InferenceInput.Params


public static class InferenceInput.Params
extends Object

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


Summary

Nested classes

class InferenceInput.Params.Builder

A builder for Params 

Constants

int DELEGATE_CPU

The model inference will run on CPU.

int MODEL_TYPE_TENSORFLOW_LITE

The model is a tensorflow lite model.

Public methods

boolean equals(Object o)

Indicates whether some other object is "equal to" this one.

int getDelegateType()

The delegate to run model inference.

KeyValueStore getKeyValueStore()

A KeyValueStore where pre-trained model is stored.

String getModelKey()

The key of the table where the corresponding value stores a pre-trained model.

int getModelType()

The type of the pre-trained model.

int getRecommendedNumThreads()

The number of threads used for intraop parallelism on CPU, must be positive number.

int hashCode()

Returns a hash code value for the object.

Inherited methods

Constants

DELEGATE_CPU

Added in API level 35
public static final int DELEGATE_CPU

The model inference will run on CPU.

Constant Value: 1 (0x00000001)

MODEL_TYPE_TENSORFLOW_LITE

Added in API level 35
public static final int MODEL_TYPE_TENSORFLOW_LITE

The model is a tensorflow lite model.

Constant Value: 1 (0x00000001)

Public methods

equals

Added in API level 35
public boolean equals (Object o)

Indicates whether some other object is "equal to" this one.

The equals method implements an equivalence relation on non-null object references:

  • It is reflexive: for any non-null reference value x, x.equals(x) should return true.
  • It is symmetric: for any non-null reference values x and y, x.equals(y) should return true if and only if y.equals(x) returns true.
  • It is transitive: for any non-null reference values x, y, and z, if x.equals(y) returns true and y.equals(z) returns true, then x.equals(z) should return true.
  • It is consistent: for any non-null reference values x and y, multiple invocations of x.equals(y) consistently return true or consistently return false, provided no information used in equals comparisons on the objects is modified.
  • For any non-null reference value x, x.equals(null) should return false.

An equivalence relation partitions the elements it operates on into equivalence classes; all the members of an equivalence class are equal to each other. Members of an equivalence class are substitutable for each other, at least for some purposes.

Parameters
o Object: This value may be null.

Returns
boolean true if this object is the same as the obj argument; false otherwise.

getDelegateType

Added in API level 35
public int getDelegateType ()

The delegate to run model inference. If not set, the default value is DELEGATE_CPU.

Returns
int Value is DELEGATE_CPU

getKeyValueStore

Added in API level 35
public KeyValueStore getKeyValueStore ()

A KeyValueStore where pre-trained model is stored. Only supports TFLite model now.

Returns
KeyValueStore This value cannot be null.

getModelKey

Added in API level 35
public String getModelKey ()

The key of the table where the corresponding value stores a pre-trained model. Only supports TFLite model now.

Returns
String This value cannot be null.

getModelType

Added in API level 35
public int getModelType ()

The type of the pre-trained model. If not set, the default value is MODEL_TYPE_TENSORFLOW_LITE . Only supports MODEL_TYPE_TENSORFLOW_LITE for now.

Returns
int Value is MODEL_TYPE_TENSORFLOW_LITE

getRecommendedNumThreads

Added in API level 35
public int getRecommendedNumThreads ()

The number of threads used for intraop parallelism on CPU, must be positive number. Adopters can set this field based on model architecture. The actual thread number depends on system resources and other constraints.

Returns
int Value is 1 or greater

hashCode

Added in API level 35
public int hashCode ()

Returns a hash code value for the object. This method is supported for the benefit of hash tables such as those provided by HashMap.

The general contract of hashCode is:

  • Whenever it is invoked on the same object more than once during an execution of a Java application, the hashCode method must consistently return the same integer, provided no information used in equals comparisons on the object is modified. This integer need not remain consistent from one execution of an application to another execution of the same application.
  • If two objects are equal according to the equals method, then calling the hashCode method on each of the two objects must produce the same integer result.
  • It is not required that if two objects are unequal according to the equals method, then calling the hashCode method on each of the two objects must produce distinct integer results. However, the programmer should be aware that producing distinct integer results for unequal objects may improve the performance of hash tables.

Returns
int a hash code value for this object.