InferenceInput.Builder

public static final class InferenceInput.Builder
extends Object

java.lang.Object
   ↳ android.adservices.ondevicepersonalization.InferenceInput.Builder

A builder for InferenceInput

Summary

Public constructors

Builder(InferenceInput.Params params, Object[] inputData, InferenceOutput expectedOutputStructure)

Creates a new Builder.

Public methods

InferenceInput build()

Builds the instance.

InferenceInput.Builder setBatchSize(int value)

The number of input examples.

InferenceInput.Builder setExpectedOutputStructure(InferenceOutput value)

The empty InferenceOutput representing the expected output structure.

InferenceInput.Builder setInputData(Object... value)

An array of input data.

InferenceInput.Builder setParams(InferenceInput.Params value)

The configuration that controls runtime interpreter behavior.

Inherited methods

Public constructors

Builder

public Builder (InferenceInput.Params params, 
                Object[] inputData, 
                InferenceOutput expectedOutputStructure)

Creates a new Builder.

Parameters
params InferenceInput.Params: The configuration that controls runtime interpreter behavior. This value cannot be null.
inputData Object: An array of input data. The inputs should be in the same order as inputs of the model.

For example, if a model takes multiple inputs: 

String[] input0 = {"foo", "bar"}; // string tensor shape is [2].
 int[] input1 = new int[]{3, 2, 1}; // int tensor shape is [3].
 Object[] inputData = {input0, input1, ...};
For TFLite, this field is mapped to inputs of runForMultipleInputsOutputs: https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi#parameters_9 This value cannot be null.
expectedOutputStructure InferenceOutput: The empty InferenceOutput representing the expected output structure. For TFLite, the inference code will verify whether this expected output structure matches model output signature.

If a model produce string tensors: 

String[] output = new String[3][2];  // Output tensor shape is [3, 2].
 HashMap<Integer, Object> outputs = new HashMap<>();
 outputs.put(0, output);
 expectedOutputStructure = new InferenceOutput.Builder().setDataOutputs(outputs).build();
This value cannot be null.

Public methods

build

public InferenceInput build ()

Builds the instance.

Returns
InferenceInput This value cannot be null.

setBatchSize

public InferenceInput.Builder setBatchSize (int value)

The number of input examples. Adopter can set this field to run batching inference. The batch size is 1 by default. The batch size should match the input data size.

Parameters
value int

Returns
InferenceInput.Builder This value cannot be null.

setExpectedOutputStructure

public InferenceInput.Builder setExpectedOutputStructure (InferenceOutput value)

The empty InferenceOutput representing the expected output structure. For TFLite, the inference code will verify whether this expected output structure matches model output signature.

If a model produce string tensors: 

String[] output = new String[3][2];  // Output tensor shape is [3, 2].
 HashMap<Integer, Object> outputs = new HashMap<>();
 outputs.put(0, output);
 expectedOutputStructure = new InferenceOutput.Builder().setDataOutputs(outputs).build();

Parameters
value InferenceOutput: This value cannot be null.
Returns
InferenceInput.Builder This value cannot be null.

setInputData

public InferenceInput.Builder setInputData (Object... value)

An array of input data. The inputs should be in the same order as inputs of the model.

For example, if a model takes multiple inputs: 

String[] input0 = {"foo", "bar"}; // string tensor shape is [2].
 int[] input1 = new int[]{3, 2, 1}; // int tensor shape is [3].
 Object[] inputData = {input0, input1, ...};
For TFLite, this field is mapped to inputs of runForMultipleInputsOutputs: https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi#parameters_9

Parameters
value Object: This value cannot be null.
Returns
InferenceInput.Builder This value cannot be null.

setParams

public InferenceInput.Builder setParams (InferenceInput.Params value)

The configuration that controls runtime interpreter behavior.

Parameters
value InferenceInput.Params: This value cannot be null.
Returns
InferenceInput.Builder This value cannot be null.