Added in API level 35

Builder


class Builder
kotlin.Any
   ↳ android.adservices.ondevicepersonalization.InferenceOutput.Builder

A builder for InferenceOutput

Summary

Public constructors

Public methods
InferenceOutput.Builder
addDataOutput(key: Int, value: Any)

InferenceOutput

Builds the instance.

InferenceOutput.Builder

A byte array that holds input data.

InferenceOutput.Builder

Note: use InferenceOutput.Builder.setData(byte[]) instead.

Public constructors

Builder

Added in API level 35
Builder()

Public methods

addDataOutput

Added in API level 35
fun addDataOutput(
    key: Int,
    value: Any
): InferenceOutput.Builder
Parameters
value Any: This value cannot be null.
Return
InferenceOutput.Builder This value cannot be null.

See Also

build

Added in API level 35
fun build(): InferenceOutput

Builds the instance. This builder should not be touched after calling this!

Return
InferenceOutput This value cannot be null.

setData

fun setData(value: ByteArray): InferenceOutput.Builder

A byte array that holds input data. The inputs should be in the same order as inputs of the model.

For LiteRT, this field is a serialized Map that is mapped to outputs of runForMultipleInputsOutputs: https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi#parameters_9

For ExecuTorch model, this field is a serialized EValue array.

Parameters
value ByteArray: This value cannot be null.
Return
InferenceOutput.Builder This value cannot be null.

setDataOutputs

Added in API level 35
fun setDataOutputs(value: MutableMap<Int!, Any!>): InferenceOutput.Builder

Note: use InferenceOutput.Builder.setData(byte[]) instead.

A map mapping output indices to multidimensional arrays of output.

For TFLite, this field is mapped to outputs of runForMultipleInputsOutputs: https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi#parameters_9

Parameters
value MutableMap<Int!, Any!>: This value cannot be null.
Return
InferenceOutput.Builder This value cannot be null.