SoftmaxComponent Class Reference

#include <nnet-simple-component.h>

Inheritance diagram for SoftmaxComponent:
Collaboration diagram for SoftmaxComponent:

Public Member Functions

 SoftmaxComponent (const SoftmaxComponent &other)
 
 SoftmaxComponent ()
 
virtual std::string Type () const
 Returns a string such as "SigmoidComponent", describing the type of the object. More...
 
virtual int32 Properties () const
 Return bitmask of the component's properties. More...
 
virtual void * Propagate (const ComponentPrecomputedIndexes *indexes, const CuMatrixBase< BaseFloat > &in, CuMatrixBase< BaseFloat > *out) const
 Propagate function. More...
 
virtual void Backprop (const std::string &debug_info, const ComponentPrecomputedIndexes *indexes, const CuMatrixBase< BaseFloat > &in_value, const CuMatrixBase< BaseFloat > &out_value, const CuMatrixBase< BaseFloat > &out_deriv, void *memo, Component *to_update, CuMatrixBase< BaseFloat > *in_deriv) const
 Backprop function; depending on which of the arguments 'to_update' and 'in_deriv' are non-NULL, this can compute input-data derivatives and/or perform model update. More...
 
virtual void StoreStats (const CuMatrixBase< BaseFloat > &in_value, const CuMatrixBase< BaseFloat > &out_value, void *memo)
 This function may store stats on average activation values, and for some component types, the average value of the derivative of the nonlinearity. More...
 
virtual ComponentCopy () const
 Copies component (deep copy). More...
 
- Public Member Functions inherited from NonlinearComponent
 NonlinearComponent ()
 
 NonlinearComponent (const NonlinearComponent &other)
 
virtual int32 InputDim () const
 Returns input-dimension of this component. More...
 
virtual int32 OutputDim () const
 Returns output-dimension of this component. More...
 
virtual void InitFromConfig (ConfigLine *cfl)
 Initialize, from a ConfigLine object. More...
 
virtual void Read (std::istream &is, bool binary)
 We implement Read at this level as it just needs the Type(). More...
 
virtual void ZeroStats ()
 Components that provide an implementation of StoreStats should also provide an implementation of ZeroStats(), to set those stats to zero. More...
 
virtual std::string Info () const
 Returns some text-form information about this component, for diagnostics. More...
 
virtual void Write (std::ostream &os, bool binary) const
 Write component to stream. More...
 
virtual void Scale (BaseFloat scale)
 This virtual function when called on – an UpdatableComponent scales the parameters by "scale" when called by an UpdatableComponent. More...
 
virtual void Add (BaseFloat alpha, const Component &other)
 This virtual function when called by – an UpdatableComponent adds the parameters of another updatable component, times some constant, to the current parameters. More...
 
virtual void ConsolidateMemory ()
 This virtual function relates to memory management, and avoiding fragmentation. More...
 
const CuVector< double > & ValueSum () const
 
const CuVector< double > & DerivSum () const
 
double Count () const
 
- Public Member Functions inherited from Component
virtual void GetInputIndexes (const MiscComputationInfo &misc_info, const Index &output_index, std::vector< Index > *desired_indexes) const
 This function only does something interesting for non-simple Components. More...
 
virtual bool IsComputable (const MiscComputationInfo &misc_info, const Index &output_index, const IndexSet &input_index_set, std::vector< Index > *used_inputs) const
 This function only does something interesting for non-simple Components, and it exists to make it possible to manage optionally-required inputs. More...
 
virtual void ReorderIndexes (std::vector< Index > *input_indexes, std::vector< Index > *output_indexes) const
 This function only does something interesting for non-simple Components. More...
 
virtual ComponentPrecomputedIndexesPrecomputeIndexes (const MiscComputationInfo &misc_info, const std::vector< Index > &input_indexes, const std::vector< Index > &output_indexes, bool need_backprop) const
 This function must return NULL for simple Components. More...
 
virtual void DeleteMemo (void *memo) const
 This virtual function only needs to be overwritten by Components that return a non-NULL memo from their Propagate() function. More...
 
 Component ()
 
virtual ~Component ()
 

Private Member Functions

SoftmaxComponentoperator= (const SoftmaxComponent &other)
 

Additional Inherited Members

- Static Public Member Functions inherited from Component
static ComponentReadNew (std::istream &is, bool binary)
 Read component from stream (works out its type). Dies on error. More...
 
static ComponentNewComponentOfType (const std::string &type)
 Returns a new Component of the given type e.g. More...
 
- Protected Types inherited from NonlinearComponent
enum  { kUnsetThreshold = -1000 }
 
- Protected Member Functions inherited from NonlinearComponent
void StoreStatsInternal (const CuMatrixBase< BaseFloat > &out_value, const CuMatrixBase< BaseFloat > *deriv=NULL)
 
void StoreBackpropStats (const CuMatrixBase< BaseFloat > &out_deriv)
 
const NonlinearComponentoperator= (const NonlinearComponent &other)
 
- Protected Attributes inherited from NonlinearComponent
int32 dim_
 
int32 block_dim_
 
CuVector< double > value_sum_
 
CuVector< double > deriv_sum_
 
double count_
 
CuVector< double > oderiv_sumsq_
 
double oderiv_count_
 
double num_dims_self_repaired_
 
double num_dims_processed_
 
BaseFloat self_repair_lower_threshold_
 
BaseFloat self_repair_upper_threshold_
 
BaseFloat self_repair_scale_
 

Detailed Description

Definition at line 677 of file nnet-simple-component.h.

Constructor & Destructor Documentation

◆ SoftmaxComponent() [1/2]

SoftmaxComponent ( const SoftmaxComponent other)
inlineexplicit

Definition at line 679 of file nnet-simple-component.h.

◆ SoftmaxComponent() [2/2]

SoftmaxComponent ( )
inline

Definition at line 681 of file nnet-simple-component.h.

681 { }

Member Function Documentation

◆ Backprop()

void Backprop ( const std::string &  debug_info,
const ComponentPrecomputedIndexes indexes,
const CuMatrixBase< BaseFloat > &  in_value,
const CuMatrixBase< BaseFloat > &  out_value,
const CuMatrixBase< BaseFloat > &  out_deriv,
void *  memo,
Component to_update,
CuMatrixBase< BaseFloat > *  in_deriv 
) const
virtual

Backprop function; depending on which of the arguments 'to_update' and 'in_deriv' are non-NULL, this can compute input-data derivatives and/or perform model update.

Parameters
[in]debug_infoThe component name, to be printed out in any warning messages.
[in]indexesA pointer to some information output by this class's PrecomputeIndexes function (will be NULL for simple components, i.e. those that don't do things like splicing).
[in]in_valueThe matrix that was given as input to the Propagate function. Will be ignored (and may be empty) if Properties()&kBackpropNeedsInput == 0.
[in]out_valueThe matrix that was output from the Propagate function. Will be ignored (and may be empty) if Properties()&kBackpropNeedsOutput == 0
[in]out_derivThe derivative at the output of this component.
[in]memoThis will normally be NULL, but for component types that set the flag kUsesMemo, this will be the return value of the Propagate() function that corresponds to this Backprop() function. Ownership of any pointers is not transferred to the Backprop function; DeleteMemo() will be called to delete it.
[out]to_updateIf model update is desired, the Component to be updated, else NULL. Does not have to be identical to this. If supplied, you can assume that to_update->Properties() & kUpdatableComponent is nonzero.
[out]in_derivThe derivative at the input of this component, if needed (else NULL). If Properties()&kBackpropInPlace, may be the same matrix as out_deriv. If Properties()&kBackpropAdds, this is added to by the Backprop routine, else it is set. The component code chooses which mode to work in, based on convenience.

Implements Component.

Definition at line 3578 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::DiffSoftmaxPerRow(), NVTX_RANGE, and NonlinearComponent::StoreBackpropStats().

3585  {
3586  NVTX_RANGE("SoftmaxComponent::Backprop");
3587 
3588  if (to_update_in) {
3589  SoftmaxComponent *to_update =
3590  dynamic_cast<SoftmaxComponent*>(to_update_in);
3591  to_update->StoreBackpropStats(out_deriv);
3592  }
3593 
3594  if (in_deriv == NULL)
3595  return;
3596  /*
3597  Note on the derivative of the softmax function: let it be
3598  p_i = exp(x_i) / sum_i exp_i
3599  The [matrix-valued] Jacobian of this function is
3600  diag(p) - p p^T
3601  Let the derivative vector at the output be e, and at the input be
3602  d. We have
3603  d = diag(p) e - p (p^T e).
3604  d_i = p_i e_i - p_i (p^T e).
3605  */
3606  in_deriv->DiffSoftmaxPerRow(out_value, out_deriv);
3607 }
#define NVTX_RANGE(name)
Definition: cu-common.h:143

◆ Copy()

virtual Component* Copy ( ) const
inlinevirtual

Copies component (deep copy).

Implements Component.

Definition at line 701 of file nnet-simple-component.h.

◆ operator=()

SoftmaxComponent& operator= ( const SoftmaxComponent other)
private

◆ Propagate()

void * Propagate ( const ComponentPrecomputedIndexes indexes,
const CuMatrixBase< BaseFloat > &  in,
CuMatrixBase< BaseFloat > *  out 
) const
virtual

Propagate function.

Parameters
[in]indexesA pointer to some information output by this class's PrecomputeIndexes function (will be NULL for simple components, i.e. those that don't do things like splicing).
[in]inThe input to this component. Num-columns == InputDim().
[out]outThe output of this component. Num-columns == OutputDim(). Note: output of this component will be added to the initial value of "out" if Properties()&kPropagateAdds != 0; otherwise the output will be set and the initial value ignored. Each Component chooses whether it is more convenient implementation-wise to add or set, and the calling code has to deal with it.
Returns
Normally returns NULL, but may return a non-NULL value for components which have the flag kUsesMemo set. This value will be passed into the corresponding Backprop routine.

Implements Component.

Definition at line 3563 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::ApplyFloor(), and CuMatrixBase< Real >::SoftMaxPerRow().

3565  {
3566  // Apply softmax function to each row of the output...
3567  // for that row, we do
3568  // x_i = exp(x_i) / sum_j exp(x_j).
3569  out->SoftMaxPerRow(in);
3570 
3571  // This floor on the output helps us deal with
3572  // almost-zeros in a way that doesn't lead to overflow.
3573  out->ApplyFloor(1.0e-20);
3574 
3575  return NULL;
3576 }

◆ Properties()

◆ StoreStats()

void StoreStats ( const CuMatrixBase< BaseFloat > &  in_value,
const CuMatrixBase< BaseFloat > &  out_value,
void *  memo 
)
virtual

This function may store stats on average activation values, and for some component types, the average value of the derivative of the nonlinearity.

It only does something for those components that have nonzero Properties()&kStoresStats.

Parameters
[in]in_valueThe input to the Propagate() function. Note: if the component sets the flag kPropagateInPlace, this should not be used; the empty matrix will be provided here if in-place propagation was used.
[in]out_valueThe output of the Propagate() function.
[in]memoThe 'memo' returned by the Propagate() function; this will usually be NULL.

Reimplemented from Component.

Definition at line 3609 of file nnet-simple-component.cc.

3611  {
3612  // We don't store derivative stats for this component type, just activation
3613  // stats.
3614  StoreStatsInternal(out_value, NULL);
3615 }
void StoreStatsInternal(const CuMatrixBase< BaseFloat > &out_value, const CuMatrixBase< BaseFloat > *deriv=NULL)

◆ Type()

virtual std::string Type ( ) const
inlinevirtual

Returns a string such as "SigmoidComponent", describing the type of the object.

Implements Component.

Definition at line 682 of file nnet-simple-component.h.

682 { return "SoftmaxComponent"; }

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