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 by. 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...
 
void Init (int32 input_dim, int32 output_dim, int32 num_blocks, BaseFloat param_stddev, BaseFloat bias_mean, BaseFloat bias_stddev)
 
 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 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 of gradient descent. More...
 
BaseFloat MaxChange () const
 Gets per-component max-change value. More...
 
- 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...
 
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

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 534 of file nnet-simple-component.h.

Constructor & Destructor Documentation

Definition at line 542 of file nnet-simple-component.h.

Referenced by BlockAffineComponent::Copy().

542 { }
BlockAffineComponent ( const BlockAffineComponent other)
explicit

Definition at line 1643 of file nnet-simple-component.cc.

1643  :
1644  UpdatableComponent(other),
1645  linear_params_(other.linear_params_),
1646  bias_params_(other.bias_params_),
1647  num_blocks_(other.num_blocks_) {}
BlockAffineComponent ( const RepeatedAffineComponent rac)
explicit

Definition at line 1649 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().

1649  :
1650  UpdatableComponent(rac),
1651  linear_params_(rac.num_repeats_ * rac.linear_params_.NumRows(),
1652  rac.linear_params_.NumCols(), kUndefined),
1653  bias_params_(rac.num_repeats_ * rac.linear_params_.NumRows(), kUndefined),
1654  num_blocks_(rac.num_repeats_) {
1655  // copy rac's linear_params_ and bias_params_ to this.
1656  int32 num_rows_in_block = rac.linear_params_.NumRows();
1657  for(int32 block_counter = 0; block_counter < num_blocks_; block_counter++) {
1658  int32 row_offset = block_counter * num_rows_in_block;
1659  CuSubMatrix<BaseFloat> block = this->linear_params_.RowRange(row_offset,
1660  num_rows_in_block);
1661  block.CopyFromMat(rac.linear_params_);
1662  CuSubVector<BaseFloat> block_bias = this->bias_params_.Range(row_offset,
1663  num_rows_in_block);
1664  block_bias.CopyFromVec(rac.bias_params_);
1665  }
1666 }
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:539
CuSubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Definition: cu-vector.h:132

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 it relates to adding stats Otherwise it should do nothing.

Reimplemented from Component.

Definition at line 1853 of file nnet-simple-component.cc.

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

1853  {
1854  const BlockAffineComponent *other =
1855  dynamic_cast<const BlockAffineComponent *>(&other_in);
1856  KALDI_ASSERT(other != NULL);
1857  linear_params_.AddMat(alpha, other->linear_params_);
1858  bias_params_.AddVec(alpha, other->bias_params_);
1859 }
void AddMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType trans=kNoTrans)
*this += alpha * A
Definition: cu-matrix.cc:939
#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:1126
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 1757 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().

1764  {
1765  BlockAffineComponent *to_update = dynamic_cast<BlockAffineComponent*>(to_update_in);
1766 
1767  const int32 num_rows_in_block = linear_params_.NumRows() / num_blocks_;
1768  const int32 num_cols_in_block = linear_params_.NumCols();
1769 
1770  // Propagate the derivative back to the input.
1771  // add with coefficient 1.0 since property kBackpropAdds is true.
1772  // If we wanted to add with coefficient 0.0 we'd need to zero the
1773  // in_deriv, in case of infinities.
1774  if (in_deriv) {
1775  std::vector<CuSubMatrix<BaseFloat> *> in_deriv_batch, out_deriv_batch, linear_params_batch;
1776 
1777  for(int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1778  CuSubMatrix<BaseFloat> *in_deriv_block =
1779  new CuSubMatrix<BaseFloat>(in_deriv->ColRange(block_counter * num_cols_in_block,
1780  num_cols_in_block));
1781  in_deriv_batch.push_back(in_deriv_block);
1782 
1783  CuSubMatrix<BaseFloat> *out_deriv_block =
1784  new CuSubMatrix<BaseFloat>(out_deriv.ColRange(block_counter * num_rows_in_block,
1785  num_rows_in_block));
1786  out_deriv_batch.push_back(out_deriv_block);
1787 
1788  CuSubMatrix<BaseFloat> *linear_params_block =
1789  new CuSubMatrix<BaseFloat>(linear_params_.RowRange(block_counter * num_rows_in_block,
1790  num_rows_in_block));
1791  linear_params_batch.push_back(linear_params_block);
1792  }
1793 
1794  AddMatMatBatched<BaseFloat>(1.0, in_deriv_batch, out_deriv_batch, kNoTrans,
1795  linear_params_batch, kNoTrans, 1.0);
1796 
1797  DeletePointers(&in_deriv_batch);
1798  DeletePointers(&out_deriv_batch);
1799  DeletePointers(&linear_params_batch);
1800  }
1801 
1802  if (to_update != NULL) {
1803 
1804  { // linear params update
1805 
1806  std::vector<CuSubMatrix<BaseFloat> *> in_value_batch,
1807  out_deriv_batch, linear_params_batch;
1808 
1809  for (int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1810  CuSubMatrix<BaseFloat> *in_value_block =
1811  new CuSubMatrix<BaseFloat>(in_value.ColRange(block_counter * num_cols_in_block,
1812  num_cols_in_block));
1813  in_value_batch.push_back(in_value_block);
1814 
1815  CuSubMatrix<BaseFloat> *out_deriv_block =
1816  new CuSubMatrix<BaseFloat>(out_deriv.ColRange(block_counter * num_rows_in_block,
1817  num_rows_in_block));
1818  out_deriv_batch.push_back(out_deriv_block);
1819 
1820  CuSubMatrix<BaseFloat> *linear_params_block =
1821  new CuSubMatrix<BaseFloat>(to_update->linear_params_.RowRange(block_counter * num_rows_in_block,
1822  num_rows_in_block));
1823  linear_params_batch.push_back(linear_params_block);
1824  }
1825 
1826  AddMatMatBatched<BaseFloat>(to_update->learning_rate_,
1827  linear_params_batch,
1828  out_deriv_batch, kTrans,
1829  in_value_batch, kNoTrans, 1.0);
1830 
1831  DeletePointers(&in_value_batch);
1832  DeletePointers(&out_deriv_batch);
1833  DeletePointers(&linear_params_batch);
1834  } // end linear params update
1835 
1836  { // bias update
1837  to_update->bias_params_.AddRowSumMat(to_update->learning_rate_,
1838  out_deriv, 1.0);
1839  } // end bias update
1840  }
1841 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:196
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:539
CuSubMatrix< Real > ColRange(const MatrixIndexT col_offset, const MatrixIndexT num_cols) const
Definition: cu-matrix.h:544
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
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 1668 of file nnet-simple-component.cc.

References BlockAffineComponent::BlockAffineComponent().

1668  {
1669  BlockAffineComponent *ans = new BlockAffineComponent(*this);
1670  return ans;
1671 }
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 1871 of file nnet-simple-component.cc.

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

1871  {
1872  const BlockAffineComponent *other =
1873  dynamic_cast<const BlockAffineComponent*>(&other_in);
1874  return TraceMatMat(linear_params_, other->linear_params_, kTrans) +
1875  VecVec(bias_params_, other->bias_params_);
1876 }
Real TraceMatMat(const MatrixBase< Real > &A, const MatrixBase< Real > &B, MatrixTransposeType trans)
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:36
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 1673 of file nnet-simple-component.cc.

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

1673  {
1674  std::ostringstream stream;
1675  stream << UpdatableComponent::Info()
1676  << ", num-blocks=" << num_blocks_;
1677  PrintParameterStats(stream, "linear-params", linear_params_);
1678  PrintParameterStats(stream, "bias", bias_params_, true);
1679  return stream.str();
1680 }
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:520
void Init ( int32  input_dim,
int32  output_dim,
int32  num_blocks,
BaseFloat  param_stddev,
BaseFloat  bias_mean,
BaseFloat  bias_stddev 
)

Definition at line 1682 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().

1685  {
1686  KALDI_ASSERT(input_dim > 0 && output_dim > 0 && num_blocks >= 1);
1687  KALDI_ASSERT(output_dim % num_blocks == 0 && input_dim % num_blocks == 0);
1688  const int32 num_columns_per_block = input_dim / num_blocks;
1689  linear_params_.Resize(output_dim, num_columns_per_block);
1690  bias_params_.Resize(output_dim);
1691  KALDI_ASSERT(param_stddev >= 0.0 && bias_stddev >= 0.0);
1693  linear_params_.Scale(param_stddev);
1695  bias_params_.Scale(bias_stddev);
1696  bias_params_.Add(bias_mean);
1697  num_blocks_ = num_blocks;
1698 }
void Scale(Real value)
Definition: cu-vector.cc:1105
void Scale(Real value)
Definition: cu-matrix.cc:608
void Resize(MatrixIndexT dim, MatrixResizeType t=kSetZero)
Allocate the memory.
Definition: cu-vector.cc:892
void Resize(MatrixIndexT rows, MatrixIndexT cols, MatrixResizeType resize_type=kSetZero, MatrixStrideType stride_type=kDefaultStride)
Allocate the memory.
Definition: cu-matrix.cc:47
void Add(Real value)
Definition: cu-vector.cc:1046
#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 1700 of file nnet-simple-component.cc.

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

1700  {
1701  int32 input_dim = -1, output_dim = -1, num_blocks = -1;
1702  if(!cfl->GetValue("input-dim", &input_dim) ||
1703  !cfl->GetValue("output-dim", &output_dim) ||
1704  !cfl->GetValue("num-blocks", &num_blocks))
1705  KALDI_ERR << "Invalid initializer for layer of type "
1706  << Type() << ": \"" << cfl->WholeLine() << "\"";
1708  BaseFloat param_stddev = 1.0 / std::sqrt(input_dim / num_blocks),
1709  bias_mean = 0.0, bias_stddev = 1.0;
1710  cfl->GetValue("param-stddev", &param_stddev);
1711  cfl->GetValue("bias-stddev", &bias_stddev);
1712  cfl->GetValue("bias-mean", &bias_mean);
1713 
1714  if (cfl->HasUnusedValues())
1715  KALDI_ERR << "Invalid initializer for layer of type "
1716  << Type() << ": \"" << cfl->WholeLine() << "\"";
1717 
1718  Init(input_dim, output_dim, num_blocks,
1719  param_stddev, bias_mean, bias_stddev);
1720 }
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 536 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 1904 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().

1904  {
1906 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:196
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:67
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
const BlockAffineComponent& operator= ( const BlockAffineComponent other)
private
virtual int32 OutputDim ( ) const
inlinevirtual

Returns output-dimension of this component.

Implements Component.

Definition at line 537 of file nnet-simple-component.h.

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

537 { return linear_params_.NumRows(); }
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
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 1861 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().

1861  {
1862  CuMatrix<BaseFloat> temp_linear_params(linear_params_);
1863  temp_linear_params.SetRandn();
1864  linear_params_.AddMat(stddev, temp_linear_params);
1865 
1866  CuVector<BaseFloat> temp_bias_params(bias_params_);
1867  temp_bias_params.SetRandn();
1868  bias_params_.AddVec(stddev, temp_bias_params);
1869 }
void AddMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType trans=kNoTrans)
*this += alpha * A
Definition: cu-matrix.cc:939
void AddVec(Real alpha, const CuVectorBase< Real > &vec, Real beta=1.0)
Definition: cu-vector.cc:1126
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 1722 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().

1724  {
1726  // block_dimension is both the number of columns, and the number of rows,
1727  // of a block.
1728  int32 num_rows_in_block = linear_params_.NumRows() / num_blocks_;
1729  int32 num_cols_in_block = linear_params_.NumCols();
1730  std::vector<CuSubMatrix<BaseFloat> *> in_batch, out_batch,
1731  linear_params_batch;
1732  for(int block_counter = 0; block_counter < num_blocks_; block_counter++) {
1733  CuSubMatrix<BaseFloat> *in_block =
1734  new CuSubMatrix<BaseFloat>(in.ColRange(block_counter * num_cols_in_block,
1735  num_cols_in_block));
1736  in_batch.push_back(in_block);
1737 
1738  CuSubMatrix<BaseFloat> *out_block =
1739  new CuSubMatrix<BaseFloat>(out->ColRange(block_counter * num_rows_in_block,
1740  num_rows_in_block));
1741  out_batch.push_back(out_block);
1742 
1743  CuSubMatrix<BaseFloat> *linear_params_block =
1744  new CuSubMatrix<BaseFloat>(linear_params_.RowRange(block_counter * num_rows_in_block,
1745  num_rows_in_block));
1746  linear_params_batch.push_back(linear_params_block);
1747  }
1748  AddMatMatBatched<BaseFloat>(1.0, out_batch, in_batch, kNoTrans,
1749  linear_params_batch, kTrans, 1.0);
1750 
1751  DeletePointers(&in_batch);
1752  DeletePointers(&out_batch);
1753  DeletePointers(&linear_params_batch);
1754  return NULL;
1755 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2144
MatrixIndexT NumCols() const
Definition: cu-matrix.h:196
CuSubMatrix< Real > RowRange(const MatrixIndexT row_offset, const MatrixIndexT num_rows) const
Definition: cu-matrix.h:539
CuSubMatrix< Real > ColRange(const MatrixIndexT col_offset, const MatrixIndexT num_cols) const
Definition: cu-matrix.h:544
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
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
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 1878 of file nnet-simple-component.cc.

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

1878  {
1879  ReadUpdatableCommon(is, binary); // read opening tag and learning rate.
1880  ExpectToken(is, binary, "<NumBlocks>");
1881  ReadBasicType(is, binary, &num_blocks_);
1882  ExpectToken(is, binary, "<LinearParams>");
1883  linear_params_.Read(is, binary);
1884  ExpectToken(is, binary, "<BiasParams>");
1885  bias_params_.Read(is, binary);
1886  ExpectToken(is, binary, "<IsGradient>");
1887  ReadBasicType(is, binary, &is_gradient_);
1888  ExpectToken(is, binary, "</BlockAffineComponent>");
1889 }
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:862
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)
void Read(std::istream &is, bool binary)
I/O functions.
Definition: cu-matrix.cc:459
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 by.

by "scale" when called by an UpdatableComponent. stores stats, like BatchNormComponent– it relates to scaling activation stats, not parameters.

Reimplemented from Component.

Definition at line 1843 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().

1843  {
1844  if (scale == 0.0) {
1847  } else {
1848  linear_params_.Scale(scale);
1849  bias_params_.Scale(scale);
1850  }
1851 }
void Scale(Real value)
Definition: cu-vector.cc:1105
void Scale(Real value)
Definition: cu-matrix.cc:608
void SetZero()
Math operations, some calling kernels.
Definition: cu-matrix.cc:474
void SetZero()
Math operations.
Definition: cu-vector.cc:988
virtual std::string Type ( ) const
inlinevirtual

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

Implements Component.

Definition at line 543 of file nnet-simple-component.h.

Referenced by BlockAffineComponent::InitFromConfig().

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

Converts the parameters from vector form.

Reimplemented from UpdatableComponent.

Definition at line 1916 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().

1916  {
1917  KALDI_ASSERT(params.Dim() == this->NumParameters());
1918  int32 num_linear_params = linear_params_.NumCols() * linear_params_.NumRows();
1919  int32 num_bias_params = bias_params_.Dim();
1920  linear_params_.CopyRowsFromVec(params.Range(0, num_linear_params));
1921  bias_params_.CopyFromVec(params.Range(num_linear_params, num_bias_params));
1922 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2144
MatrixIndexT NumCols() const
Definition: cu-matrix.h:196
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:67
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
void CopyFromVec(const CuVectorBase< Real > &src)
Copy functions; these will crash if the dimension do not match.
Definition: cu-vector.cc:970
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:62
SubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Returns a sub-vector of a vector (a range of elements).
Definition: kaldi-vector.h:92
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 1908 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().

1908  {
1909  KALDI_ASSERT(params->Dim() == this->NumParameters());
1910  int32 num_linear_params = linear_params_.NumCols() * linear_params_.NumRows();
1911  int32 num_bias_params = bias_params_.Dim();
1912  params->Range(0, num_linear_params).CopyRowsFromMat(linear_params_);
1913  params->Range(num_linear_params, num_bias_params).CopyFromVec(bias_params_);
1914 }
MatrixIndexT NumCols() const
Definition: cu-matrix.h:196
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:67
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
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:62
SubVector< Real > Range(const MatrixIndexT o, const MatrixIndexT l)
Returns a sub-vector of a vector (a range of elements).
Definition: kaldi-vector.h:92
void Write ( std::ostream &  os,
bool  binary 
) const
virtual

Write component to stream.

Implements Component.

Definition at line 1891 of file nnet-simple-component.cc.

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

1891  {
1892  WriteUpdatableCommon(os, binary); // Write opening tag and learning rate
1893  WriteToken(os, binary, "<NumBlocks>");
1894  WriteBasicType(os, binary, num_blocks_);
1895  WriteToken(os, binary, "<LinearParams>");
1896  linear_params_.Write(os, binary);
1897  WriteToken(os, binary, "<BiasParams>");
1898  bias_params_.Write(os, binary);
1899  WriteToken(os, binary, "<IsGradient>");
1900  WriteBasicType(os, binary, is_gradient_);
1901  WriteToken(os, binary, "</BlockAffineComponent>");
1902 }
void Write(std::ostream &is, bool binary) const
Definition: cu-vector.cc:872
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
bool is_gradient_
True if this component is to be treated as a gradient rather than as parameters.
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:467

Member Data Documentation


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