Added in Android VanillaIceCream

Summary: Nested Classes | Constants | Methods | Inherited Methods

InferenceInput.Params

---

Kotlin |Java

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

From class java.lang.Object Object clone() Creates and returns a copy of this object. boolean equals(Object obj) Indicates whether some other object is "equal to" this one. void finalize() Called by the garbage collector on an object when garbage collection determines that there are no more references to the object. final Class<?> getClass() Returns the runtime class of this Object. int hashCode() Returns a hash code value for the object. final void notify() Wakes up a single thread that is waiting on this object's monitor. final void notifyAll() Wakes up all threads that are waiting on this object's monitor. String toString() Returns a string representation of the object. final void wait(long timeoutMillis, int nanos) Causes the current thread to wait until it is awakened, typically by being notified or interrupted, or until a certain amount of real time has elapsed. final void wait(long timeoutMillis) Causes the current thread to wait until it is awakened, typically by being notified or interrupted, or until a certain amount of real time has elapsed. final void wait() Causes the current thread to wait until it is awakened, typically by being notified or interrupted.

Constants

DELEGATE_CPU

Added in Android VanillaIceCream

public static final int DELEGATE_CPU

The model inference will run on CPU.

Constant Value: 1 (0x00000001)

MODEL_TYPE_TENSORFLOW_LITE

Added in Android VanillaIceCream

public static final int MODEL_TYPE_TENSORFLOW_LITE

The model is a tensorflow lite model.

Constant Value: 1 (0x00000001)

Public methods

equals

Added in Android VanillaIceCream

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 Android VanillaIceCream

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 Android VanillaIceCream

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 Android VanillaIceCream

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 Android VanillaIceCream

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 Android VanillaIceCream

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 Android VanillaIceCream

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.