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

#include <nnet-simple-component.h>

Inheritance diagram for AffineComponent:
Collaboration diagram for AffineComponent:

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...
 
 AffineComponent ()
 
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...
 
virtual void SetParams (const CuVectorBase< BaseFloat > &bias, const CuMatrixBase< BaseFloat > &linear)
 
const CuVector< BaseFloat > & BiasParams () const
 
const CuMatrix< BaseFloat > & LinearParams () const
 
 AffineComponent (const AffineComponent &other)
 
 AffineComponent (const CuMatrixBase< BaseFloat > &linear_params, const CuVectorBase< BaseFloat > &bias_params, BaseFloat learning_rate)
 
void Init (int32 input_dim, int32 output_dim, BaseFloat param_stddev, BaseFloat bias_stddev)
 
void Init (std::string matrix_filename)
 
virtual void Resize (int32 input_dim, int32 output_dim)
 
- 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 SetLearningRateFactor (BaseFloat lrate_factor)
 
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 Member Functions

virtual void Update (const std::string &debug_info, const CuMatrixBase< BaseFloat > &in_value, const CuMatrixBase< BaseFloat > &out_deriv)
 
virtual void UpdateSimple (const CuMatrixBase< BaseFloat > &in_value, const CuMatrixBase< BaseFloat > &out_deriv)
 
const AffineComponentoperator= (const AffineComponent &other)
 
- 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
 

Protected Attributes

CuMatrix< BaseFloatlinear_params_
 
CuVector< BaseFloatbias_params_
 
- 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...
 

Friends

class SoftmaxComponent
 
class NaturalGradientAffineComponent
 

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...
 

Detailed Description

Definition at line 440 of file nnet-simple-component.h.

Constructor & Destructor Documentation

AffineComponent ( )
inline

Definition at line 450 of file nnet-simple-component.h.

Referenced by AffineComponent::Copy().

450 { } // use Init to really initialize.
AffineComponent ( const AffineComponent other)
explicit

Definition at line 1138 of file nnet-simple-component.cc.

1138  :
1139  UpdatableComponent(component),
1140  linear_params_(component.linear_params_),
1141  bias_params_(component.bias_params_) { }
CuMatrix< BaseFloat > linear_params_
AffineComponent ( const CuMatrixBase< BaseFloat > &  linear_params,
const CuVectorBase< BaseFloat > &  bias_params,
BaseFloat  learning_rate 
)

Definition at line 1143 of file nnet-simple-component.cc.

References CuVectorBase< Real >::Dim(), KALDI_ASSERT, CuMatrixBase< Real >::NumRows(), and UpdatableComponent::SetUnderlyingLearningRate().

1145  :
1146  linear_params_(linear_params),
1147  bias_params_(bias_params) {
1148  SetUnderlyingLearningRate(learning_rate);
1149  KALDI_ASSERT(linear_params.NumRows() == bias_params.Dim()&&
1150  bias_params.Dim() != 0);
1151 }
MatrixIndexT Dim() const
Dimensions.
Definition: cu-vector.h:67
MatrixIndexT NumRows() const
Dimensions.
Definition: cu-matrix.h:195
CuMatrix< BaseFloat > linear_params_
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
virtual void SetUnderlyingLearningRate(BaseFloat lrate)
Sets the learning rate of gradient descent- gets multiplied by learning_rate_factor_.

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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1130 of file nnet-simple-component.cc.

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

1130  {
1131  const AffineComponent *other =
1132  dynamic_cast<const AffineComponent*>(&other_in);
1133  KALDI_ASSERT(other != NULL);
1134  linear_params_.AddMat(alpha, other->linear_params_);
1135  bias_params_.AddVec(alpha, other->bias_params_);
1136 }
CuMatrix< BaseFloat > linear_params_
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 1263 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::AddMatMat(), UpdatableComponent::is_gradient_, kaldi::kNoTrans, AffineComponent::linear_params_, AffineComponent::Update(), and AffineComponent::UpdateSimple().

1270  {
1271  AffineComponent *to_update = dynamic_cast<AffineComponent*>(to_update_in);
1272 
1273  // Propagate the derivative back to the input.
1274  // add with coefficient 1.0 since property kBackpropAdds is true.
1275  // If we wanted to add with coefficient 0.0 we'd need to zero the
1276  // in_deriv, in case of infinities.
1277  if (in_deriv)
1278  in_deriv->AddMatMat(1.0, out_deriv, kNoTrans, linear_params_, kNoTrans,
1279  1.0);
1280 
1281  if (to_update != NULL) {
1282  // Next update the model (must do this 2nd so the derivatives we propagate
1283  // are accurate, in case this == to_update_in.)
1284  if (to_update->is_gradient_)
1285  to_update->UpdateSimple(in_value, out_deriv);
1286  else // the call below is to a virtual function that may be re-implemented
1287  to_update->Update(debug_info, in_value, out_deriv); // by child classes.
1288  }
1289 }
void AddMatMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType transA, const CuMatrixBase< Real > &B, MatrixTransposeType transB, Real beta)
C = alpha * A(^T)*B(^T) + beta * C.
Definition: cu-matrix.cc:1142
CuMatrix< BaseFloat > linear_params_
Component * Copy ( ) const
virtual

Copies component (deep copy).

Implements Component.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1178 of file nnet-simple-component.cc.

References AffineComponent::AffineComponent().

Referenced by ModelCollapser::CollapseComponentsScale(), and ModelCollapser::GetDiagonallyPreModifiedComponentIndex().

1178  {
1179  AffineComponent *ans = new AffineComponent(*this);
1180  return ans;
1181 }
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 1183 of file nnet-simple-component.cc.

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

1183  {
1184  const AffineComponent *other =
1185  dynamic_cast<const AffineComponent*>(&other_in);
1186  return TraceMatMat(linear_params_, other->linear_params_, kTrans)
1187  + VecVec(bias_params_, other->bias_params_);
1188 }
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.
CuMatrix< BaseFloat > linear_params_
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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1170 of file nnet-simple-component.cc.

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

1170  {
1171  std::ostringstream stream;
1172  stream << UpdatableComponent::Info();
1173  PrintParameterStats(stream, "linear-params", linear_params_);
1174  PrintParameterStats(stream, "bias", bias_params_, true);
1175  return stream.str();
1176 }
CuMatrix< BaseFloat > linear_params_
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,
BaseFloat  param_stddev,
BaseFloat  bias_stddev 
)

Definition at line 1190 of file nnet-simple-component.cc.

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

Referenced by ModelCollapser::CollapseComponentsAffine(), and AffineComponent::InitFromConfig().

1191  {
1192  linear_params_.Resize(output_dim, input_dim);
1193  bias_params_.Resize(output_dim);
1194  KALDI_ASSERT(output_dim > 0 && input_dim > 0 && param_stddev >= 0.0);
1195  linear_params_.SetRandn(); // sets to random normally distributed noise.
1196  linear_params_.Scale(param_stddev);
1198  bias_params_.Scale(bias_stddev);
1199 }
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
CuMatrix< BaseFloat > linear_params_
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
void Init ( std::string  matrix_filename)

Definition at line 1201 of file nnet-simple-component.cc.

References AffineComponent::bias_params_, CuVectorBase< Real >::CopyColFromMat(), CuMatrixBase< Real >::CopyFromMat(), KALDI_ASSERT, AffineComponent::linear_params_, CuMatrixBase< Real >::NumCols(), CuMatrixBase< Real >::NumRows(), CuMatrixBase< Real >::Range(), kaldi::ReadKaldiObject(), CuVector< Real >::Resize(), and CuMatrix< Real >::Resize().

1201  {
1202  CuMatrix<BaseFloat> mat;
1203  ReadKaldiObject(matrix_filename, &mat); // will abort on failure.
1204  KALDI_ASSERT(mat.NumCols() >= 2);
1205  int32 input_dim = mat.NumCols() - 1, output_dim = mat.NumRows();
1206  linear_params_.Resize(output_dim, input_dim);
1207  bias_params_.Resize(output_dim);
1208  linear_params_.CopyFromMat(mat.Range(0, output_dim, 0, input_dim));
1209  bias_params_.CopyColFromMat(mat, input_dim);
1210 }
void CopyColFromMat(const CuMatrixBase< Real > &mat, MatrixIndexT col)
Definition: cu-vector.cc:79
void CopyFromMat(const MatrixBase< OtherReal > &src, MatrixTransposeType trans=kNoTrans)
Definition: cu-matrix.cc:337
void Resize(MatrixIndexT dim, MatrixResizeType t=kSetZero)
Allocate the memory.
Definition: cu-vector.cc:892
void ReadKaldiObject(const std::string &filename, Matrix< float > *m)
Definition: kaldi-io.cc:818
void Resize(MatrixIndexT rows, MatrixIndexT cols, MatrixResizeType resize_type=kSetZero, MatrixStrideType stride_type=kDefaultStride)
Allocate the memory.
Definition: cu-matrix.cc:47
CuMatrix< BaseFloat > linear_params_
#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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1212 of file nnet-simple-component.cc.

References ConfigLine::GetValue(), ConfigLine::HasUnusedValues(), AffineComponent::Init(), UpdatableComponent::InitLearningRatesFromConfig(), AffineComponent::InputDim(), KALDI_ASSERT, KALDI_ERR, AffineComponent::OutputDim(), ConfigLine::UnusedValues(), and ConfigLine::WholeLine().

1212  {
1213  bool ok = true;
1214  std::string matrix_filename;
1215  int32 input_dim = -1, output_dim = -1;
1217  if (cfl->GetValue("matrix", &matrix_filename)) {
1218  Init(matrix_filename);
1219  if (cfl->GetValue("input-dim", &input_dim))
1220  KALDI_ASSERT(input_dim == InputDim() &&
1221  "input-dim mismatch vs. matrix.");
1222  if (cfl->GetValue("output-dim", &output_dim))
1223  KALDI_ASSERT(output_dim == OutputDim() &&
1224  "output-dim mismatch vs. matrix.");
1225  } else {
1226  ok = ok && cfl->GetValue("input-dim", &input_dim);
1227  ok = ok && cfl->GetValue("output-dim", &output_dim);
1228  BaseFloat param_stddev = 1.0 / std::sqrt(input_dim),
1229  bias_stddev = 1.0;
1230  cfl->GetValue("param-stddev", &param_stddev);
1231  cfl->GetValue("bias-stddev", &bias_stddev);
1232  Init(input_dim, output_dim,
1233  param_stddev, bias_stddev);
1234  }
1235  if (cfl->HasUnusedValues())
1236  KALDI_ERR << "Could not process these elements in initializer: "
1237  << cfl->UnusedValues();
1238  if (!ok)
1239  KALDI_ERR << "Bad initializer " << cfl->WholeLine();
1240 }
void InitLearningRatesFromConfig(ConfigLine *cfl)
virtual int32 OutputDim() const
Returns output-dimension of this component.
virtual int32 InputDim() const
Returns input-dimension of this component.
void Init(int32 input_dim, int32 output_dim, BaseFloat param_stddev, BaseFloat bias_stddev)
float BaseFloat
Definition: kaldi-types.h:29
#define KALDI_ERR
Definition: kaldi-error.h:127
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
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 1313 of file nnet-simple-component.cc.

References AffineComponent::InputDim(), and AffineComponent::OutputDim().

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

1313  {
1314  return (InputDim() + 1) * OutputDim();
1315 }
virtual int32 OutputDim() const
Returns output-dimension of this component.
virtual int32 InputDim() const
Returns input-dimension of this component.
const AffineComponent& operator= ( const AffineComponent other)
protected
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 1160 of file nnet-simple-component.cc.

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

1160  {
1161  CuMatrix<BaseFloat> temp_linear_params(linear_params_);
1162  temp_linear_params.SetRandn();
1163  linear_params_.AddMat(stddev, temp_linear_params);
1164 
1165  CuVector<BaseFloat> temp_bias_params(bias_params_);
1166  temp_bias_params.SetRandn();
1167  bias_params_.AddVec(stddev, temp_bias_params);
1168 }
CuMatrix< BaseFloat > linear_params_
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 1245 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::AddMatMat(), AffineComponent::bias_params_, CuMatrixBase< Real >::CopyRowsFromVec(), kaldi::kNoTrans, kaldi::kTrans, and AffineComponent::linear_params_.

1247  {
1248 
1249  // No need for asserts as they'll happen within the matrix operations.
1250  out->CopyRowsFromVec(bias_params_); // copies bias_params_ to each row
1251  // of *out.
1252  out->AddMatMat(1.0, in, kNoTrans, linear_params_, kTrans, 1.0);
1253  return NULL;
1254 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2146
void AddMatMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType transA, const CuMatrixBase< Real > &B, MatrixTransposeType transB, Real beta)
C = alpha * A(^T)*B(^T) + beta * C.
Definition: cu-matrix.cc:1142
CuMatrix< BaseFloat > linear_params_
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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1291 of file nnet-simple-component.cc.

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

1291  {
1292  ReadUpdatableCommon(is, binary); // read opening tag and learning rate.
1293  ExpectToken(is, binary, "<LinearParams>");
1294  linear_params_.Read(is, binary);
1295  ExpectToken(is, binary, "<BiasParams>");
1296  bias_params_.Read(is, binary);
1297  ExpectToken(is, binary, "<IsGradient>");
1298  ReadBasicType(is, binary, &is_gradient_);
1299  ExpectToken(is, binary, "</AffineComponent>");
1300 }
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
CuMatrix< BaseFloat > linear_params_
bool is_gradient_
True if this component is to be treated as a gradient rather than as parameters.
void Resize ( int32  input_dim,
int32  output_dim 
)
virtual

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1124 of file nnet-simple-component.cc.

References AffineComponent::bias_params_, KALDI_ASSERT, AffineComponent::linear_params_, CuVector< Real >::Resize(), and CuMatrix< Real >::Resize().

1124  {
1125  KALDI_ASSERT(input_dim > 0 && output_dim > 0);
1126  bias_params_.Resize(output_dim);
1127  linear_params_.Resize(output_dim, input_dim);
1128 }
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
CuMatrix< BaseFloat > linear_params_
#define KALDI_ASSERT(cond)
Definition: kaldi-error.h:169
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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1113 of file nnet-simple-component.cc.

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

1113  {
1114  if (scale == 0.0) {
1115  // If scale == 0.0 we call SetZero() which will get rid of NaN's and inf's.
1118  } else {
1119  linear_params_.Scale(scale);
1120  bias_params_.Scale(scale);
1121  }
1122 }
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
CuMatrix< BaseFloat > linear_params_
virtual std::string Type ( ) const
inlinevirtual

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

Implements Component.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 451 of file nnet-simple-component.h.

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

Converts the parameters from vector form.

Reimplemented from UpdatableComponent.

Definition at line 1322 of file nnet-simple-component.cc.

References AffineComponent::bias_params_, CuVectorBase< Real >::CopyFromVec(), CuMatrixBase< Real >::CopyRowsFromVec(), VectorBase< Real >::Dim(), AffineComponent::InputDim(), KALDI_ASSERT, AffineComponent::linear_params_, AffineComponent::NumParameters(), AffineComponent::OutputDim(), and VectorBase< Real >::Range().

1322  {
1323  KALDI_ASSERT(params.Dim() == this->NumParameters());
1326  OutputDim()));
1327 }
void CopyRowsFromVec(const CuVectorBase< Real > &v)
This function has two modes of operation.
Definition: cu-matrix.cc:2146
virtual int32 OutputDim() const
Returns output-dimension of this component.
virtual int32 InputDim() const
Returns input-dimension of this component.
virtual int32 NumParameters() const
The following new virtual function returns the total dimension of the parameters in this class...
void CopyFromVec(const CuVectorBase< Real > &src)
Copy functions; these will crash if the dimension do not match.
Definition: cu-vector.cc:970
CuMatrix< BaseFloat > linear_params_
#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
virtual void Update ( const std::string &  debug_info,
const CuMatrixBase< BaseFloat > &  in_value,
const CuMatrixBase< BaseFloat > &  out_deriv 
)
inlineprotectedvirtual

Reimplemented in NaturalGradientAffineComponent.

Definition at line 508 of file nnet-simple-component.h.

References AffineComponent::UpdateSimple().

Referenced by AffineComponent::Backprop().

511  {
512  UpdateSimple(in_value, out_deriv);
513  }
virtual void UpdateSimple(const CuMatrixBase< BaseFloat > &in_value, const CuMatrixBase< BaseFloat > &out_deriv)
void UpdateSimple ( const CuMatrixBase< BaseFloat > &  in_value,
const CuMatrixBase< BaseFloat > &  out_deriv 
)
protectedvirtual

Definition at line 1256 of file nnet-simple-component.cc.

References CuMatrixBase< Real >::AddMatMat(), CuVectorBase< Real >::AddRowSumMat(), AffineComponent::bias_params_, kaldi::kNoTrans, kaldi::kTrans, UpdatableComponent::learning_rate_, and AffineComponent::linear_params_.

Referenced by AffineComponent::Backprop(), and AffineComponent::Update().

1257  {
1258  bias_params_.AddRowSumMat(learning_rate_, out_deriv, 1.0);
1260  in_value, kNoTrans, 1.0);
1261 }
void AddRowSumMat(Real alpha, const CuMatrixBase< Real > &mat, Real beta=1.0)
Sum the rows of the matrix, add to vector.
Definition: cu-vector.cc:1166
BaseFloat learning_rate_
learning rate (typically 0.0..0.01)
void AddMatMat(Real alpha, const CuMatrixBase< Real > &A, MatrixTransposeType transA, const CuMatrixBase< Real > &B, MatrixTransposeType transB, Real beta)
C = alpha * A(^T)*B(^T) + beta * C.
Definition: cu-matrix.cc:1142
CuMatrix< BaseFloat > linear_params_
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 1316 of file nnet-simple-component.cc.

References AffineComponent::bias_params_, VectorBase< Real >::Dim(), AffineComponent::InputDim(), KALDI_ASSERT, AffineComponent::linear_params_, AffineComponent::NumParameters(), AffineComponent::OutputDim(), and VectorBase< Real >::Range().

1316  {
1317  KALDI_ASSERT(params->Dim() == this->NumParameters());
1318  params->Range(0, InputDim() * OutputDim()).CopyRowsFromMat(linear_params_);
1319  params->Range(InputDim() * OutputDim(),
1320  OutputDim()).CopyFromVec(bias_params_);
1321 }
virtual int32 OutputDim() const
Returns output-dimension of this component.
virtual int32 InputDim() const
Returns input-dimension of this component.
virtual int32 NumParameters() const
The following new virtual function returns the total dimension of the parameters in this class...
CuMatrix< BaseFloat > linear_params_
#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.

Reimplemented in NaturalGradientAffineComponent.

Definition at line 1302 of file nnet-simple-component.cc.

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

1302  {
1303  WriteUpdatableCommon(os, binary); // Write opening tag and learning rate
1304  WriteToken(os, binary, "<LinearParams>");
1305  linear_params_.Write(os, binary);
1306  WriteToken(os, binary, "<BiasParams>");
1307  bias_params_.Write(os, binary);
1308  WriteToken(os, binary, "<IsGradient>");
1309  WriteBasicType(os, binary, is_gradient_);
1310  WriteToken(os, binary, "</AffineComponent>");
1311 }
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
CuMatrix< BaseFloat > linear_params_
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

Friends And Related Function Documentation

friend class NaturalGradientAffineComponent
friend

Definition at line 505 of file nnet-simple-component.h.

friend class SoftmaxComponent
friend

Definition at line 441 of file nnet-simple-component.h.

Member Data Documentation


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