Modifier and Type | Method and Description |
---|---|
void |
SameDiff.evaluate(MultiDataSetIterator iterator,
Map<String,List<IEvaluation>> variableEvals,
Map<String,Integer> predictionLabelMapping,
Listener... listeners)
Perform evaluation using classes such as
Evaluation for classifier outputs
and RegressionEvaluation for regression outputs.Example: classifier evaluation Predictions variable name: "softmaxOutput" Evaluations to perform: Evaluation Data: single input, single output MultiDataSets Code: |
void |
SameDiff.evaluate(MultiDataSetIterator iterator,
String outputVariable,
int labelIndex,
IEvaluation... evaluations)
|
void |
SameDiff.evaluate(MultiDataSetIterator iterator,
String outputVariable,
int labelIndex,
List<Listener> listeners,
IEvaluation... evaluations)
Evaluate the performance of a single variable's prediction.
For example, if the variable to evaluatate was called "softmax" you would use: |
protected History |
SameDiff.fit(MultiDataSetIterator iter,
int numEpochs,
boolean incrementEpochCount,
MultiDataSetIterator validationData,
int validationFrequency,
Listener... listeners) |
History |
SameDiff.fit(MultiDataSetIterator iter,
int numEpochs,
Listener... listeners)
See
SameDiff.fit(MultiDataSetIterator, int, MultiDataSetIterator, int, Listener...) , does not preform validation. |
History |
SameDiff.fit(MultiDataSetIterator iter,
int numEpochs,
MultiDataSetIterator validationIter,
int validationFrequency,
Listener... listeners)
Fit the SameDiff instance based on MultiDataSetIterator for the specified number of epochs.
This method can both singe input, single output and multi-input, multi-output SameDiff instances Note that a TrainingConfig must be set via SameDiff.setTrainingConfig(TrainingConfig) before training can
be performed. |
protected History |
SameDiff.fitHelper(MultiDataSetIterator iter,
int numEpochs,
boolean incrementEpochCount,
MultiDataSetIterator validationData,
int validationFrequency,
List<Listener> listeners) |
Map<String,INDArray> |
SameDiff.output(MultiDataSetIterator iterator,
List<Listener> listeners,
String... outputs)
Perform inference.
Example: classifier inference Predictions variable name: "softmaxOutput" Evaluations to perform: Evaluation Data: single output MultiDataSets Code: |
Map<String,INDArray> |
SameDiff.output(MultiDataSetIterator dataSet,
String... outputs)
|
List<Map<String,INDArray>> |
SameDiff.outputBatches(MultiDataSetIterator iterator,
List<Listener> listeners,
String... outputs)
Perform inference.
Example: classifier inference Predictions variable name: "softmaxOutput" Evaluations to perform: Evaluation Data: single output MultiDataSets Code: |
List<Map<String,INDArray>> |
SameDiff.outputBatches(MultiDataSetIterator iterator,
String... outputs)
|
Modifier and Type | Method and Description |
---|---|
EvaluationConfig |
EvaluationConfig.data(MultiDataSetIterator data)
Set the data to evaluate on.
|
OutputConfig |
OutputConfig.data(MultiDataSetIterator data)
Set the data to use as input.
|
FitConfig |
FitConfig.train(MultiDataSetIterator trainingData)
Set the training data
|
FitConfig |
FitConfig.train(MultiDataSetIterator trainingData,
int epochs)
Set the training data and number of epochs
|
FitConfig |
FitConfig.validate(MultiDataSetIterator validationData)
Set the validation data
|
FitConfig |
FitConfig.validate(MultiDataSetIterator validationData,
int validationFrequency)
Set the validation data and frequency
|
Modifier and Type | Class and Description |
---|---|
class |
AsyncMultiDataSetIterator
Async prefetching iterator wrapper for MultiDataSetIterator implementations
This will asynchronously prefetch the specified number of minibatches from the underlying iterator.
Also has the option (enabled by default for most constructors) to use a cyclical workspace to avoid creating INDArrays with off-heap memory that needs to be cleaned up by the JVM garbage collector. Note that appropriate DL4J fit methods automatically utilize this iterator, so users don't need to manually wrap their iterators when fitting a network |
Modifier and Type | Field and Description |
---|---|
protected MultiDataSetIterator |
AsyncMultiDataSetIterator.backedIterator |
Modifier and Type | Class and Description |
---|---|
class |
MultiDataSetIteratorAdapter
Iterator that adapts a DataSetIterator to a MultiDataSetIterator
|
class |
SingletonMultiDataSetIterator
A very simple adapter class for converting a single MultiDataSet to a MultiDataSetIterator.
|
Modifier and Type | Interface and Description |
---|---|
interface |
ParallelMultiDataSetIterator |
Modifier and Type | Class and Description |
---|---|
class |
TestMultiDataSetIterator |
Modifier and Type | Method and Description |
---|---|
MultiDataSetIterator |
MultiDataSetIteratorFactory.create()
Create a
MultiDataSetIterator |
Modifier and Type | Method and Description |
---|---|
void |
MultiNormalizerHybrid.fit(MultiDataSetIterator iterator)
Iterates over a dataset
accumulating statistics for normalization
|
void |
MultiDataNormalization.fit(MultiDataSetIterator iterator)
Iterates over a dataset
accumulating statistics for normalization
|
void |
ImageMultiPreProcessingScaler.fit(MultiDataSetIterator iterator) |
void |
AbstractMultiDataSetNormalizer.fit(MultiDataSetIterator iterator)
Fit an iterator
|
Copyright © 2019. All rights reserved.