Builder

Builder

Builder(
    params: InferenceInput.Params, 
    inputData: Array<Any!>, 
    expectedOutputStructure: InferenceOutput)

Note: use android.adservices.ondevicepersonalization.InferenceInput.Builder#Builder(android.adservices.ondevicepersonalization.InferenceInput.Params,byte[]) instead.

Creates a new Builder for LiteRT model inference input. For LiteRT, inputData field is mapped to inputs of runForMultipleInputsOutputs: https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi#parameters_9 The inputs should be in the same order as inputs * of the model. *

For example, if a model takes multiple inputs: *

<code>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, ...};
  </code>

If a model produce string tensors:

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

build

fun build(): InferenceInput

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

setBatchSize

fun setBatchSize(value: Int): InferenceInput.Builder

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.

setExpectedOutputStructure

fun setExpectedOutputStructure(value: InferenceOutput): InferenceInput.Builder

The empty InferenceOutput representing the expected output structure. It's only required by LiteRT model. For LiteRT, the inference code will verify whether this expected output structure matches model output signature.

If a model produce string tensors:

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

setInputData

fun setInputData(vararg value: Any!): InferenceInput.Builder

Note: use android.adservices.ondevicepersonalization.InferenceInput.Builder#setInputData(byte[]) instead.

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:

<code>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, ...};
  </code>

setParams

fun setParams(value: InferenceInput.Params): InferenceInput.Builder

The configuration that controls runtime interpreter behavior.