MyCaffe  1.11.7.7
Deep learning software for Windows C# programmers.
MyCaffe.layers.BatchNormLayer< T > Class Template Reference

The BatchNormLayer normalizes the input to have 0-mean and/or unit (1) variance across the batch. This layer is initialized with the BatchNormParameter. More...

Inheritance diagram for MyCaffe.layers.BatchNormLayer< T >:
MyCaffe.layers.Layer< T >

Public Member Functions

 BatchNormLayer (CudaDnn< T > cuda, Log log, LayerParameter p)
 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 BlobCollection< T > PreProcessInput (PropertySet customInput, 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 void 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. 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 void forward (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Perform the forward compuation. More...
 
override void backward (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Perform the backward computation. More...
 
void forward_cuda (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Perform the forward compuation using the native Cuda version. More...
 
void backward_cuda (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Perform the backward computation using the native Cuda version. More...
 
void forward_cudnn (BlobCollection< T > colBottom, BlobCollection< T > colTop)
 Perform the forward compuation using cuDNN. More...
 
void backward_cudnn (BlobCollection< T > colTop, List< bool > rgbPropagateDown, BlobCollection< T > colBottom)
 Perform the backward computation using cuDNN. More...
 
- Protected Member Functions inherited from MyCaffe.layers.Layer< T >
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 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 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...
 
bool shareParameter (Blob< T > b, List< int > rgMinShape)
 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 lSize)
 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...
 

Properties

override BlobCollection< T > internal_blobs [get]
 Returns the collection of internal Blobs used by the Layer. More...
 
override int ExactNumBottomBlobs [get]
 Returns the exact number of bottom (input) Blobs required: input More...
 
override int ExactNumTopBlobs [get]
 Returns the exact number of top (output) Blobs required: batchnorm More...
 
- Properties inherited from MyCaffe.layers.Layer< T >
virtual bool SupportsPreProcessing [get]
 Should return true when pre processing methods are overriden. More...
 
virtual bool SupportsPostProcessing [get]
 Should return true when pre postprocessing methods are overriden. More...
 
BlobCollection< T > blobs [get]
 Returns the collection of learnable parameter Blobs for the Layer. More...
 
virtual 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, IXImageDatabaseBase imgDb=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...
 
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...
 
- 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 BatchNormLayer normalizes the input to have 0-mean and/or unit (1) variance across the batch. This layer is initialized with the BatchNormParameter.

This layer computes Batch Normalization as described in [1]. For each channel in the data (i.e. axis 1), it subtracts the mean and divides by the variance, where both statistics are computed across both spatial dimensions and across the different examples in the batch.

By default, during training time, the network its computing global mean/variance statistics via a running average, which is then used at test time to allow deterministic outputs for each input. You can manually toggle whether the network is accumulating or using the statistics via the use_global_stats option. For reference, these statistics are kept int the layer's three blobs: (0) mean, (1) variance, and (2) moving average factor. IMPORTANT: for this feature to work, you MUST set the learning rate to zero for all three parameter blobs, i.e., param {lr_mult: 0} three times in the layer definition.

Note that the original papaer also included a per-channel learned bias and scaling factor. To implement this in Caffe, define a 'ScaleLayer' configured with 'bias_term: true' after each 'BatchNormLayer' to handle both the bias and scaling factor.

[1] S. Ioffe and C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167 (2015).

See also
In Defense of the Triplet Loss for Person Re-Identification by Alexander Hermans, Lucas Beyer, and Bastian Leibe, 2017.
Layer Normalization by Jimmy Lei Ba, and Jamie Ryan Kiros, and Geoffrey E. Hinton, 2016.
Template Parameters
TSpecifies the base type float or double. Using float is recommended to conserve GPU memory.

Definition at line 45 of file BatchNormLayer.cs.

Constructor & Destructor Documentation

◆ BatchNormLayer()

Constructor.

Parameters
cudaSpecifies the CudaDnn connection to Cuda.
logSpecifies the Log for output.
pprovides BatchNormParam batch_norm_param.

Definition at line 84 of file BatchNormLayer.cs.

Member Function Documentation

◆ backward()

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

Perform the backward computation.

Implements MyCaffe.layers.Layer< T >.

Definition at line 539 of file BatchNormLayer.cs.

◆ backward_cuda()

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

Perform the backward computation using the native Cuda version.

Definition at line 619 of file BatchNormLayer.cs.

◆ backward_cudnn()

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

Perform the backward computation using cuDNN.

Definition at line 740 of file BatchNormLayer.cs.

◆ dispose()

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

Releases all GPU and host resources used by the Layer.

Reimplemented from MyCaffe.layers.Layer< T >.

Definition at line 120 of file BatchNormLayer.cs.

◆ forward()

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

Perform the forward compuation.

Implements MyCaffe.layers.Layer< T >.

Definition at line 528 of file BatchNormLayer.cs.

◆ forward_cuda()

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

Perform the forward compuation using the native Cuda version.

Definition at line 550 of file BatchNormLayer.cs.

◆ forward_cudnn()

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

Perform the forward compuation using cuDNN.

Definition at line 687 of file BatchNormLayer.cs.

◆ LayerSetUp()

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

Setup the layer.

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

Implements MyCaffe.layers.Layer< T >.

Definition at line 276 of file BatchNormLayer.cs.

◆ ReInitializeParameters()

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

Re-initialize the parameters of the layer.

Parameters
targetSpecifies 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 256 of file BatchNormLayer.cs.

◆ Reshape()

override void MyCaffe.layers.BatchNormLayer< 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.

Implements MyCaffe.layers.Layer< T >.

Definition at line 431 of file BatchNormLayer.cs.

Property Documentation

◆ ExactNumBottomBlobs

override int MyCaffe.layers.BatchNormLayer< T >.ExactNumBottomBlobs
get

Returns the exact number of bottom (input) Blobs required: input

Definition at line 238 of file BatchNormLayer.cs.

◆ ExactNumTopBlobs

override int MyCaffe.layers.BatchNormLayer< T >.ExactNumTopBlobs
get

Returns the exact number of top (output) Blobs required: batchnorm

Definition at line 246 of file BatchNormLayer.cs.

◆ internal_blobs

override BlobCollection<T> MyCaffe.layers.BatchNormLayer< T >.internal_blobs
get

Returns the collection of internal Blobs used by the Layer.

Definition at line 202 of file BatchNormLayer.cs.


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