtual

Releases all GPU and host resources used by the Layer.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 50 of file TanhLayer.cs.

◆ forward()

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

Computes the forward calculation using either the Engine.CAFFE or Engine.CUDNN mode.

Parameters
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs.
colToptop otuput Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the computed outputs $ y = \frac{\exp(2x) - 1}{\exp(2x) + 1} $

Implements MyCaffe.layers.Layer< T >.

Definition at line 126 of file TanhLayer.cs.

◆ forward_cuda()

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

Computes the forward calculation using the Engine.CAFFE mode.

Parameters
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs.
colToptop otuput Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the computed outputs $ y = \frac{\exp(2x) - 1}{\exp(2x) + 1} $

Definition at line 172 of file TanhLayer.cs.

◆ forward_cudnn()

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

Computes the forward calculation using the Engine.CUDNN mode.

Parameters
colBottombottom input Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the inputs.
colToptop otuput Blob vector (Length 1)
  1. $ (N \times C \times H \times W) $ the computed outputs $ y = \frac{\exp(2x) - 1}{\exp(2x) + 1} $

Definition at line 221 of file TanhLayer.cs.

◆ LayerSetUp()

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

Setup the layer to run in either Engine.CAFFE or Engine.CUDNN mode.

Parameters
colBottomSpecifies the collection of bottom (input) Blobs.
colTopSpecifies the collection of top (output) Blobs.

Reimplemented from MyCaffe.layers.NeuronLayer< T >.

Definition at line 78 of file TanhLayer.cs.

◆ Reshape()

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

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

Parameters
colBottomSpecifies the collection of bottom (input) Blobs.
colTopSpecifies the collection of top (output) Blobs.

Reimplemented from MyCaffe.layers.NeuronLayer< T >.

Definition at line 97 of file TanhLayer.cs.


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