spatialml:securemr/com.pico.spatial.ml.securemr/Pipeline/ModelInferenceType

ModelInferenceType

enum ModelInferenceType : Enum<Pipeline.ModelInferenceType>

Model inference type, determining what inference engine the algorithm model will be run on, and what hardware backend will be used to accelerate the model inference.

Entries

QNN_HTP

Running a QNN (Qualcomm Neural Network) model, using QNN engine on Qualcomm HTP hardware

LITE_RT_CPU

Running a TensorFlow Lite model by using the LiteRT / TFLite runtime on the CPU backend.

LITE_RT_GPU

Running a TensorFlow Lite model by using the LiteRT / TFLite runtime on the GPU backend.

LITE_RT_NPU

Running a TensorFlow Lite model by using the LiteRT / TFLite runtime on the NPU backend.

Properties

entries

val entries: EnumEntries<Pipeline.ModelInferenceType>

Returns a representation of an immutable list of all enum entries, in the order they're declared.

Functions

valueOf

fun valueOf(value: String): Pipeline.ModelInferenceType

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

values

fun values(): Array<Pipeline.ModelInferenceType>

Returns an array containing the constants of this enum type, in the order they're declared.