All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
BlockAffineComponent Class Reference

This class implements an affine transform using a block diagonal matrix e.g., one whose weight matrix is all zeros except for blocks on the diagonal. More...

#include <nnet-simple-component.h>

Inheritance diagram for BlockAffineComponent:
Collaboration diagram for BlockAffineComponent:

Public Member Functions

virtual int32 InputDim () const
 Returns input-dimension of this component. More...
 
virtual int32 OutputDim () const
 Returns output-dimension of this component. More...
 
virtual std::string Info () const
 Returns some text-form information about this component, for diagnostics. More...
 
virtual void InitFromConfig (ConfigLine *cfl)
 Initialize, from a ConfigLine object. More...
 
 BlockAffineComponent ()
 
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 > &, 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 Read (std::istream &is, bool binary)
 Read function (used after we know the type of the Component); accepts input that is missing the token that describes the component type, in case it has already been consumed. More...
 
virtual void Write (std::ostream &os, bool binary) const
 Write component to stream. More...
 
virtual ComponentCopy () const
 Copies component (deep copy). 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 PerturbParams (BaseFloat stddev)
 This function is to be used in testing. More...
 
virtual BaseFloat DotProduct (const UpdatableComponent &other) const
 Computes dot-product between parameters of two instances of a Component. More...
 
virtual int32 NumParameters () const
 The following new virtual function returns the total dimension of the parameters in this class. More...
 
virtual void Vectorize (VectorBase< BaseFloat > *params) const
 Turns the parameters into vector form. More...
 
virtual void UnVectorize (const VectorBase< BaseFloat > &params)
 Converts the parameters from vector form. More...
 
 BlockAffineComponent (const BlockAffineComponent &other)
 
 BlockAffineComponent (const RepeatedAffineComponent &rac)
 
- Public Member Functions inherited from UpdatableComponent
 UpdatableComponent (const UpdatableComponent &other)
 
 UpdatableComponent ()
 
virtual ~UpdatableComponent ()
 
virtual void SetUnderlyingLearningRate (BaseFloat lrate)
 Sets the learning rate of gradient descent- gets multiplied by learning_rate_factor_. More...
 
virtual void SetActualLearningRate (BaseFloat lrate)
 Sets the learning rate directly, bypassing learning_rate_factor_. More...
 
virtual void SetAsGradient ()
 Sets is_gradient_ to true and sets learning_rate_ to 1, ignoring learning_rate_factor_. More...
 
virtual BaseFloat LearningRateFactor ()
 
virtual void SetLearningRateFactor (BaseFloat lrate_factor)
 
void SetUpdatableConfigs (const UpdatableComponent &other)
 
virtual void FreezeNaturalGradient (bool freeze)
 freezes/unfreezes NaturalGradient updates, if applicable (to be overriden by components that use Natural Gradient). More...
 
BaseFloat LearningRate () const
 Gets the learning rate to be used in gradient descent. More...
 
BaseFloat MaxChange () const
 Returns the per-component max-change value, which is interpreted as the maximum change (in l2 norm) in parameters that is allowed per minibatch for this component. More...
 
void SetMaxChange (BaseFloat max_change)
 
BaseFloat L2Regularization () const
 Returns the l2 regularization constant, which may be set in any updatable component (usually from the config file). More...
 
void SetL2Regularization (BaseFloat a)
 
- Public Member Functions inherited from Component
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 void ZeroStats ()
 Components that provide an implementation of StoreStats should also provide an implementation of ZeroStats(), to set those stats to zero. More...
 
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
ComponentPrecomputedIndexes
PrecomputeIndexes (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 ()
 

Protected Attributes

CuMatrix< BaseFloatlinear_params_
 
CuVector< BaseFloatbias_params_
 
int32 num_blocks_
 
- Protected Attributes inherited from UpdatableComponent
BaseFloat learning_rate_
 learning rate (typically 0.0..0.01) More...
 
BaseFloat learning_rate_factor_
 learning rate factor (normally 1.0, but can be set to another < value so that when < you call SetLearningRate(), that value will be scaled by this factor. More...
 
BaseFloat l2_regularize_
 L2 regularization constant. More...
 
bool is_gradient_
 True if this component is to be treated as a gradient rather than as parameters. More...
 
BaseFloat max_change_
 configuration value for imposing max-change More...
 

Private Member Functions

void Init (int32 input_dim, int32 output_dim, int32 num_blocks, BaseFloat param_stddev, BaseFloat bias_mean, BaseFloat bias_stddev)
 
const BlockAffineComponentoperator= (const BlockAffineComponent &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 Member Functions inherited from UpdatableComponent
void InitLearningRatesFromConfig (ConfigLine *cfl)
 
std::string ReadUpdatableCommon (std::istream &is, bool binary)
 
void WriteUpdatableCommon (std::ostream &is, bool binary) const
 

Detailed Description

This class implements an affine transform using a block diagonal matrix e.g., one whose weight matrix is all zeros except for blocks on the diagonal.

All these blocks have the same dimensions. input-dim: num cols of block diagonal matrix. output-dim: num rows of block diagonal matrix. num-blocks: number of blocks in diagonal of the matrix. num-blocks must divide both input-dim and output-dim

Definition at line 483 of file nnet-simple-component.h.

Constructor & Destructor Documentation

Definition at line 491 of file nnet-simple-component.h.

Referenced by BlockAffineComponent::Copy().

491 { }
BlockAffineComponent ( const BlockAffineComponent other)
explicit

Definition at line 1560 of file nnet-simple-component.cc.

1560  :
1561  UpdatableComponent(other),
1562  linear_params_(other.linear_params_),
1563  bias_params_(other.bias_params_),
1564  num_blocks_(other.num_blocks_) {}
BlockAffineComponent ( const RepeatedAffineComponent rac)
explicit

Definition at line 1566 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, RepeatedAffineComponent::bias_params_, CuMatrixBase< Real >::CopyFromMat(), CuVectorBase< Real >::CopyFromVec(), BlockAffineComponent::linear_params_, RepeatedAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, CuMatrixBase< Real >::NumRows(), CuVectorBase< Real >::Range(), and CuMatrixBase< Real >::RowRange().

1566  :
1567  UpdatableComponent(rac),
1568  linear_params_(rac.num_repeats_ * rac.linear_params_.NumRows(),
1569  rac.linear_params_.NumCols(), kUndefined),
1570  bias_params_(rac.num_repeats_ * rac.linear_params_.NumRows(), kUndefined),
1571  num_blocks_(rac.num_repeats_) {
1572  // copy rac's linear_params_ and bias_params_ to this.
1573  int32 num_rows_in_block = rac.linear_params_.NumRows();
1574  for(int32 block_counter = 0; block_counter < num_blocks_; block_counter++) {
1575  int32 row_offset = block_counter * num_rows_in_block;
1576  CuSubMatrix<BaseFloat> block = this->linear_params_.RowRange(row_offset,
1577  num_rows_in_block);
1578  block.CopyFromMat(rac.linear_params_);
1579  CuSubVector<BaseFloat> block_bias = this->bias_params_.Range(row_offset,
1580  num_rows_in_block);
1581  block_bias.CopyFromVec(rac.bias_params_);
1582  }
1583 }
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:587
CuSubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Definition: cu-vector.h:145

Member Function Documentation

void Add ( BaseFloat  alpha,
const Component other 
)
virtual

This virtual function when called by – an UpdatableComponent adds the parameters of another updatable component, times some constant, to the current parameters.

– a NonlinearComponent (or another component that stores stats, like BatchNormComponent)– it relates to adding stats. Otherwise it will normally do nothing.

Reimplemented from Component.

Definition at line 1770 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::AddMat(), CuVectorBase< Real >::AddVec(), BlockAffineComponent::bias_params_, KALDI_ASSERT, and BlockAffineComponent::linear_params_.

1770  {
1771  const BlockAffineComponent *other =
1772  dynamic_cast<const BlockAffineComponent *>(&other_in);
1773  KALDI_ASSERT(other != NULL);
1774  linear_params_.AddMat(alpha, other->linear_params_);
1775  bias_params_.AddVec(alpha, other->bias_params_);
1776 }
void AddMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType trans=kNoTrans)
*this += alpha * A
Definition: cu-matrix.cc:941
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
void AddVec(Real alpha, const CuVectorBase< Real > &vec, Real beta=1.0)
Definition: cu-vector.cc:1182
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 1674 of file nnet-simple-component.cc.

References CuVectorBase< Real >::AddRowSumMat(), BlockAffineComponent::bias_params_, CuMatrixBase< Real >::ColRange(), kaldi::DeletePointers(), kaldi::kNoTrans, kaldi::kTrans, UpdatableComponent::learning_rate_, BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, CuMatrixBase< Real >::NumCols(), CuMatrixBase< Real >::NumRows(), and CuMatrixBase< Real >::RowRange().

1681  {
1682  BlockAffineComponent *to_update = dynamic_cast<BlockAffineComponent*>(to_update_in);
1683 
1684  const int32 num_rows_in_block = linear_params_.NumRows() / num_blocks_;
1685  const int32 num_cols_in_block = linear_params_.NumCols();
1686 
1687  // Propagate the derivative back to the input.
1688  // add with coefficient 1.0 since property kBackpropAdds is true.
1689  // If we wanted to add with coefficient 0.0 we'd need to zero the
1690  // in_deriv, in case of infinities.
1691  if (in_deriv) {
1692  std::vector<CuSubMatrix<BaseFloat> *> in_deriv_batch, out_deriv_batch, linear_params_batch;
1693 
1694  for(int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1695  CuSubMatrix<BaseFloat> *in_deriv_block =
1696  new CuSubMatrix<BaseFloat>(in_deriv->ColRange(block_counter * num_cols_in_block,
1697  num_cols_in_block));
1698  in_deriv_batch.push_back(in_deriv_block);
1699 
1700  CuSubMatrix<BaseFloat> *out_deriv_block =
1701  new CuSubMatrix<BaseFloat>(out_deriv.ColRange(block_counter * num_rows_in_block,
1702  num_rows_in_block));
1703  out_deriv_batch.push_back(out_deriv_block);
1704 
1705  CuSubMatrix<BaseFloat> *linear_params_block =
1706  new CuSubMatrix<BaseFloat>(linear_params_.RowRange(block_counter * num_rows_in_block,
1707  num_rows_in_block));
1708  linear_params_batch.push_back(linear_params_block);
1709  }
1710 
1711  AddMatMatBatched<BaseFloat>(1.0, in_deriv_batch, out_deriv_batch, kNoTrans,
1712  linear_params_batch, kNoTrans, 1.0);
1713 
1714  DeletePointers(&in_deriv_batch);
1715  DeletePointers(&out_deriv_batch);
1716  DeletePointers(&linear_params_batch);
1717  }
1718 
1719  if (to_update != NULL) {
1720 
1721  { // linear params update
1722 
1723  std::vector<CuSubMatrix<BaseFloat> *> in_value_batch,
1724  out_deriv_batch, linear_params_batch;
1725 
1726  for (int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1727  CuSubMatrix<BaseFloat> *in_value_block =
1728  new CuSubMatrix<BaseFloat>(in_value.ColRange(block_counter * num_cols_in_block,
1729  num_cols_in_block));
1730  in_value_batch.push_back(in_value_block);
1731 
1732  CuSubMatrix<BaseFloat> *out_deriv_block =
1733  new CuSubMatrix<BaseFloat>(out_deriv.ColRange(block_counter * num_rows_in_block,
1734  num_rows_in_block));
1735  out_deriv_batch.push_back(out_deriv_block);
1736 
1737  CuSubMatrix<BaseFloat> *linear_params_block =
1738  new CuSubMatrix<BaseFloat>(to_update->linear_params_.RowRange(block_counter * num_rows_in_block,
1739  num_rows_in_block));
1740  linear_params_batch.push_back(linear_params_block);
1741  }
1742 
1743  AddMatMatBatched<BaseFloat>(to_update->learning_rate_,
1744  linear_params_batch,
1745  out_deriv_batch, kTrans,
1746  in_value_batch, kNoTrans, 1.0);
1747 
1748  DeletePointers(&in_value_batch);
1749  DeletePointers(&out_deriv_batch);
1750  DeletePointers(&linear_params_batch);
1751  } // end linear params update
1752 
1753  { // bias update
1754  to_update->bias_params_.AddRowSumMat(to_update->learning_rate_,
1755  out_deriv, 1.0);
1756  } // end bias update
1757  }
1758 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:206
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:587
CuSubMatrix< Real > ColRange(const MatrixIndexT col_offset, const MatrixIndexT num_cols) const
Definition: cu-matrix.h:592
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
void DeletePointers(std::vector< A * > *v)
Deletes any non-NULL pointers in the vector v, and sets the corresponding entries of v to NULL...
Definition: stl-utils.h:186
Component * Copy ( ) const
virtual

Copies component (deep copy).

Implements Component.

Definition at line 1585 of file nnet-simple-component.cc.

References BlockAffineComponent::BlockAffineComponent().

1585  {
1586  BlockAffineComponent *ans = new BlockAffineComponent(*this);
1587  return ans;
1588 }
BaseFloat DotProduct ( const UpdatableComponent other) const
virtual

Computes dot-product between parameters of two instances of a Component.

Can be used for computing parameter-norm of an UpdatableComponent.

Implements UpdatableComponent.

Definition at line 1788 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, kaldi::kTrans, BlockAffineComponent::linear_params_, kaldi::TraceMatMat(), and kaldi::VecVec().

1788  {
1789  const BlockAffineComponent *other =
1790  dynamic_cast<const BlockAffineComponent*>(&other_in);
1791  return TraceMatMat(linear_params_, other->linear_params_, kTrans) +
1792  VecVec(bias_params_, other->bias_params_);
1793 }
Real TraceMatMat(const MatrixBase< Real > &A, const MatrixBase< Real > &B, MatrixTransposeType trans=kNoTrans)
We need to declare this here as it will be a friend function.
Real VecVec(const VectorBase< Real > &a, const VectorBase< Real > &b)
Returns dot product between v1 and v2.
Definition: kaldi-vector.cc:37
std::string Info ( ) const
virtual

Returns some text-form information about this component, for diagnostics.

Starts with the type of the component. E.g. "SigmoidComponent dim=900", although most components will have much more info.

Reimplemented from UpdatableComponent.

Definition at line 1590 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, UpdatableComponent::Info(), BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, and kaldi::nnet3::PrintParameterStats().

1590  {
1591  std::ostringstream stream;
1592  stream << UpdatableComponent::Info()
1593  << ", num-blocks=" << num_blocks_;
1594  PrintParameterStats(stream, "linear-params", linear_params_);
1595  PrintParameterStats(stream, "bias", bias_params_, true);
1596  return stream.str();
1597 }
virtual std::string Info() const
Returns some text-form information about this component, for diagnostics.
void PrintParameterStats(std::ostringstream &os, const std::string &name, const CuVectorBase< BaseFloat > &params, bool include_mean)
Print to 'os' some information about the mean and standard deviation of some parameters, used in Info() functions in nnet-simple-component.cc.
Definition: nnet-parse.cc:530
void Init ( int32  input_dim,
int32  output_dim,
int32  num_blocks,
BaseFloat  param_stddev,
BaseFloat  bias_mean,
BaseFloat  bias_stddev 
)
private

Definition at line 1599 of file nnet-simple-component.cc.

References CuVectorBase< Real >::Add(), BlockAffineComponent::bias_params_, KALDI_ASSERT, BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, CuVector< Real >::Resize(), CuMatrix< Real >::Resize(), CuVectorBase< Real >::Scale(), CuMatrixBase< Real >::Scale(), CuVectorBase< Real >::SetRandn(), and CuMatrixBase< Real >::SetRandn().

Referenced by BlockAffineComponent::InitFromConfig().

1602  {
1603  KALDI_ASSERT(input_dim > 0 && output_dim > 0 && num_blocks >= 1);
1604  KALDI_ASSERT(output_dim % num_blocks == 0 && input_dim % num_blocks == 0);
1605  const int32 num_columns_per_block = input_dim / num_blocks;
1606  linear_params_.Resize(output_dim, num_columns_per_block);
1607  bias_params_.Resize(output_dim);
1608  KALDI_ASSERT(param_stddev >= 0.0 && bias_stddev >= 0.0);
1610  linear_params_.Scale(param_stddev);
1612  bias_params_.Scale(bias_stddev);
1613  bias_params_.Add(bias_mean);
1614  num_blocks_ = num_blocks;
1615 }
void Scale(Real value)
Definition: cu-vector.cc:1161
void Scale(Real value)
Definition: cu-matrix.cc:610
void Resize(MatrixIndexT dim, MatrixResizeType t=kSetZero)
Allocate the memory.
Definition: cu-vector.cc:941
void Resize(MatrixIndexT rows, MatrixIndexT cols, MatrixResizeType resize_type=kSetZero, MatrixStrideType stride_type=kDefaultStride)
Allocate the memory.
Definition: cu-matrix.cc:49
void Add(Real value)
Definition: cu-vector.cc:1102
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
void InitFromConfig ( ConfigLine cfl)
virtual

Initialize, from a ConfigLine object.

Parameters
[in]cflA ConfigLine containing any parameters that are needed for initialization. For example: "dim=100 param-stddev=0.1"

Implements Component.

Definition at line 1617 of file nnet-simple-component.cc.

References ConfigLine::GetValue(), ConfigLine::HasUnusedValues(), BlockAffineComponent::Init(), UpdatableComponent::InitLearningRatesFromConfig(), KALDI_ERR, BlockAffineComponent::Type(), and ConfigLine::WholeLine().

1617  {
1618  int32 input_dim = -1, output_dim = -1, num_blocks = -1;
1619  if(!cfl->GetValue("input-dim", &input_dim) ||
1620  !cfl->GetValue("output-dim", &output_dim) ||
1621  !cfl->GetValue("num-blocks", &num_blocks))
1622  KALDI_ERR << "Invalid initializer for layer of type "
1623  << Type() << ": \"" << cfl->WholeLine() << "\"";
1625  BaseFloat param_stddev = 1.0 / std::sqrt(input_dim / num_blocks),
1626  bias_mean = 0.0, bias_stddev = 1.0;
1627  cfl->GetValue("param-stddev", &param_stddev);
1628  cfl->GetValue("bias-stddev", &bias_stddev);
1629  cfl->GetValue("bias-mean", &bias_mean);
1630 
1631  if (cfl->HasUnusedValues())
1632  KALDI_ERR << "Invalid initializer for layer of type "
1633  << Type() << ": \"" << cfl->WholeLine() << "\"";
1634 
1635  Init(input_dim, output_dim, num_blocks,
1636  param_stddev, bias_mean, bias_stddev);
1637 }
void InitLearningRatesFromConfig(ConfigLine *cfl)
float BaseFloat
Definition: kaldi-types.h:29
void Init(int32 input_dim, int32 output_dim, int32 num_blocks, BaseFloat param_stddev, BaseFloat bias_mean, BaseFloat bias_stddev)
#define KALDI_ERR
Definition: kaldi-error.h:127
virtual std::string Type() const
Returns a string such as "SigmoidComponent", describing the type of the object.
virtual int32 InputDim ( ) const
inlinevirtual

Returns input-dimension of this component.

Implements Component.

Definition at line 485 of file nnet-simple-component.h.

References BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, and CuMatrixBase< Real >::NumCols().

int32 NumParameters ( ) const
virtual

The following new virtual function returns the total dimension of the parameters in this class.

Reimplemented from UpdatableComponent.

Definition at line 1823 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, CuVectorBase< Real >::Dim(), BlockAffineComponent::linear_params_, CuMatrixBase< Real >::NumCols(), and CuMatrixBase< Real >::NumRows().

Referenced by BlockAffineComponent::UnVectorize(), and BlockAffineComponent::Vectorize().

1823  {
1825 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:206
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:68
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
const BlockAffineComponent& operator= ( const BlockAffineComponent other)
private
virtual int32 OutputDim ( ) const
inlinevirtual

Returns output-dimension of this component.

Implements Component.

Definition at line 486 of file nnet-simple-component.h.

References BlockAffineComponent::linear_params_, and CuMatrixBase< Real >::NumRows().

486 { return linear_params_.NumRows(); }
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
void PerturbParams ( BaseFloat  stddev)
virtual

This function is to be used in testing.

It adds unit noise times "stddev" to the parameters of the component.

Implements UpdatableComponent.

Definition at line 1778 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::AddMat(), CuVectorBase< Real >::AddVec(), BlockAffineComponent::bias_params_, BlockAffineComponent::linear_params_, CuVectorBase< Real >::SetRandn(), and CuMatrixBase< Real >::SetRandn().

1778  {
1779  CuMatrix<BaseFloat> temp_linear_params(linear_params_);
1780  temp_linear_params.SetRandn();
1781  linear_params_.AddMat(stddev, temp_linear_params);
1782 
1783  CuVector<BaseFloat> temp_bias_params(bias_params_);
1784  temp_bias_params.SetRandn();
1785  bias_params_.AddVec(stddev, temp_bias_params);
1786 }
void AddMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType trans=kNoTrans)
*this += alpha * A
Definition: cu-matrix.cc:941
void AddVec(Real alpha, const CuVectorBase< Real > &vec, Real beta=1.0)
Definition: cu-vector.cc:1182
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 1639 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, CuMatrixBase< Real >::ColRange(), CuMatrixBase< Real >::CopyRowsFromVec(), kaldi::DeletePointers(), kaldi::kNoTrans, kaldi::kTrans, BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, CuMatrixBase< Real >::NumCols(), CuMatrixBase< Real >::NumRows(), and CuMatrixBase< Real >::RowRange().

1641  {
1643  // block_dimension is both the number of columns, and the number of rows,
1644  // of a block.
1645  int32 num_rows_in_block = linear_params_.NumRows() / num_blocks_;
1646  int32 num_cols_in_block = linear_params_.NumCols();
1647  std::vector<CuSubMatrix<BaseFloat> *> in_batch, out_batch,
1648  linear_params_batch;
1649  for(int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1650  CuSubMatrix<BaseFloat> *in_block =
1651  new CuSubMatrix<BaseFloat>(in.ColRange(block_counter * num_cols_in_block,
1652  num_cols_in_block));
1653  in_batch.push_back(in_block);
1654 
1655  CuSubMatrix<BaseFloat> *out_block =
1656  new CuSubMatrix<BaseFloat>(out->ColRange(block_counter * num_rows_in_block,
1657  num_rows_in_block));
1658  out_batch.push_back(out_block);
1659 
1660  CuSubMatrix<BaseFloat> *linear_params_block =
1661  new CuSubMatrix<BaseFloat>(linear_params_.RowRange(block_counter * num_rows_in_block,
1662  num_rows_in_block));
1663  linear_params_batch.push_back(linear_params_block);
1664  }
1665  AddMatMatBatched<BaseFloat>(1.0, out_batch, in_batch, kNoTrans,
1666  linear_params_batch, kTrans, 1.0);
1667 
1668  DeletePointers(&in_batch);
1669  DeletePointers(&out_batch);
1670  DeletePointers(&linear_params_batch);
1671  return NULL;
1672 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2282
MatrixIndexT NumCols() const
Definition: cu-matrix.h:206
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:587
CuSubMatrix< Real > ColRange(const MatrixIndexT col_offset, const MatrixIndexT num_cols) const
Definition: cu-matrix.h:592
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
void DeletePointers(std::vector< A * > *v)
Deletes any non-NULL pointers in the vector v, and sets the corresponding entries of v to NULL...
Definition: stl-utils.h:186
virtual int32 Properties ( ) const
inlinevirtual
void Read ( std::istream &  is,
bool  binary 
)
virtual

Read function (used after we know the type of the Component); accepts input that is missing the token that describes the component type, in case it has already been consumed.

Implements Component.

Definition at line 1795 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, kaldi::nnet3::ExpectToken(), UpdatableComponent::is_gradient_, BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, kaldi::PeekToken(), CuVector< Real >::Read(), CuMatrix< Real >::Read(), kaldi::ReadBasicType(), and UpdatableComponent::ReadUpdatableCommon().

1795  {
1796  ReadUpdatableCommon(is, binary); // read opening tag and learning rate.
1797  ExpectToken(is, binary, "<NumBlocks>");
1798  ReadBasicType(is, binary, &num_blocks_);
1799  ExpectToken(is, binary, "<LinearParams>");
1800  linear_params_.Read(is, binary);
1801  ExpectToken(is, binary, "<BiasParams>");
1802  bias_params_.Read(is, binary);
1803  if (PeekToken(is, binary) == 'I') {
1804  // for back compatibility; we don't write this here any
1805  // more as it's written and read in Write/ReadUpdatableCommon
1806  ExpectToken(is, binary, "<IsGradient>");
1807  ReadBasicType(is, binary, &is_gradient_);
1808  }
1809  ExpectToken(is, binary, "</BlockAffineComponent>");
1810 }
void ReadBasicType(std::istream &is, bool binary, T *t)
ReadBasicType is the name of the read function for bool, integer types, and floating-point types...
Definition: io-funcs-inl.h:55
void Read(std::istream &is, bool binary)
I/O.
Definition: cu-vector.cc:911
static void ExpectToken(const std::string &token, const std::string &what_we_are_parsing, const std::string **next_token)
std::string ReadUpdatableCommon(std::istream &is, bool binary)
int PeekToken(std::istream &is, bool binary)
PeekToken will return the first character of the next token, or -1 if end of file.
Definition: io-funcs.cc:170
void Read(std::istream &is, bool binary)
I/O functions.
Definition: cu-matrix.cc:461
bool is_gradient_
True if this component is to be treated as a gradient rather than as parameters.
void Scale ( BaseFloat  scale)
virtual

This virtual function when called on – an UpdatableComponent scales the parameters by "scale" when called by an UpdatableComponent.

– a Nonlinear component (or another component that stores stats, like BatchNormComponent)– it relates to scaling activation stats, not parameters. Otherwise it will normally do nothing.

Reimplemented from Component.

Definition at line 1760 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, BlockAffineComponent::linear_params_, CuVectorBase< Real >::Scale(), CuMatrixBase< Real >::Scale(), CuVectorBase< Real >::SetZero(), and CuMatrixBase< Real >::SetZero().

1760  {
1761  if (scale == 0.0) {
1764  } else {
1765  linear_params_.Scale(scale);
1766  bias_params_.Scale(scale);
1767  }
1768 }
void Scale(Real value)
Definition: cu-vector.cc:1161
void Scale(Real value)
Definition: cu-matrix.cc:610
void SetZero()
Math operations, some calling kernels.
Definition: cu-matrix.cc:476
void SetZero()
Math operations.
Definition: cu-vector.cc:1044
virtual std::string Type ( ) const
inlinevirtual

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

Implements Component.

Definition at line 492 of file nnet-simple-component.h.

Referenced by BlockAffineComponent::InitFromConfig().

492 { return "BlockAffineComponent"; }
void UnVectorize ( const VectorBase< BaseFloat > &  params)
virtual

Converts the parameters from vector form.

Reimplemented from UpdatableComponent.

Definition at line 1835 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, CuVectorBase< Real >::CopyFromVec(), CuMatrixBase< Real >::CopyRowsFromVec(), VectorBase< Real >::Dim(), CuVectorBase< Real >::Dim(), KALDI_ASSERT, BlockAffineComponent::linear_params_, CuMatrixBase< Real >::NumCols(), BlockAffineComponent::NumParameters(), CuMatrixBase< Real >::NumRows(), and VectorBase< Real >::Range().

1835  {
1836  KALDI_ASSERT(params.Dim() == this->NumParameters());
1837  int32 num_linear_params = linear_params_.NumCols() * linear_params_.NumRows();
1838  int32 num_bias_params = bias_params_.Dim();
1839  linear_params_.CopyRowsFromVec(params.Range(0, num_linear_params));
1840  bias_params_.CopyFromVec(params.Range(num_linear_params, num_bias_params));
1841 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2282
MatrixIndexT NumCols() const
Definition: cu-matrix.h:206
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:68
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
void CopyFromVec(const CuVectorBase< Real > &src)
Copy functions; these will crash if the dimension do not match.
Definition: cu-vector.cc:1026
virtual int32 NumParameters() const
The following new virtual function returns the total dimension of the parameters in this class...
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
MatrixIndexT Dim() const
Returns the dimension of the vector.
Definition: kaldi-vector.h:63
SubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Returns a sub-vector of a vector (a range of elements).
Definition: kaldi-vector.h:93
void Vectorize ( VectorBase< BaseFloat > *  params) const
virtual

Turns the parameters into vector form.

We put the vector form on the CPU, because in the kinds of situations where we do this, we'll tend to use too much memory for the GPU.

Reimplemented from UpdatableComponent.

Definition at line 1827 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, VectorBase< Real >::Dim(), CuVectorBase< Real >::Dim(), KALDI_ASSERT, BlockAffineComponent::linear_params_, CuMatrixBase< Real >::NumCols(), BlockAffineComponent::NumParameters(), CuMatrixBase< Real >::NumRows(), and VectorBase< Real >::Range().

1827  {
1828  KALDI_ASSERT(params->Dim() == this->NumParameters());
1829  int32 num_linear_params = linear_params_.NumCols() * linear_params_.NumRows();
1830  int32 num_bias_params = bias_params_.Dim();
1831  params->Range(0, num_linear_params).CopyRowsFromMat(linear_params_);
1832  params->Range(num_linear_params, num_bias_params).CopyFromVec(bias_params_);
1833 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:206
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:68
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:205
virtual int32 NumParameters() const
The following new virtual function returns the total dimension of the parameters in this class...
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
MatrixIndexT Dim() const
Returns the dimension of the vector.
Definition: kaldi-vector.h:63
SubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Returns a sub-vector of a vector (a range of elements).
Definition: kaldi-vector.h:93
void Write ( std::ostream &  os,
bool  binary 
) const
virtual

Write component to stream.

Implements Component.

Definition at line 1812 of file nnet-simple-component.cc.

References BlockAffineComponent::bias_params_, BlockAffineComponent::linear_params_, BlockAffineComponent::num_blocks_, CuVector< Real >::Write(), CuMatrixBase< Real >::Write(), kaldi::WriteBasicType(), kaldi::WriteToken(), and UpdatableComponent::WriteUpdatableCommon().

1812  {
1813  WriteUpdatableCommon(os, binary); // Write opening tag and learning rate
1814  WriteToken(os, binary, "<NumBlocks>");
1815  WriteBasicType(os, binary, num_blocks_);
1816  WriteToken(os, binary, "<LinearParams>");
1817  linear_params_.Write(os, binary);
1818  WriteToken(os, binary, "<BiasParams>");
1819  bias_params_.Write(os, binary);
1820  WriteToken(os, binary, "</BlockAffineComponent>");
1821 }
void Write(std::ostream &is, bool binary) const
Definition: cu-vector.cc:921
void WriteUpdatableCommon(std::ostream &is, bool binary) const
void WriteToken(std::ostream &os, bool binary, const char *token)
The WriteToken functions are for writing nonempty sequences of non-space characters.
Definition: io-funcs.cc:134
void WriteBasicType(std::ostream &os, bool binary, T t)
WriteBasicType is the name of the write function for bool, integer types, and floating-point types...
Definition: io-funcs-inl.h:34
void Write(std::ostream &os, bool binary) const
Definition: cu-matrix.cc:469

Member Data Documentation


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