All Classes

Class	Description
AbstractAccuracy	Accuracy is an Evaluator that computes the accuracy score.
AbstractBaseBlock	This provides shared functionality for both the DJL-based AbstractBlocks and the imported AbstractSymbolBlocks.
AbstractBlock	AbstractBlock is an abstract implementation of Block.
AbstractCompositeLoss	AbstractCompositeLoss is a Loss class that can combine other Losses together to make a larger loss.
AbstractEmbedding<T>	An Embedding maps elements of type T to a 1-Dimensional representative NDArrays.
AbstractIndexedEmbedding<T>	An AbstractEmbedding where each embedded item can be assigned an integer index.
AbstractRepository	The AbstractRepository is the shared base for implementers of the Repository interface.
AbstractSymbolBlock	AbstractSymbolBlock is an abstract implementation of SymbolBlock.
Accuracy	Accuracy is the AbstractAccuracy with multiple classes.
ActionSpace	Contains the available actions that can be taken in an RlEnv.
Activation	Utility class that provides activation functions and blocks.
Adadelta	Adadelta is an Adadelta Optimizer.
Adadelta.Builder	The Builder to construct an Adadelta object.
Adagrad	Adagrad is an AdaGrad Optimizer.
Adagrad.Builder	The Builder to construct an Adagrad object.
Adam	Adam is a generalization of the AdaGrad Optimizer.
Adam.Builder	The Builder to construct an Adam object.
Application	A class contains common tasks that can be completed using deep learning.
Application.Audio	The common set of applications for audio data.
Application.CV	The common set of applications for computer vision (image and video data).
Application.NLP	The common set of applications for natural language processing (text data).
Application.Tabular	The common set of applications for tabular data.
Application.TimeSeries	The common set of applications for timeseries extension.
ArgumentsUtil	A utility class to extract data from model's arguments.
ArrayDataset	ArrayDataset is an implementation of RandomAccessDataset that consist entirely of large NDArrays.
ArrayDataset.Builder	The Builder to construct an ArrayDataset.
Artifact	An Artifact is a set of data files such as a model or dataset.
Artifact.Item	A file (possibly compressed) within an Artifact.
Artifact.VersionComparator	A Comparator to compare artifacts based on their version numbers.
Audio	Audio is a container of an audio in DJL.
AudioFactory	AudioFactory contains audio creation mechanism on top of different platforms like PC and Android.
BaseHpOptimizer	A base containing shared implementations for HpOptimizers.
BaseImageTranslator<T>	Built-in Translator that provides default image pre-processing.
BaseImageTranslator.BaseBuilder<T extends BaseImageTranslator.BaseBuilder>	A builder to extend for all classes extending the BaseImageTranslator.
BaseImageTranslator.ClassificationBuilder<T extends BaseImageTranslator.BaseBuilder>	A Builder to construct a ImageClassificationTranslator.
BaseImageTranslator.SynsetLoader
BaseModel	BaseModel is the basic implementation of Model.
BaseModelLoader	Shared code for the ModelLoader implementations.
BaseNDManager	BaseNDManager is the default implementation of NDManager.
BaseNDManager.TempResource
Batch	A Batch is used to hold multiple items (data and label pairs) from a Dataset.
Batchifier	An interface for different strategies to convert between Record NDLists and Batch NDList.
BatchNorm	In batch training (training with more than one samples per iteration), a batch normalization layer works by normalizing the values of input data to have mean of 0 and variance of 1.
BatchNorm.BaseBuilder<T extends BatchNorm.BaseBuilder<T>>	The Builder to construct a BatchNorm type of Block.
BatchNorm.Builder	The Builder to construct a BatchNorm.
BatchSampler	BatchSampler is a Sampler that returns a single epoch over the data.
BertBlock	Implements the core bert model (without next sentence and masked language task) of bert.
BertBlock.Builder	The Builder to construct a BertBlock type of Block.
BertFullTokenizer	BertFullTokenizer runs end to end tokenization of input text
BertMaskedLanguageModelBlock	Block for the bert masked language task.
BertMaskedLanguageModelLoss	The loss for the bert masked language model task.
BertNextSentenceBlock	Block to perform the Bert next-sentence-prediction task.
BertNextSentenceLoss	Calculates the loss for the next sentence prediction task.
BertPretrainingBlock	Creates a block that performs all bert pretraining tasks (next sentence and masked language).
BertPretrainingLoss	Loss that combines the next sentence and masked language losses of bert pretraining.
BertToken	BertToken contains all the information for Bert model after encoding question and paragraph.
BertTokenizer	BertTokenizer is a class to help you encode question and paragraph sentence.
BigGANTranslator	Built-in Translator that provides preprocessing and postprocessing for BigGAN.
BigGANTranslatorFactory	A TranslatorFactory that creates a BigGANTranslator instance.
BinaryAccuracy	BinaryAccuracy is the AbstractAccuracy with two classes.
Block	A Block is a composable function that forms a neural network.
BlockFactory	Block factory is a component to make standard for block creating and saving procedure.
BlockList	Represents a set of names and Blocks.
Blocks	Utility class that provides some useful blocks.
BoundingBox	An interface representing a bounding box around an object inside an image.
BoundingBoxError	BoundingBoxError is an Evaluator that computes the error in the prediction of bounding boxes in SingleShotDetection model.
BufferedImageFactory	BufferedImageFactory is the default implementation of ImageFactory.
BulkDataIterable	BulkDataIterable specializes DataIterable in using ArrayDataset.getByRange(NDManager, long, long) or ArrayDataset.getByIndices(NDManager, long...) to create Batch instances more efficiently.
BytesSupplier	Represents a supplier of byte[].
CategoryMask	A class representing the segmentation result of an image in an Application.CV.SEMANTIC_SEGMENTATION case.
CategoryMask.SegmentationSerializer	A customized Gson serializer to serialize the Segmentation object.
CenterCrop	A Transform that crops the center of an image.
Classifications	Classifications is the container that stores the classification results for classification on a single input.
Classifications.Classification	A Classification stores the classification result for a single class on a single input.
Classifications.ClassificationsSerializer	A customized Gson serializer to serialize the Classifications object.
ConstantEmbedding	An AbstractIndexedEmbedding that always returns a constant value.
ConstantInitializer	Initializer that generates tensors with constant values.
Conv1d	A Conv1d layer works similar to Convolution layer with the exception of the number of dimension it operates on being only one, which is LayoutType.WIDTH.
Conv1d.Builder	The Builder to construct a Conv1d type of Block.
Conv1dTranspose	A Conv1dTranspose layer works similar to Deconvolution layer with the exception of the number of dimension it operates on being only one, which is LayoutType.WIDTH.
Conv1dTranspose.Builder	The Builder to construct a Conv1dTranspose type of Block.
Conv2d	Being the pioneer of convolution layers, Conv2d layer works on two dimensions of input, LayoutType.WIDTH and LayoutType.HEIGHT as usually a Conv2d layer is used to process data with two spatial dimensions, namely image.
Conv2d.Builder	The Builder to construct a Conv2d type of Block.
Conv2dTranspose	The input to a Conv2dTranspose is an NDList with a single 4-D NDArray.
Conv2dTranspose.Builder	The Builder to construct a Conv2dTranspose type of Block.
Conv3d	Conv3d layer behaves just as Convolution does, with the distinction being it operates of 3-dimensional data such as medical images or video data.
Conv3d.Builder	The Builder to construct a Conv3d type of Block.
Convolution	A convolution layer does a dot product calculation on each channel of \(k\)-channel input data by specified number of filters, each containing \(k\) kernels for calculating each channel in the input data and then summed per filter, hence the number of filters denote the number of output channels of a convolution layer.
Convolution.ConvolutionBuilder<T extends Convolution.ConvolutionBuilder>	A builder that can build any Convolution block.
CosineTracker	CosineTracker is an implementation of Tracker which is updated by taking sections of a cosine curve to smoothly reduce learning rate until a specified step and base learning rate.
CosineTracker.Builder	The Builder to construct an CosineTracker object.
Coverage	Coverage for a Regression problem: it measures the percent of predictions greater than the actual target, to determine whether the predictor is over-forecasting or under-forecasting.
Criteria<I,O>	The Criteria class contains search criteria to look up a ZooModel.
Criteria.Builder<I,O>	A Builder to construct a Criteria.
Crop	A Transform that crops the image to a given location and size.
CyclicalTracker	CyclicalTracker is an implementation of Tracker which is a policy of learning rate adjustment that increases the learning rate off a base value in a cyclical nature, as detailed in the paper Cyclical Learning Rates for Training Neural Networks.
CyclicalTracker.Builder	The Builder to construct an CyclicalTracker object.
CyclicalTracker.CyclicalMode	CyclicalTracker provides three predefined cyclical modes and can be selected by this enum.
CyclicalTracker.ScaleFunction	ScaleFunction is an interface to implement a custom scale function.
DataDesc	A data descriptor class that encapsulates information of a NDArray.
DataIterable	DataIterable is a data loader that combines Dataset, Batchifier, Pipeline, and Sampler to provide an iterable over the given RandomAccessDataset.
Dataset	An interface to represent a set of sample data/label pairs to train a model.
Dataset.Usage	An enum that indicates the mode - training, test or validation.
DataType	An enum representing the underlying NDArray's data type.
DataType.Format	The general data type format categories.
Decoder	Decoder is an abstract block that be can used as decoder in encoder-decoder architecture.
Deconvolution	Transposed convolution, also named fractionally-strided convolution Dumoulin & Visin or deconvolution Long et al., 2015, serves this purpose.
Deconvolution.DeconvolutionBuilder<T extends Deconvolution.DeconvolutionBuilder>	A builder that can build any Deconvolution block.
DefaultModelZoo	A ModelZoo that contains models in specified locations.
DefaultTrainingConfig	DefaultTrainingConfig is an implementation of the TrainingConfig interface.
DefaultTranslatorFactory	A default implementation of TranslatorFactory.
DefaultVocabulary	The default implementation of Vocabulary.
DefaultVocabulary.Builder	Builder class that is used to build the DefaultVocabulary.
DefaultZooProvider	An ZooProvider implementation can load models from specified locations.
DeferredTranslatorFactory	A TranslatorFactory that creates the Translator based on serving.properties file.
DetectedObjects	A class representing the detected objects results for a single image in an Application.CV.OBJECT_DETECTION case.
DetectedObjects.DetectedObject	A DetectedObject represents a single potential detected Object for an image.
Device	The Device class provides the specified assignment for CPU/GPU processing on the NDArray.
Device.Type	Contains device type string constants.
Dimension	A class represents a metric dimension.
DivergenceCheckTrainingListener	TrainingListener that gives early warning if your training has failed by divergence.
DownloadUtils	A utility class downloads the file from specified url.
Dropout	A dropout layer benefits a network by allowing some units (neurons), and hence their respective connections, of a network to be randomly and temporarily removed by setting its value to 0 only during training by specified probability \(p\), usually set to 0.5.
Dropout.Builder	The Builder to construct a Dropout type of Block.
EasyHpo	Helper for easy training with hyperparameters.
EasyTrain	Helper for easy training of a whole model, a trainining batch, or a validation batch.
ElasticNetWeightDecay	ElasticWeightDecay calculates L1+L2 penalty of a set of parameters.
Embedding<T>	An Embedding block map a collection of items to 1-Dimensional representative NDArrays.
Embedding.BaseBuilder<T,B extends Embedding.BaseBuilder<T,B>>	The Builder to construct a Embedding type of Block.
EmbeddingException	Thrown to indicate that there was some error while loading embeddings.
Encoder	Encoder is an abstract block that be can used as encoder in encoder-decoder architecture.
EncoderDecoder	EncoderDecoder is a general implementation of the very popular encoder-decoder architecture.
Engine	The Engine interface is the base of the provided implementation for DJL.
EngineException	Thrown to indicate that a native error is raised from the underlying Engine.
EngineProvider	The EngineProvider instance manufactures an Engine instance, which is available in the system.
Ensembleable<T>	Represents a class that can be ensembled (or averaged).
EpochTrainingListener	EpochTrainingListener that tracks epochs.
EpsilonGreedy	The EpsilonGreedy is a simple exploration/excitation agent.
Evaluator	Base class for all Evaluators that can be used to evaluate the performance of a model.
EvaluatorTrainingListener	TrainingListener that records evaluator results.
ExpansionTranslatorFactory<IbaseT,ObaseT>	A TranslatorFactory based on a Translator and it's TranslatorOptions.
FactorTracker	FactorTracker is an implementation of Tracker which is updated by a multiplicative factor.
FactorTracker.Builder	The Builder to construct an FactorTracker object.
FilenameUtils	A class containing utility methods.
FileTranslator<T>	Built-in Translator that provides image pre-processing from file path.
FixedPerVarTracker	FixedPerVarTracker is an implementation of Tracker which returns a fixed value.
FixedPerVarTracker.Builder	The Builder to construct an FixedPerVarTracker object.
GhostBatchNorm	GhostBatchNorm is similar to BatchNorm except that it splits a batch into a smaller sub-batches aka ghost batches, and normalize them individually to have a mean of 0 and variance of 1 and finally concatenate them again to a single batch.
GhostBatchNorm.Builder	The Builder to construct a GhostBatchNorm.
GradientCollector	An interface that provides a mechanism to collect gradients during training.
GRU	GRU is an abstract implementation of recurrent neural networks which applies GRU (Gated Recurrent Unit) recurrent layer to input.
GRU.Builder	The Builder to construct a GRU type of Block.
HingeLoss	HingeLoss is a type of Loss.
HpBool	A Hyperparameter for a boolean option.
HpCategorical<T>	A Hyperparameter which is one of a fixed number of options (similar to an enum).
HpFloat	A Hyperparameter for a float.
HpInt	A Hyperparameter for an integer.
HpOptimizer	An optimizer for Hyperparameters.
HpORandom	A simple HpOptimizer that tries random hyperparameter choices within the range.
HpSet	A nestable set of Hyperparameters.
HpVal<T>	A Hyperparameter with a known value instead of a range of possible values.
Hyperparameter<T>	A class representing an input to the network that can't be differentiated.
HyphenNormalizer	Unicode normalization does not take care of "exotic" hyphens that we normally do not want in NLP input.
IdEmbedding	An Embedding from integer ids to float vectors.
IdEmbedding.Builder	The Builder to construct an IdEmbedding type of Block.
IdentityBlockFactory	A BlockFactory class that creates IdentityBlock.
Image	Image is a container of an image in DJL.
Image.Flag	Flag indicates the color channel options for images.
Image.Interpolation	Interpolation indicates the Interpolation options for resizinig an image.
ImageClassificationTranslator	A generic Translator for Image Classification tasks.
ImageClassificationTranslator.Builder	A Builder to construct a ImageClassificationTranslator.
ImageClassificationTranslatorFactory	A TranslatorFactory that creates an ImageClassificationTranslator.
ImageFactory	ImageFactory contains image creation mechanism on top of different platforms like PC and Android.
ImageFeatureExtractor	A generic Translator for Image Classification feature extraction tasks.
ImageFeatureExtractor.Builder	A Builder to construct a ImageFeatureExtractor.
ImageFeatureExtractorFactory	A TranslatorFactory that creates an ImageClassificationTranslator.
ImageServingTranslator	A Translator that can handle generic CV Input and Output.
IndexEvaluator	A wrapper for an Evaluator that evaluates on only a particular NDArray in the predictions and/or labels NDLists.
IndexLoss	A wrapper for a Loss that evaluates on only a particular NDArray in the predictions and/or labels NDLists.
Initializer	An interface representing an initialization method.
Input	A class stores the generic input data for inference.
InputStreamTranslator<T>	Built-in Translator that provides image pre-processing from InputStream.
InstanceSegmentationTranslator	A BaseImageTranslator that post-process the NDArray into DetectedObjects with boundaries at the detailed pixel level.
InstanceSegmentationTranslator.Builder	The builder for Instance Segmentation translator.
InstanceSegmentationTranslatorFactory	A TranslatorFactory that creates a InstanceSegmentationTranslator instance.
JarRepository	A JarRepository is a Repository contains an archive file from classpath.
Joints	A result of all joints found during Human Pose Estimation on a single image.
Joints.Joint	A joint that was detected using Human Pose Estimation on an image.
L1Loss	L1Loss calculates L1 loss between label and prediction.
L1WeightDecay	L1WeightDecay calculates L1 penalty of a set of parameters.
L2Loss	Calculates L2Loss between label and prediction, a.k.a.
L2WeightDecay	L2WeightDecay calculates L2 penalty of a set of parameters.
LambdaBlock	LambdaBlock is a Block with no parameters or children.
LambdaProcessor	TextProcessor will apply user defined lambda function on input tokens.
Landmark	Landmark is the container that stores the key points for landmark on a single face.
LayerNorm	Layer normalization works by normalizing the values of input data for each input sample to have mean of 0 and variance of 1.
LayerNorm.Builder	The Builder to construct a LayerNorm.
LayoutType	An enum to represent the meaning of a particular axis in an NDArray.
LazyNDArray	An NDArray that waits to compute values until they are needed.
License	A License is a container to save the license information.
Linear	A Linear block applies a linear transformation \(Y = XW^T + b\).
Linear.Builder	The Builder to construct a Linear type of Block.
LinearCollection	A LinearCollection block applies \(m\) linear transformations \(Y_i = X_i W_i + b_i\) for each \(i \in [1, \ldots, m]\) and \(m = \prod_{j=1}^t s_j\).
LinearCollection.Builder	The Builder to construct a LinearCollection type of Block.
LinearTracker	FactorTracker is an implementation of Tracker which is updated by a constant factor.
LinearTracker.Builder	The Builder to construct an LinearTracker object.
LocalParameterServer	LocalParameterServer is an implementation of the ParameterServer interface.
LocalRepository	A LocalRepository is a Repository located in a filesystem directory.
LoggingTrainingListener	TrainingListener that outputs the progress of training each batch and epoch into logs.
Loss	Loss functions (or Cost functions) are used to evaluate the model predictions against true labels for optimization.
LowerCaseConvertor	LowerCaseConvertor converts every character of the input tokens to it's respective lower case character.
LruReplayBuffer	A simple ReplayBuffer that randomly selects across the whole buffer, but always removes the oldest items in the buffer once it is full.
LSTM	LSTM is an implementation of recurrent neural networks which applies Long Short-Term Memory recurrent layer to input.
LSTM.Builder	The Builder to construct a LSTM type of Block.
MalformedModelException	Thrown to indicate Model parameters are not in expected format or are malformed.
Mask	A mask with a probability for each pixel within a bounding rectangle.
MaskedSoftmaxCrossEntropyLoss	MaskedSoftmaxCrossEntropyLoss is an implementation of Loss that only considers a specific number of values for the loss computations, and masks the rest according to the given sequence.
MemoryTrainingListener	TrainingListener that collects the memory usage information.
Metadata	A Metadata is a collection of Artifacts with unified metadata (including MRL) that are stored in the same "metadata.json" file.
Metadata.MatchAllMetadata	A Metadata class that matches all any search criteria.
Metric	A class representing a single recorded Metric value.
Metrics	A collection of Metric objects organized by metric name.
MinMaxScaler	Transform arrays by scaling each value to a given range.
MissingOps	Operators missing from NDArray that are necessary to implement Bert pretraining.
Model	A model is a collection of artifacts that is created by the training process.
ModelException	Thrown to indicate Model parameter or load exceptions parent to Model Exceptions.
ModelLoader	A ModelLoader loads a particular ZooModel from a Repository for a model zoo.
ModelNotFoundException	Thrown when an application tries to load a model from repository search path.
ModelZoo	An interface represents a collection of models.
ModelZooTextEmbedding	A WordEmbedding using a ZooModel.
MRL	The MRL (Machine learning Resource Locator) is a pointer to a Metadata "resource" on a machine learning Repository.
MultiBoxDetection	MultiBoxDetection is the class that takes the output of a multi-box detection model, and converts it into an NDList that contains the object detections.
MultiBoxDetection.Builder	The Builder to construct a MultiBoxDetection object.
MultiBoxPrior	MultiBoxPrior is the class that generates anchor boxes that act as priors for object detection.
MultiBoxPrior.Builder	The Builder to construct a MultiBoxPrior object.
MultiBoxTarget	MultiBoxTarget is the class that computes the training targets for training a Single Shot Detection (SSD) models.
MultiBoxTarget.Builder	The Builder to construct a MultiBoxTarget object.
MultiFactorTracker	MultiFactorTracker is an implementation of Tracker which returns piecewise constant values for fixed numbers of steps.
MultiFactorTracker.Builder	The Builder to construct an MultiFactorTracker object.
Multiplication	A Multiplication block performs an element-wise multiplication of inputs and weights as opposed to a Linear block which additionally sums up each element-wise multiplication.
Multiplication.Builder	The Builder to construct a Multiplication type of Block.
Nag	Nag is a Nesterov accelerated gradient optimizer.
Nag.Builder	The Builder to construct an Nag object.
NamedEntity	A class that represents a NamedEntity object.
NDArray	An interface representing an n-dimensional array.
NDArrayAdapter	A base implementation of the NDArray that does nothing.
NDArrayIndexer	A helper class for NDArray implementations for operations with an NDIndex.
NDArrays	This class contains various methods for manipulating NDArrays.
NDArraySupplier	Represents a supplier of NDArray.
NDImageUtils	NDImageUtils is an image processing utility to load, reshape, and convert images using NDArray images.
NDIndex	The NDIndex allows you to specify a subset of an NDArray that can be used for fetching or updating.
NDIndexAll	An NDIndexElement to return all values in a particular dimension.
NDIndexBooleans	An NDIndexElement to return values based on a mask binary NDArray.
NDIndexElement	An index for particular dimensions created by NDIndex.
NDIndexFixed	An NDIndexElement that returns only a specific value in the corresponding dimension.
NDIndexFullPick	A simplified representation of a pick-based NDIndex.
NDIndexFullSlice	An index as a slice on all dimensions where some dimensions can be squeezed.
NDIndexFullTake	A simplified representation of a take-based NDIndex.
NDIndexNull	An NDIndexElement to return all values in a particular dimension.
NDIndexPick	An NDIndexElement that gets elements by index in the specified axis.
NDIndexSlice	An NDIndexElement that returns a range of values in the specified dimension.
NDIndexTake	An NDIndexElement that gets elements by index in the specified axis.
NDList	An NDList represents a sequence of NDArrays with names.
NDManager	NDArray managers are used to create NDArrays (n-dimensional array on native engine).
NDManager.SystemNDManager	A NDManager.SystemNDManager is a marker class for a base NDManager.
NDResource	An object which is managed by an NDManager and tracks the manager it is attached to.
NDUtils	A class containing utility methods for NDArray operations.
NlpUtils	Utility functions for processing String and Characters in NLP problems.
NoBatchifyTranslator<I,O>	A Translator that does not use a Batchifier.
NoopServingTranslatorFactory	A TranslatorFactory that creates a RawTranslator instance.
NoopTranslator	A no operational Translator implementation.
NormalInitializer	NormalInitializer initializes weights with random values sampled from a normal distribution with a mean of zero and standard deviation of sigma.
Normalize	A Transform that normalizes an image NDArray of shape CHW or NCHW.
ObjectDetectionTranslator	A BaseImageTranslator that post-process the NDArray into DetectedObjects with boundaries.
ObjectDetectionTranslator.ObjectDetectionBuilder<T extends ObjectDetectionTranslator.ObjectDetectionBuilder>	The base builder for the object detection translator.
ObjectDetectionTranslatorFactory	An abstract TranslatorFactory that creates a ObjectDetectionTranslator instance.
OneHot	A Transform that converts the labels NDArray to one-hot labels.
Optimizer	An Optimizer updates the weight parameters to minimize the loss function.
Optimizer.OptimizerBuilder<T extends Optimizer.OptimizerBuilder>	The Builder to construct an Optimizer.
Output	A class stores the generic inference results.
PaddingStackBatchifier	The padding stack batchifier is a StackBatchifier that also pads elements to reach the same length.
PaddingStackBatchifier.Builder	Builder to build a PaddingStackBatchifier.
ParallelBlock	ParallelBlock is a Block whose children form a parallel branch in the network and are combined to produce a single output.
Parameter	Parameter is a container class that holds a learnable parameter of a model.
Parameter.Builder	A Builder to construct a Parameter.
Parameter.Type	Enumerates the types of Parameter.
ParameterList	Represents a set of names and Parameters.
ParameterServer	An interface for a key-value store to store parameters, and their corresponding gradients.
ParameterStore	The ParameterStore contains a map from a parameter to the mirrors of it on other devices.
ParameterTracker	A Tracker represents a collection of hyperparameters or Trackers that changes gradually through the training process.
Pipeline	Pipeline allows applying multiple transforms on an input NDList.
Point	A point representing a location in (x,y) coordinate space, specified in double precision.
PointwiseFeedForwardBlock	Fully connected Feed-Forward network, only applied to the last dimension of the input.
PolynomialDecayTracker	Polynomial decay Tracker.
PolynomialDecayTracker.Builder	Builder for PolynomialDecayTracker.
Pool	Utility class that provides Block and methods for different pooling functions.
PostProcessor<O>	An interface that provides post-processing functionality.
Predictor<I,O>	The Predictor interface provides a session for model inference.
Prelu	Applies Leaky Parametric ReLU activation element-wise to the input.
PreProcessor<I>	An interface that provides pre-processing functionality.
ProgressBar	ProgressBar is an implementation of Progress.
PunctuationSeparator	PunctuationSeparator separates punctuation into a separate token.
QAgent	An RlAgent that implements Q or Deep-Q Learning.
QAInput	The input container for a Application.NLP.QUESTION_ANSWER model.
QaServingTranslator	A Translator that can handle generic question answering Input and Output.
QATranslator	An abstract class to define the question answering translator.
QATranslator.BaseBuilder<T extends QATranslator.BaseBuilder>	The builder for question answering translator.
QuantileL1Loss	QuantileL1Loss calculates the Weighted Quantile Loss between labels and predictions.
RandomAccessDataset	RandomAccessDataset represent the dataset that support random access reads.
RandomAccessDataset.BaseBuilder<T extends RandomAccessDataset.BaseBuilder<T>>	The Builder to construct a RandomAccessDataset.
RandomBrightness	A Transform that randomly jitters image brightness with a factor chosen from [max(0, 1 - brightness), 1 + brightness].
RandomColorJitter	A Transform that randomly jitters the brightness, contrast, saturation, and hue of an image.
RandomFlipLeftRight	A Transform that randomly flip the input image left to right with a probability of 0.5.
RandomFlipTopBottom	A Transform that randomly flip the input image top to bottom with a probability of 0.5.
RandomHue	A Transform that randomly jitters image hue with a factor chosen from [max(0, 1 - hue), 1 + hue].
RandomResizedCrop	A Transform that crop the input image with random scale and aspect ratio.
RandomSampler	RandomSampler is an implementation of the Sampler.SubSampler interface.
Record	Record represents a single element of data and labels from Dataset.
Rectangle	A Rectangle specifies an area in a coordinate space that is enclosed by the Rectangle object's upper-left point Point in the coordinate space, its width, and its height.
RecurrentBlock	RecurrentBlock is an abstract implementation of recurrent neural networks.
RecurrentBlock.BaseBuilder<T extends RecurrentBlock.BaseBuilder>	The Builder to construct a RecurrentBlock type of Block.
RemoteRepository	A RemoteRepository is a Repository located on a remote web server.
ReplayBuffer	Records RlEnv.Steps so that they can be trained on.
Repository	Repository is a format for storing data Artifacts for various uses including deep learning models and datasets.
RepositoryFactory	A interface responsible to create Repository instances.
Resize	A Transform that resizes the image.
RlAgent	An RlAgent is the model or technique to decide the actions to take in an RlEnv.
RlEnv	An environment to use for reinforcement learning.
RlEnv.Step	A record of taking a step in the environment.
RmsProp	The RMSProp Optimizer.
RmsProp.Builder	The Builder to construct an RmsProp object.
RNN	RNN is an implementation of recurrent neural networks which applies a single-gate recurrent layer to input.
RNN.Activation	An enum that enumerates the type of activation.
RNN.Builder	The Builder to construct a RNN type of Block.
SampledAudioFactory	SampledAudioFactory is an implementation of ImageFactory using the Java Sampled Package.
Sampler	An interface for sampling data items from a RandomAccessDataset.
Sampler.SubSampler	An interface that samples a single data item at a time.
SaveModelTrainingListener	A TrainingListener that saves a model and can save checkpoints.
ScaledDotProductAttentionBlock	A Block implementing scaled product attention according to Vaswani et.
ScaledDotProductAttentionBlock.Builder	A builder for ScaledDotProductAttentionBlocks.
SemanticSegmentationTranslator	A Translator that post-process the Image into CategoryMask with output mask representing the class that each pixel in the original image belong to.
SemanticSegmentationTranslator.Builder	The builder for Semantic Segmentation translator.
SemanticSegmentationTranslatorFactory	A TranslatorFactory that creates a SemanticSegmentationTranslator instance.
SequenceSampler	SequenceSampler is an implementation of the Sampler.SubSampler interface.
SequentialBlock	SequentialBlock is a Block whose children form a chain of blocks with each child block feeding its output to the next.
ServingTranslator	A Translator that can handle generic Input and Output.
ServingTranslatorFactory	A TranslatorFactory that creates a generic Translator.
Sgd	Sgd is a Stochastic Gradient Descent (SGD) optimizer.
Sgd.Builder	The Builder to construct an Sgd object.
Shape	A class that presents the NDArray's shape information.
SigmoidBinaryCrossEntropyLoss	SigmoidBinaryCrossEntropyLoss is a type of Loss.
SimpleCompositeLoss	SimpleCompositeLoss is an implementation of the Loss abstract class that can combine different Loss functions by adding the individual losses together.
SimplePoseTranslator	A BaseImageTranslator that post-process the NDArray into human Joints.
SimplePoseTranslator.Builder	The builder for Pose Estimation translator.
SimplePoseTranslatorFactory	An TranslatorFactory that creates a SimplePoseTranslator instance.
SimpleRepository	A SimpleRepository is a Repository containing only a single artifact without requiring a "metadata.json" file.
SimpleText2TextTranslator	A Translator that performs pre-process and post-processing for a sequence-to-sequence text model.
SimpleTextEmbedding	A TextEmbedding that applies a WordEmbedding to each word independently.
SimpleTokenizer	SimpleTokenizer is an implementation of the Tokenizer interface that converts sentences into token by splitting them by a given delimiter.
SimpleUrlRepository	A SimpleUrlRepository is a Repository contains an archive file from a HTTP URL.
SingleShotDetectionAccuracy	SingleShotDetectionAccuracy is an implementation of AbstractAccuracy.
SingleShotDetectionLoss	SingleShotDetectionLoss is an implementation of Loss.
SingleShotDetectionTranslator	A BaseImageTranslator that post-process the NDArray into DetectedObjects with boundaries.
SingleShotDetectionTranslator.Builder	The builder for SSD translator.
SingleShotDetectionTranslatorFactory	An TranslatorFactory that creates a SingleShotDetectionTranslator instance.
SoftmaxCrossEntropyLoss	SoftmaxCrossEntropyLoss is a type of Loss that calculates the softmax cross entropy loss.
SparseFormat	An enum representing Sparse matrix storage formats.
SparseMax	SparseMax contains a generic implementation of sparsemax function the definition of SparseMax can be referred to https://arxiv.org/pdf/1602.02068.pdf.
SparseNDArray	An interface representing a Sparse NDArray.
SpeechRecognitionTranslator	A Translator that post-process the Audio into String to get a text translation of the audio.
SpeechRecognitionTranslatorFactory	A TranslatorFactory that creates a SpeechRecognitionTranslator instance.
StackBatchifier	StackBatchifier is used to merge a list of samples to form a mini-batch of NDArray(s).
StandardCapabilities	Constant definitions for the standard capability.
StyleTransferTranslator	Built-in Translator that provides preprocessing and postprocessing for StyleTransfer.
StyleTransferTranslatorFactory	A TranslatorFactory that creates a StyleTransferTranslator instance.
SymbolBlock	SymbolBlock is a Block is used to load models that were exported directly from the engine in its native format.
TabNetClassificationLoss	Calculates the loss for tabNet in Classification tasks.
TabNetRegressionLoss	Calculates the loss of tabNet for regression tasks.
TextClassificationServingTranslator	A Translator that can handle generic text classification Input and Output.
TextCleaner	Applies remove or replace of certain characters based on condition.
TextEmbedding	A class to manage 1-D NDArray representations of multiple words.
TextEmbeddingServingTranslator	A Translator that can handle generic text embedding Input and Output.
TextProcessor	TextProcessor allows applying pre-processing to input tokens for natural language applications.
TextTerminator	A TextProcessor that adds a beginning of string and end of string token.
TextTruncator	TextProcessor that truncates text to a maximum size.
TimeMeasureTrainingListener	TrainingListener that outputs the training time metrics after training is done.
TokenClassificationServingTranslator	A Translator that can handle generic token classification Input and Output.
Tokenizer	Tokenizer interface provides the ability to break-down sentences into embeddable tokens.
TopKAccuracy	TopKAccuracy is an Evaluator that computes the accuracy of the top k predictions.
ToTensor	A Transform that converts an image NDArray from preprocessing format to Neural Network format.
Tracker	A Tracker represents a hyperparameter that changes gradually through the training process.
TrainableTextEmbedding	TrainableTextEmbedding is an implementation of TextEmbedding based on TrainableWordEmbedding block.
TrainableWordEmbedding	TrainableWordEmbedding is an implementation of WordEmbedding and Embedding based on a DefaultVocabulary.
TrainableWordEmbedding.Builder	A builder for a TrainableWordEmbedding.
Trainer	The Trainer interface provides a session for model training.
TrainingConfig	An interface that is responsible for holding the configuration required by Trainer.
TrainingDivergedException	Thrown to indicate when there is a divergence during Training.
TrainingListener	TrainingListener offers an interface that performs some actions when certain events have occurred in the Trainer.
TrainingListener.BatchData	A class to pass data from the batch into the training listeners.
TrainingListener.Defaults	Contains default TrainingListener sets.
TrainingListenerAdapter	Base implementation of the training listener that does nothing.
TrainingResult	A class that is responsible for holding the training result produced by Trainer.
Transform	An interface to apply various transforms to the input.
TransformerEncoderBlock	Self-Attention based transformer encoder block.
TranslateException	Thrown to indicate that an error is raised during processing of the input or output.
Translator<I,O>	The Translator interface provides model pre-processing and postprocessing functionality.
TranslatorContext	The TranslatorContext interface provides a toolkit for pre-processing and postprocessing functionality.
TranslatorFactory	A utility class creates Translator instances.
TranslatorOptions	A set of possible options for Translators with different input and output types.
TruncatedNormalInitializer	Naive implementation of a truncated normal initializer.
UnicodeNormalizer	Applies unicode normalization to input strings.
UniformInitializer	UniformInitializer initializes weights with random values uniformly sampled from a given range.
UninitializedParameterException	Thrown to indicate that a Parameter was not initialized.
Unit	An interface holds metric unit constants.
UrlTranslator<T>	Built-in Translator that provides image pre-processing from URL.
Version	A Version is used for the versioning of an Artifact.
VersionRange	A VersionRange is a set of Restrictions that match some Versions.
Vocabulary	Vocabulary is a collection of tokens.
WarmUpTracker	A WarmUpTracker applies a simple warm-up before executing a main Tracker.
WarmUpTracker.Builder	The Builder to construct a WarmUpTracker.
WarmUpTracker.Mode	An enum that enumerates the types of warm-up modes for a WarmUpTracker.
WordEmbedding	A class to manage 1-D NDArray representations of words.
WordpieceTokenizer	WordpieceTokenizer tokenizes a piece of text into its word pieces.
XavierInitializer	XavierInitializer is an Initializer that performs "Xavier" initialization for parameters.
XavierInitializer.FactorType	Enum for different types of factor type.
XavierInitializer.RandomType	Enum for different types of random distributions.
YoloTranslator	A translator for yolo models.
YoloTranslator.Builder	The builder for YoloTranslator.
YoloTranslatorFactory	An TranslatorFactory that creates a YoloTranslator instance.
YOLOv3Loss	YOLOv3Loss is an implementation of Loss.
YOLOv3Loss.Builder	The Builder to construct a YOLOv3Loss object.
YoloV5Translator	A translator for YoloV5 models.
YoloV5Translator.Builder	The builder for YoloV5Translator.
YoloV5Translator.YoloOutputType	A enum represents the Yolo output type.
YoloV5TranslatorFactory	An TranslatorFactory that creates a YoloV5Translator instance.
ZooModel<I,O>	A ZooModel is a Model loaded from a model zoo and includes a default Translator.
ZooProvider	The ZooProvider is a service provider that enables ServiceLoader to locate and load at the run time.
ZooProviderNotFoundException	Runtime exception thrown when a provider of the required type cannot be found.