Class Index

A

AudioClassifier	Performs classification on audio waveforms.
AudioClassifier.AudioClassifierOptions	Options for setting up an `AudioClassifier`.
AudioClassifier.AudioClassifierOptions.Builder	A builder that helps to configure an instance of AudioClassifierOptions.

B

BaseOptions	Options to configure Task APIs in general.
BaseOptions.Builder	Builder for `BaseOptions`.
BaseTaskApi	Base class for Task API, provides shared logic to load/unload native libs to its C++ counterpart.
BaseVisionTaskApi	Base class for Task Vision APIs.
BaseVisionTaskApi.InferenceProvider<T>	Syntax sugar to run vision tasks with FrameBuffer and image processing options.
BertCluAnnotator	API for BERT-based Conversational Language Understanding.
BertCluAnnotator.BertCluAnnotatorOptions	Options for setting up a `BertCluAnnotator`.
BertCluAnnotator.BertCluAnnotatorOptions.Builder	Builder for `BertCluAnnotator.BertCluAnnotatorOptions`.
BertNLClassifier	Classifier API for NLClassification tasks with Bert models, categorizes string into different classes.
BertNLClassifier.BertNLClassifierOptions	Options to configure BertNLClassifier.
BertNLClassifier.BertNLClassifierOptions.Builder	Builder for `BertNLClassifier.BertNLClassifierOptions`.
BertQuestionAnswerer	Returns the most possible answers on a given question for QA models (BERT, Albert, etc.).
BertQuestionAnswerer.BertQuestionAnswererOptions	Options for setting up a `BertQuestionAnswerer`.
BertQuestionAnswerer.BertQuestionAnswererOptions.Builder	Builder for `BertQuestionAnswerer.BertQuestionAnswererOptions`.
BitmapExtractor	Utility for extracting `Bitmap` from `MlImage`.
BitmapMlImageBuilder	Builds `MlImage` from `Bitmap`.
BoundingBoxUtil	Helper class for converting values that represents bounding boxes into rectangles.
BoundingBoxUtil.CoordinateType	Denotes if the coordinates are actual pixels or relative ratios.
BoundingBoxUtil.Type	Denotes how a bounding box is represented.
ByteBufferExtractor	Utility for extracting `ByteBuffer` from `MlImage`.
ByteBufferMlImageBuilder	Builds a `MlImage` from a `ByteBuffer`.

C

CastOp	Casts a `TensorBuffer` to a specified data type.
Category	Category is a util class, contains a label, its display name, a float value as score, and the index of the label in the corresponding label file.
Classifications	The classification results of one head in a multihead (a.k.a.
Classifications	The classification results of one head in a multihead (a.k.a.
CluRequest	The input dialogue history for the `BertCluAnnotator`.
CluResponse	The output domain, intent, and slot information for the `BertCluAnnotator`.
CluResponse.CategoricalSlot	Represents a categorical slot whose values are within a finite set.
CluResponse.Mention	A single mention.
CluResponse.MentionedSlot	Represents a mentioned slot whose values are open text extracted from the input text.
ColoredLabel	Represents a label associated with a color for display purposes.
ColorSpaceType	Represents the type of color space of an image.
CompatibilityList	GPU Delegate CompatibilityListing data.
ComputeSettings	Options to configure how to accelerate the model inference using dedicated delegates.
ComputeSettings.Builder	Builder for `ComputeSettings`.
ComputeSettings.Delegate	TFLite accelerator delegate options.

D

DataType	Represents the type of elements in a TensorFlow Lite `Tensor` as an enum.
Delegate	Wrapper for a native TensorFlow Lite Delegate.
DelegateFactory	Allows creating delegates for different runtime flavors.
DequantizeOp	Dequantizes a `TensorBuffer` with given `zeroPoint` and `scale`.
Detection	Represents one detected object in the results of a `ObjectDetector`.

F

FileUtil File I/O utilities.

G

GpuDelegate	`Delegate` for GPU inference.
GpuDelegate.Options	This class is deprecated. Use `GpuDelegateFactory.Options` instead.
GpuDelegateFactory	`DelegateFactory` for creating a `GpuDelegate`.
GpuDelegateFactory.Options	Delegate options.
GpuDelegateFactory.Options.GpuBackend	Which GPU backend to select.

I

ImageClassifier	Performs classification on images.
ImageClassifier.ImageClassifierOptions	Options for setting up an ImageClassifier.
ImageClassifier.ImageClassifierOptions.Builder	A builder that helps to configure an instance of ImageClassifierOptions.
ImageOperator	Operates a TensorImage object.
ImageProcessingOptions	Options to configure the image processing pipeline, which operates before inference.
ImageProcessingOptions.Builder	Builder for `ImageProcessingOptions`.
ImageProcessingOptions.Orientation	Orientation type that follows EXIF specification.
ImageProcessor	ImageProcessor is a helper class for preprocessing and postprocessing `TensorImage`.
ImageProcessor.Builder	The Builder to create an ImageProcessor, which could be executed later.
ImageProperties	Groups a set of properties to describe how an image is stored.
ImageProperties	Represents the properties of an image object when being loaded to a `TensorImage`.
ImageProperties.Builder	Builder for `ImageProperties`.
ImageSearcher	Performs similarity search on images.
ImageSearcher.ImageSearcherOptions	Options for setting up an ImageSearcher.
ImageSearcher.ImageSearcherOptions.Builder	Builder for `ImageSearcher.ImageSearcherOptions`.
ImageSegmenter	Performs segmentation on images.
ImageSegmenter.ImageSegmenterOptions	Options for setting up an `ImageSegmenter`.
ImageSegmenter.ImageSegmenterOptions.Builder	Builder for `ImageSegmenter.ImageSegmenterOptions`.
Interpreter	Driver class to drive model inference with TensorFlow Lite.
Interpreter.Options	An options class for controlling runtime interpreter behavior.
InterpreterApi	Interface to TensorFlow Lite model interpreter, excluding experimental methods.
InterpreterApi.Options	An options class for controlling runtime interpreter behavior.
InterpreterApi.Options.TfLiteRuntime	Enum to represent where to get the TensorFlow Lite runtime implementation from.
InterpreterFactory	Factory for constructing InterpreterApi instances.

K

KeepForSdk Indicates that this object (class, method, etc) should be retained and not renamed when generating the SDK, but should be allowed to be stripped or renamed in end developer apps.

L

LabelAxisOp	Labels TensorBuffer with axisLabels for outputs.
LabelAxisOp.Builder	The inner builder class to build a LabelTensor Operator.
LabelUtil	Label operation utils.

M

MediaImageExtractor	Utility for extracting `Image` from `MlImage`.
MediaMlImageBuilder	Builds `MlImage` from `Image`.
MetadataExtractor	Loads metadata from TFLite Model FlatBuffer.
MetadataExtractor.QuantizationParams	Quantization parameters that corresponds to the table, `QuantizationParameters`, in the TFLite Model schema file.
MetadataParser	Information about the metadata parser that this metadata extractor library is depending on.
MlImage	Wraps image data for on-device machine learning (ODML) usages.
MlImage.ImageFormat	Specifies the image format of an image.
MlImage.Internal	Advanced API access for `MlImage`.
MlImage.StorageType	Specifies the image container type.
MlImageAdapter	Converts `MlImage` to `TensorImage` and vice versa.
Model	The wrapper class for a TFLite model and a TFLite interpreter.
Model.Builder	This class is deprecated. Please use `Model.createModel(Context, String, Options)`.
Model.Device	The runtime device type used for executing classification.
Model.Options	Options for running the model.
Model.Options.Builder	Builder of `Model.Options`.

N

NearestNeighbor	Represents the search result of a Searcher model.
NLClassifier	Classifier API for natural language classification tasks, categorizes string into different classes.
NLClassifier.NLClassifierOptions	Options to identify input and output tensors of the model.
NLClassifier.NLClassifierOptions.Builder	Builder for `NLClassifier.NLClassifierOptions`.
NormalizeOp	Normalizes a `TensorBuffer` with given mean and stddev: output = (input - mean) / stddev.

O

ObjectDetector	Performs object detection on images.
ObjectDetector.ObjectDetectorOptions	Options for setting up an ObjectDetector.
ObjectDetector.ObjectDetectorOptions.Builder	A builder that helps to configure an instance of ObjectDetectorOptions.
Operator<T>	The common interface for classes that carries an "apply" method, which converts T to another one.
OutputType	Output mask type.

P

Processor<T> Processes T object with prepared Operator<T>.

Q

QaAnswer	Answers to `QuestionAnswerer`.
QaAnswer.Pos	Position information of the answer relative to context.
QuantizeOp	Quantizes a `TensorBuffer` with given `zeroPoint` and `scale`.
QuestionAnswerer	API to answer questions based on context.

R

ResizeOp	As a computation unit for processing images, it can resize an image to user-specified size.
ResizeOp.ResizeMethod	Algorithms for resizing.
ResizeWithCropOrPadOp	As a computation unit for processing images, it could resize image to predefined size.
Rot90Op	Rotates image counter-clockwise.
RuntimeFlavor	Represents a TFLite runtime.

S

SearcherOptions	Options to configure Searcher API.
SearcherOptions.Builder	Builder for `SearcherOptions`.
Segmentation	Represents the segmentation result of an `ImageSegmenter`.
SequentialProcessor<T>	A processor base class that chains a serial of `Operator<T>` and executes them.

T

TaskJniUtils	JNI utils for Task API.
TaskJniUtils.EmptyHandleProvider	Syntax sugar to get nativeHandle from empty param list.
TaskJniUtils.FdAndOptionsHandleProvider<T>	Syntax sugar to get nativeHandle from file descriptor and options.
TaskJniUtils.MultipleBuffersHandleProvider	Syntax sugar to get nativeHandle from an array of `ByteBuffer`s.
Tensor	A typed multi-dimensional array used in Tensorflow Lite.
Tensor.QuantizationParams	Quantization parameters that corresponds to the table, `QuantizationParameters`, in the TFLite Model schema file.
TensorAudio	Defines a ring buffer and some utility functions to prepare the input audio samples.
TensorAudio.TensorAudioFormat	Wraps a few constants describing the format of the incoming audio samples, namely number of channels and the sample rate.
TensorAudio.TensorAudioFormat.Builder	Builder for `TensorAudio.TensorAudioFormat`
TensorBuffer	Represents the data buffer for either a model's input or its output.
TensorBufferFloat	Represents data buffer with float values.
TensorBufferUint8	Represents data buffer with 8-bit unsigned integer values.
TensorFlowLite	Static utility methods for loading the TensorFlowLite runtime and native code.
TensorImage	TensorImage is the wrapper class for Image object.
TensorLabel	TensorLabel is an util wrapper for TensorBuffers with meaningful labels on an axis.
TensorOperator	Applies some operation on TensorBuffers.
TensorOperatorWrapper	The adapter that makes a TensorOperator able to run with TensorImage.
TensorProcessor	TensorProcessor is a helper class for preprocessing and postprocessing tensors.
TensorProcessor.Builder	The Builder to create an `TensorProcessor`, which could be executed later.
TextSearcher	Performs similarity search on text string.
TextSearcher.TextSearcherOptions	Options for setting up an TextSearcher.
TextSearcher.TextSearcherOptions.Builder	Builder for `TextSearcher.TextSearcherOptions`.
TfLiteAudio	Entry point for the TensorFlow Lite (TFLite) Tasks Audio API provided by Google Play services.
TfLiteText	Entry point for the TensorFlow Lite (TFLite) Tasks Text API provided by Google Play services.
TfLiteVision	Entry point for the TensorFlow Lite (TFLite) Tasks Vision API provided by Google Play services.
TransformToGrayscaleOp	Transforms an image to GrayScale as an image processing unit.

V

ValidatedAccelerationConfig Interface specifying validated acceleration configuration.