Thanks for tuning in to Google I/O. View all sessions on demandWatch on demand

org.tensorflow.lite

Defines classes to load and execute TensorFlowLite models.

Interfaces

Delegate Wrapper for a native TensorFlow Lite Delegate. 
DelegateFactory Allows creating delegates for different runtime flavors. 
InterpreterApi Interface to TensorFlow Lite model interpreter, excluding experimental methods. 
Tensor A typed multi-dimensional array used in Tensorflow Lite. 

Classes

Interpreter Driver class to drive model inference with TensorFlow Lite. 
Interpreter.Options An options class for controlling runtime interpreter behavior. 
InterpreterApi.Options An options class for controlling runtime interpreter behavior. 
InterpreterFactory Factory for constructing InterpreterApi instances. 
Tensor.QuantizationParams Quantization parameters that corresponds to the table, QuantizationParameters, in the TFLite Model schema file. 
TensorFlowLite Static utility methods for loading the TensorFlowLite runtime and native code. 

Enums

DataType Represents the type of elements in a TensorFlow Lite Tensor as an enum. 
InterpreterApi.Options.TfLiteRuntime Enum to represent where to get the TensorFlow Lite runtime implementation from. 
RuntimeFlavor Represents a TFLite runtime.