PerElementScaleComponent scales each dimension of its input with a separate trainable scale; it's like a linear component with a diagonal matrix. More...
#include <nnet-simple-component.h>
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... | |
PerElementScaleComponent () | |
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 Component * | Copy () 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 > ¶ms) |
Converts the parameters from vector form. More... | |
PerElementScaleComponent (const PerElementScaleComponent &other) | |
void | Init (int32 dim, BaseFloat param_mean, BaseFloat param_stddev) |
void | Init (std::string vector_filename) |
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... | |
virtual void | ConsolidateMemory () |
This virtual function relates to memory management, and avoiding fragmentation. 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 PerElementScaleComponent & | operator= (const PerElementScaleComponent &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 | |
CuVector< BaseFloat > | scales_ |
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... | |
Additional Inherited Members | |
Static Public Member Functions inherited from Component | |
static Component * | ReadNew (std::istream &is, bool binary) |
Read component from stream (works out its type). Dies on error. More... | |
static Component * | NewComponentOfType (const std::string &type) |
Returns a new Component of the given type e.g. More... | |
PerElementScaleComponent scales each dimension of its input with a separate trainable scale; it's like a linear component with a diagonal matrix.
This version (and its child class NaturalGradientPerElementScaleComponent) requires the input for backprop. See also ScaleAndOffsetComponent.
Accepted values on its config line, with defaults if applicable:
vector If specified, the offsets will be read from this file ('vector' is interpreted as an rxfilename).
dim The dimension that this component inputs and outputs. Only required if 'vector' is not specified.
param-mean=1.0 Mean of randomly initialized offset parameters; should only be supplied if 'vector' is not supplied. param-stddev=0.0 Standard deviation of randomly initialized offset parameters; should only be supplied if 'vector' is not supplied.
Definition at line 1513 of file nnet-simple-component.h.
|
inline |
Definition at line 1521 of file nnet-simple-component.h.
Referenced by PerElementScaleComponent::Copy().
|
explicit |
Definition at line 1962 of file nnet-simple-component.cc.
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 1954 of file nnet-simple-component.cc.
References KALDI_ASSERT, and PerElementScaleComponent::scales_.
Referenced by CompositeComponent::Add().
|
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.
[in] | debug_info | The component name, to be printed out in any warning messages. |
[in] | indexes | A 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_value | The matrix that was given as input to the Propagate function. Will be ignored (and may be empty) if Properties()&kBackpropNeedsInput == 0. |
[in] | out_value | The matrix that was output from the Propagate function. Will be ignored (and may be empty) if Properties()&kBackpropNeedsOutput == 0 |
[in] | out_deriv | The derivative at the output of this component. |
[in] | memo | This 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_update | If 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_deriv | The 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 2048 of file nnet-simple-component.cc.
References CuMatrixBase< Real >::CopyFromMat(), CuMatrixBase< Real >::Data(), UpdatableComponent::is_gradient_, CuMatrixBase< Real >::MulColsVec(), NVTX_RANGE, PerElementScaleComponent::scales_, PerElementScaleComponent::Update(), and PerElementScaleComponent::UpdateSimple().
Referenced by CompositeComponent::Backprop().
|
virtual |
Copies component (deep copy).
Implements Component.
Reimplemented in NaturalGradientPerElementScaleComponent.
Definition at line 1982 of file nnet-simple-component.cc.
References PerElementScaleComponent::PerElementScaleComponent().
|
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 1986 of file nnet-simple-component.cc.
References PerElementScaleComponent::scales_, and kaldi::VecVec().
|
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 NaturalGradientPerElementScaleComponent.
Definition at line 1973 of file nnet-simple-component.cc.
References UpdatableComponent::Info(), kaldi::nnet3::PrintParameterStats(), and PerElementScaleComponent::scales_.
Referenced by NaturalGradientPerElementScaleComponent::Info().
Definition at line 1993 of file nnet-simple-component.cc.
References KALDI_ASSERT, and PerElementScaleComponent::scales_.
Referenced by NaturalGradientPerElementScaleComponent::Init(), and PerElementScaleComponent::InitFromConfig().
void Init | ( | std::string | vector_filename | ) |
Definition at line 2003 of file nnet-simple-component.cc.
References CuVectorBase< Real >::Dim(), kaldi::ReadKaldiObject(), and PerElementScaleComponent::scales_.
|
virtual |
Initialize, from a ConfigLine object.
[in] | cfl | A ConfigLine containing any parameters that are needed for initialization. For example: "dim=100 param-stddev=0.1" |
Implements Component.
Reimplemented in NaturalGradientPerElementScaleComponent.
Definition at line 2010 of file nnet-simple-component.cc.
References ConfigLine::GetValue(), ConfigLine::HasUnusedValues(), PerElementScaleComponent::Init(), UpdatableComponent::InitLearningRatesFromConfig(), PerElementScaleComponent::InputDim(), KALDI_ASSERT, KALDI_ERR, and ConfigLine::UnusedValues().
|
inlinevirtual |
Returns input-dimension of this component.
Implements Component.
Definition at line 1515 of file nnet-simple-component.h.
Referenced by CompositeComponent::Backprop(), CompositeComponent::Init(), PerElementScaleComponent::InitFromConfig(), PerElementScaleComponent::NumParameters(), and CompositeComponent::Propagate().
|
virtual |
The following new virtual function returns the total dimension of the parameters in this class.
Reimplemented from UpdatableComponent.
Definition at line 2098 of file nnet-simple-component.cc.
References PerElementScaleComponent::InputDim().
|
protected |
|
inlinevirtual |
Returns output-dimension of this component.
Implements Component.
Definition at line 1516 of file nnet-simple-component.h.
References Component::Info(), and PnormComponent::InitFromConfig().
Referenced by CompositeComponent::Backprop(), CompositeComponent::Init(), and CompositeComponent::Propagate().
|
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 1967 of file nnet-simple-component.cc.
References kaldi::kUndefined, PerElementScaleComponent::scales_, and CuVectorBase< Real >::SetRandn().
|
virtual |
Propagate function.
[in] | indexes | A 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 | The input to this component. Num-columns == InputDim(). |
[out] | out | The 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. |
Implements Component.
Definition at line 2032 of file nnet-simple-component.cc.
References CuMatrixBase< Real >::CopyFromMat(), CuMatrixBase< Real >::MulColsVec(), and PerElementScaleComponent::scales_.
Referenced by CompositeComponent::Propagate().
|
inlinevirtual |
Return bitmask of the component's properties.
These properties depend only on the component's type. See enum ComponentProperties.
Implements Component.
Definition at line 1523 of file nnet-simple-component.h.
References Component::Add(), PnormComponent::Backprop(), PnormComponent::Copy(), kaldi::nnet3::DotProduct(), PnormComponent::Init(), kaldi::nnet3::kBackpropInPlace, kaldi::nnet3::kBackpropNeedsInput, kaldi::nnet3::kPropagateInPlace, kaldi::nnet3::kSimpleComponent, kaldi::nnet3::kUpdatableComponent, kaldi::nnet3::NumParameters(), kaldi::nnet3::PerturbParams(), PnormComponent::Propagate(), PnormComponent::Read(), Component::Scale(), and PnormComponent::Write().
Referenced by CompositeComponent::Backprop(), CompositeComponent::DotProduct(), CompositeComponent::FreezeNaturalGradient(), CompositeComponent::GetStrideType(), CompositeComponent::Init(), CompositeComponent::NumParameters(), CompositeComponent::PerturbParams(), CompositeComponent::SetActualLearningRate(), CompositeComponent::SetAsGradient(), CompositeComponent::SetUnderlyingLearningRate(), CompositeComponent::UnVectorize(), and CompositeComponent::Vectorize().
|
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 NaturalGradientPerElementScaleComponent.
Definition at line 2078 of file nnet-simple-component.cc.
References kaldi::nnet3::ExpectToken(), UpdatableComponent::is_gradient_, kaldi::PeekToken(), kaldi::ReadBasicType(), UpdatableComponent::ReadUpdatableCommon(), and PerElementScaleComponent::scales_.
|
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 1946 of file nnet-simple-component.cc.
Referenced by CompositeComponent::Scale().
|
inlinevirtual |
Returns a string such as "SigmoidComponent", describing the type of the object.
Implements Component.
Reimplemented in NaturalGradientPerElementScaleComponent.
Definition at line 1522 of file nnet-simple-component.h.
|
virtual |
Converts the parameters from vector form.
Reimplemented from UpdatableComponent.
Definition at line 2106 of file nnet-simple-component.cc.
References PerElementScaleComponent::scales_.
|
inlineprotectedvirtual |
Reimplemented in NaturalGradientPerElementScaleComponent.
Definition at line 1564 of file nnet-simple-component.h.
Referenced by PerElementScaleComponent::Backprop().
|
protectedvirtual |
Definition at line 2041 of file nnet-simple-component.cc.
References kaldi::kNoTrans, kaldi::kTrans, UpdatableComponent::learning_rate_, and PerElementScaleComponent::scales_.
Referenced by PerElementScaleComponent::Backprop().
|
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 2102 of file nnet-simple-component.cc.
References VectorBase< Real >::CopyFromVec(), and PerElementScaleComponent::scales_.
|
virtual |
Write component to stream.
Implements Component.
Reimplemented in NaturalGradientPerElementScaleComponent.
Definition at line 2091 of file nnet-simple-component.cc.
References PerElementScaleComponent::scales_, kaldi::WriteToken(), and UpdatableComponent::WriteUpdatableCommon().
Definition at line 1578 of file nnet-simple-component.h.
Referenced by PerElementScaleComponent::Add(), PerElementScaleComponent::Backprop(), PerElementScaleComponent::DotProduct(), PerElementScaleComponent::Info(), PerElementScaleComponent::Init(), PerElementScaleComponent::PerturbParams(), PerElementScaleComponent::Propagate(), PerElementScaleComponent::Read(), PerElementScaleComponent::UnVectorize(), NaturalGradientPerElementScaleComponent::Update(), PerElementScaleComponent::UpdateSimple(), PerElementScaleComponent::Vectorize(), and PerElementScaleComponent::Write().