Introducing Google AI Edge Portal: Benchmark Edge AI at scale. Sign-up to request access during private preview.

InterpreterFactory

class InterpreterFactory

Factory for constructing InterpreterApi instances.

Deprecated; please use the InterpreterApi.create method instead.

Summary

Public constructors
`InterpreterFactory()`

Public functions
`InterpreterApi!`	`create(byteBuffer: ByteBuffer, options: InterpreterApi.Options!)` Constructs an `InterpreterApi` instance, using the specified model and options.
`InterpreterApi!`	`create(modelFile: File, options: InterpreterApi.Options!)` Constructs an `InterpreterApi` instance, using the specified model and options.

InterpreterFactory()

fun create(byteBuffer: ByteBuffer, options: InterpreterApi.Options!): InterpreterApi!

Constructs an InterpreterApi instance, using the specified model and options. The model will be read from a ByteBuffer.

Parameters
`byteBuffer: ByteBuffer`	A pre-trained TF Lite model, in binary serialized form. The ByteBuffer should not be modified after the construction of an `InterpreterApi` instance. The `ByteBuffer` can be either a `MappedByteBuffer` that memory-maps a model file, or a direct `ByteBuffer` of nativeOrder() that contains the bytes content of a model.
`options: InterpreterApi.Options!`	A set of options for customizing interpreter behavior.

Throws
`java.lang.IllegalArgumentException`	if `byteBuffer` is not a `MappedByteBuffer` nor a direct `ByteBuffer` of nativeOrder.

fun create(modelFile: File, options: InterpreterApi.Options!): InterpreterApi!

Constructs an InterpreterApi instance, using the specified model and options. The model will be loaded from a file.

Parameters
`modelFile: File`	A file containing a pre-trained TF Lite model.
`options: InterpreterApi.Options!`	A set of options for customizing interpreter behavior.

Throws
`java.lang.IllegalArgumentException`	if `modelFile` does not encode a valid TensorFlow Lite model.