#include <nnet-general-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... | |
ConstantComponent () | |
ConstantComponent (const ConstantComponent &other) | |
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 > &, 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 | 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 | 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... | |
virtual void | ConsolidateMemory () |
This virtual function relates to memory management, and avoiding fragmentation. More... | |
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 | 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 () |
Private Member Functions | |
const ConstantComponent & | operator= (const ConstantComponent &other) |
Private Attributes | |
CuVector< BaseFloat > | output_ |
bool | is_updatable_ |
bool | use_natural_gradient_ |
OnlineNaturalGradient | preconditioner_ |
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... | |
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 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... | |
Definition at line 628 of file nnet-general-component.h.
Definition at line 1222 of file nnet-general-component.cc.
Referenced by ConstantComponent::Copy().
ConstantComponent | ( | const ConstantComponent & | other | ) |
Definition at line 1226 of file nnet-general-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 1341 of file nnet-general-component.cc.
References ConstantComponent::is_updatable_, KALDI_ASSERT, and ConstantComponent::output_.
|
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 1241 of file nnet-general-component.cc.
References UpdatableComponent::is_gradient_, ConstantComponent::is_updatable_, KALDI_ASSERT, UpdatableComponent::learning_rate_, NVTX_RANGE, ConstantComponent::output_, OnlineNaturalGradient::PreconditionDirections(), ConstantComponent::preconditioner_, and ConstantComponent::use_natural_gradient_.
|
virtual |
This virtual function relates to memory management, and avoiding fragmentation.
It is called only once per model, after we do the first minibatch of training. The default implementation does nothing, but it can be overridden by child classes, where it may re-initialize certain quantities that may possibly have been allocated during the forward pass (e.g. certain statistics; OnlineNaturalGradient objects). We use our own CPU-based allocator (see cu-allocator.h) and since it can't do paging since we're not in control of the GPU page table, fragmentation can be a problem. The allocator always tries to put things in 'low-address memory' (i.e. at smaller memory addresses) near the beginning of the block it allocated, to avoid fragmentation; but if permanent things (belonging to the model) are allocated in the forward pass, they can permanently stay in high memory. This function helps to prevent that, by re-allocating those things into low-address memory (It's important that it's called after all the temporary buffers for the forward-backward have been freed, so that there is low-address memory available)).
Reimplemented from Component.
Definition at line 1397 of file nnet-general-component.cc.
References ConstantComponent::preconditioner_, and OnlineNaturalGradient::Swap().
|
virtual |
Copies component (deep copy).
Implements Component.
Definition at line 1327 of file nnet-general-component.cc.
References ConstantComponent::ConstantComponent().
|
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 1356 of file nnet-general-component.cc.
References ConstantComponent::is_updatable_, KALDI_ASSERT, ConstantComponent::output_, and kaldi::VecVec().
|
inlinevirtual |
This function only does something interesting for non-simple Components.
For a given index at the output of the component, tells us what indexes are required at its input (note: "required" encompasses also optionally-required things; it will enumerate all things that we'd like to have). See also IsComputable().
[in] | misc_info | This argument is supplied to handle things that the framework can't very easily supply: information like which time indexes are needed for AggregateComponent, which time-indexes are available at the input of a recurrent network, and so on. We will add members to misc_info as needed. |
[in] | output_index | The Index at the output of the component, for which we are requesting the list of indexes at the component's input. |
[out] | desired_indexes | A list of indexes that are desired at the input. are to be written to here. By "desired" we mean required or optionally-required. |
The default implementation of this function is suitable for any SimpleComponent; it just copies the output_index to a single identical element in input_indexes.
Reimplemented from Component.
Definition at line 670 of file nnet-general-component.h.
|
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 1210 of file nnet-general-component.cc.
References UpdatableComponent::Info(), StatisticsPoolingComponent::OutputDim(), kaldi::nnet3::PrintParameterStats(), and StatisticsPoolingComponent::Type().
|
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.
Definition at line 1365 of file nnet-general-component.cc.
References VectorBase< Real >::Add(), ConfigLine::GetValue(), ConfigLine::HasUnusedValues(), UpdatableComponent::InitLearningRatesFromConfig(), ConstantComponent::is_updatable_, KALDI_ERR, ConstantComponent::output_, VectorBase< Real >::Scale(), VectorBase< Real >::SetRandn(), ConstantComponent::use_natural_gradient_, and ConfigLine::WholeLine().
|
inlinevirtual |
Returns input-dimension of this component.
Implements Component.
Definition at line 632 of file nnet-general-component.h.
|
inlinevirtual |
This function only does something interesting for non-simple Components, and it exists to make it possible to manage optionally-required inputs.
It tells the user whether a given output index is computable from a given set of input indexes, and if so, says which input indexes will be used in the computation.
Implementations of this function are required to have the property that adding an element to "input_index_set" can only ever change IsComputable from false to true, never vice versa.
[in] | misc_info | Some information specific to the computation, such as minimum and maximum times for certain components to do adaptation on; it's a place to put things that don't easily fit in the framework. |
[in] | output_index | The index that is to be computed at the output of this Component. |
[in] | input_index_set | The set of indexes that is available at the input of this Component. |
[out] | used_inputs | If this is non-NULL and the output is computable this will be set to the list of input indexes that will actually be used in the computation. |
The default implementation of this function is suitable for any SimpleComponent: it just returns true if output_index is in input_index_set, and if so sets used_inputs to vector containing that one Index.
Reimplemented from Component.
Definition at line 679 of file nnet-general-component.h.
References Component::Add(), Component::ConsolidateMemory(), kaldi::nnet3::DotProduct(), kaldi::nnet3::NumParameters(), kaldi::nnet3::PerturbParams(), and Component::Scale().
|
virtual |
The following new virtual function returns the total dimension of the parameters in this class.
Reimplemented from UpdatableComponent.
Definition at line 1384 of file nnet-general-component.cc.
References ConstantComponent::is_updatable_, KALDI_ASSERT, and ConstantComponent::output_.
|
private |
|
inlinevirtual |
Returns output-dimension of this component.
Implements Component.
Definition at line 634 of file nnet-general-component.h.
References Component::Info(), and DistributeComponent::InitFromConfig().
|
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 1350 of file nnet-general-component.cc.
References kaldi::kUndefined, ConstantComponent::output_, 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 1233 of file nnet-general-component.cc.
References CuMatrixBase< Real >::CopyRowsFromVec(), and ConstantComponent::output_.
|
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 648 of file nnet-general-component.h.
References DistributeComponent::Backprop(), DistributeComponent::Copy(), kaldi::nnet3::kUpdatableComponent, DistributeComponent::Propagate(), DistributeComponent::Read(), and DistributeComponent::Write().
|
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 1275 of file nnet-general-component.cc.
References kaldi::nnet3::ExpectToken(), UpdatableComponent::is_gradient_, ConstantComponent::is_updatable_, KALDI_ERR, UpdatableComponent::learning_rate_, UpdatableComponent::learning_rate_factor_, UpdatableComponent::max_change_, ConstantComponent::output_, kaldi::ReadBasicType(), kaldi::ReadToken(), and ConstantComponent::use_natural_gradient_.
|
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 1331 of file nnet-general-component.cc.
References ConstantComponent::is_updatable_, and ConstantComponent::output_.
|
inlinevirtual |
Returns a string such as "SigmoidComponent", describing the type of the object.
Implements Component.
Definition at line 647 of file nnet-general-component.h.
Referenced by DropoutMaskComponent::Info().
|
virtual |
Converts the parameters from vector form.
Reimplemented from UpdatableComponent.
Definition at line 1393 of file nnet-general-component.cc.
References ConstantComponent::output_.
|
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 1389 of file nnet-general-component.cc.
References VectorBase< Real >::CopyFromVec(), and ConstantComponent::output_.
|
virtual |
Write component to stream.
Implements Component.
Definition at line 1316 of file nnet-general-component.cc.
References ConstantComponent::is_updatable_, ConstantComponent::output_, ConstantComponent::use_natural_gradient_, kaldi::WriteBasicType(), kaldi::WriteToken(), and UpdatableComponent::WriteUpdatableCommon().
|
private |
Definition at line 702 of file nnet-general-component.h.
Referenced by ConstantComponent::Add(), ConstantComponent::Backprop(), ConstantComponent::DotProduct(), ConstantComponent::InitFromConfig(), ConstantComponent::NumParameters(), ConstantComponent::Read(), ConstantComponent::Scale(), and ConstantComponent::Write().
Definition at line 700 of file nnet-general-component.h.
Referenced by ConstantComponent::Add(), ConstantComponent::Backprop(), ConstantComponent::DotProduct(), ConstantComponent::InitFromConfig(), ConstantComponent::NumParameters(), ConstantComponent::PerturbParams(), ConstantComponent::Propagate(), ConstantComponent::Read(), ConstantComponent::Scale(), ConstantComponent::UnVectorize(), ConstantComponent::Vectorize(), and ConstantComponent::Write().
|
private |
Definition at line 705 of file nnet-general-component.h.
Referenced by ConstantComponent::Backprop(), and ConstantComponent::ConsolidateMemory().
|
private |
Definition at line 704 of file nnet-general-component.h.
Referenced by ConstantComponent::Backprop(), ConstantComponent::InitFromConfig(), ConstantComponent::Read(), and ConstantComponent::Write().