O
- Type of aggregator model output.L
- Type of labels.AM
- Type of aggregator model.public class StackedVectorDatasetTrainer<O,AM extends IgniteModel<Vector,O>,L> extends SimpleStackedDatasetTrainer<Vector,O,AM,L>
StackedDatasetTrainer
with Vector
as submodels input and output.DatasetTrainer.EmptyDatasetException
envBuilder, environment
Constructor and Description |
---|
StackedVectorDatasetTrainer()
Constructs instance of this class.
|
StackedVectorDatasetTrainer(DatasetTrainer<AM,L> aggregatingTrainer)
Constructs instance of this class.
|
Modifier and Type | Method and Description |
---|---|
<M1 extends IgniteModel<Matrix,Matrix>> |
addMatrix2MatrixTrainer(DatasetTrainer<M1,L> trainer)
|
<M1 extends IgniteModel<Vector,Vector>> |
addTrainer(DatasetTrainer<M1,L> trainer)
Adds submodel trainer along with converters needed on training and inference stages.
|
<M1 extends IgniteModel<Vector,Double>> |
addTrainerWithDoubleOutput(DatasetTrainer<M1,L> trainer)
Shortcut for adding trainer
Vector -> Double where this trainer is treated as Vector -> Vector , where
output Vector is constructed by wrapping double value. |
StackedVectorDatasetTrainer<O,AM,L> |
withAggregatorInputMerger(IgniteBinaryOperator<Vector> merger)
Specify binary operator used to merge submodels outputs to one.
|
StackedVectorDatasetTrainer<O,AM,L> |
withAggregatorTrainer(DatasetTrainer<AM,L> aggregatorTrainer)
Specify aggregator trainer.
|
<L1> StackedVectorDatasetTrainer<O,AM,L1> |
withConvertedLabels(IgniteFunction<L1,L> new2Old)
Creates
DatasetTrainer with same training logic, but able to accept labels of given new type of labels. |
StackedVectorDatasetTrainer<O,AM,L> |
withEnvironmentBuilder(LearningEnvironmentBuilder envBuilder)
Changes learning Environment.
|
StackedVectorDatasetTrainer<O,AM,L> |
withOriginalFeaturesDropped()
Drop original features during training and inference.
|
StackedVectorDatasetTrainer<O,AM,L> |
withOriginalFeaturesKept()
Keep original features using
IgniteFunction.identity() as submodelInput2AggregatingInputConverter. |
StackedVectorDatasetTrainer<O,AM,L> |
withOriginalFeaturesKept(IgniteFunction<Vector,Vector> submodelInput2AggregatingInputConverter)
Keep original features during training and propagate submodels input to aggregator during inference
using given function.
|
StackedVectorDatasetTrainer<O,AM,L> |
withSubmodelOutput2VectorConverter(IgniteFunction<Vector,Vector> submodelOutput2VectorConverter)
Set function used for conversion of submodel output to
Vector . |
StackedVectorDatasetTrainer<O,AM,L> |
withVector2SubmodelInputConverter(IgniteFunction<Vector,Vector> vector2SubmodelInputConverter)
Set function used for conversion of
Vector to submodel input. |
fitWithInitializedDeployingContext, isUpdateable, update, updateModel
fit, fit, fit, fit, fit, fit, getLastTrainedModelOrThrowEmptyDatasetException, identityTrainer, learningEnvironment, update, update, update, update
public StackedVectorDatasetTrainer(DatasetTrainer<AM,L> aggregatingTrainer)
aggregatingTrainer
- Aggregator trainer.public StackedVectorDatasetTrainer()
public <M1 extends IgniteModel<Vector,Vector>> StackedVectorDatasetTrainer<O,AM,L> addTrainer(DatasetTrainer<M1,L> trainer)
addTrainer
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
trainer
- Submodel trainer.public StackedVectorDatasetTrainer<O,AM,L> withAggregatorTrainer(DatasetTrainer<AM,L> aggregatorTrainer)
withAggregatorTrainer
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
aggregatorTrainer
- Aggregator trainer.public StackedVectorDatasetTrainer<O,AM,L> withOriginalFeaturesKept()
IgniteFunction.identity()
as submodelInput2AggregatingInputConverter.withOriginalFeaturesKept
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
public StackedVectorDatasetTrainer<O,AM,L> withOriginalFeaturesDropped()
withOriginalFeaturesDropped
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
public StackedVectorDatasetTrainer<O,AM,L> withOriginalFeaturesKept(IgniteFunction<Vector,Vector> submodelInput2AggregatingInputConverter)
IS = Vector
), or, more generally,
some IS
parameters which are not reflected just by its type. So converter should be
written accordingly.withOriginalFeaturesKept
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
submodelInput2AggregatingInputConverter
- Function used to propagate submodels input to aggregator.public StackedVectorDatasetTrainer<O,AM,L> withSubmodelOutput2VectorConverter(IgniteFunction<Vector,Vector> submodelOutput2VectorConverter)
Vector
. This function is used during
building of dataset for training aggregator model. This dataset is augmented with results of submodels
converted to Vector
.withSubmodelOutput2VectorConverter
in class StackedDatasetTrainer<Vector,Vector,O,AM extends IgniteModel<Vector,O>,L>
submodelOutput2VectorConverter
- Function used for conversion of submodel output to Vector
.public StackedVectorDatasetTrainer<O,AM,L> withVector2SubmodelInputConverter(IgniteFunction<Vector,Vector> vector2SubmodelInputConverter)
Vector
to submodel input. This function is used during
building of dataset for training aggregator model. This dataset is augmented with results of submodels
applied to Vector
s in original dataset.withVector2SubmodelInputConverter
in class StackedDatasetTrainer<Vector,Vector,O,AM extends IgniteModel<Vector,O>,L>
vector2SubmodelInputConverter
- Function used for conversion of Vector
to submodel input.public StackedVectorDatasetTrainer<O,AM,L> withAggregatorInputMerger(IgniteBinaryOperator<Vector> merger)
withAggregatorInputMerger
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
merger
- Binary operator used to merge submodels outputs to one.public StackedVectorDatasetTrainer<O,AM,L> withEnvironmentBuilder(LearningEnvironmentBuilder envBuilder)
withEnvironmentBuilder
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
envBuilder
- Learning environment builder.public <L1> StackedVectorDatasetTrainer<O,AM,L1> withConvertedLabels(IgniteFunction<L1,L> new2Old)
DatasetTrainer
with same training logic, but able to accept labels of given new type of labels.withConvertedLabels
in class SimpleStackedDatasetTrainer<Vector,O,AM extends IgniteModel<Vector,O>,L>
L1
- New labels type.new2Old
- Converter of new labels to old labels.DatasetTrainer
with same training logic, but able to accept labels of given new type of labels.public <M1 extends IgniteModel<Vector,Double>> StackedVectorDatasetTrainer<O,AM,L> addTrainerWithDoubleOutput(DatasetTrainer<M1,L> trainer)
Vector -> Double
where this trainer is treated as Vector -> Vector
, where
output Vector
is constructed by wrapping double value.M1
- Type of submodel trainer model.trainer
- Submodel trainer.public <M1 extends IgniteModel<Matrix,Matrix>> StackedVectorDatasetTrainer<O,AM,L> addMatrix2MatrixTrainer(DatasetTrainer<M1,L> trainer)
Matrix -> Matrix
where this trainer is treated as Vector -> Vector
, where
input Vector
is turned into 1 x cols
Matrix
and output is a first row of output Matrix
.M1
- Type of submodel trainer model.trainer
- Submodel trainer.
GridGain In-Memory Computing Platform : ver. 8.9.14 Release Date : November 5 2024