FaceAlignmentModelBase

abstract class FaceAlignmentModelBase<I>(modelKindDescription: String?) : OnnxHighLevelModel<I, List<<ERROR CLASS>>>
Content copied to clipboard

Base class for face alignment models.

Constructors

FaceAlignmentModelBase
Link copied to clipboard
common
fun FaceAlignmentModelBase(modelKindDescription: String? = null)
Content copied to clipboard

Functions

convert
Link copied to clipboard
common
open override fun convert(output: <ERROR CLASS>): List<<ERROR CLASS>>
Content copied to clipboard

Converts raw model output to the result.

detectLandmarks
Link copied to clipboard
common
fun detectLandmarks(image: I): List<<ERROR CLASS>>
Content copied to clipboard

Detects Landmark objects on the given image.

initializeWith
Link copied to clipboard
common
open override fun initializeWith(vararg executionProviders: ExecutionProvider)
Content copied to clipboard

Initialize the model with the specified executions providers.

predict
Link copied to clipboard
common
open fun predict(input: I): List<<ERROR CLASS>>
Content copied to clipboard

Makes prediction on the given input.

summary
Link copied to clipboard
common
open fun summary(): <ERROR CLASS>
Content copied to clipboard

Properties

internalModel
Link copied to clipboard
common
abstract val internalModel: OnnxInferenceModel
Content copied to clipboard

Model used to make predictions.

modelKindDescription
Link copied to clipboard
common
open override val modelKindDescription: String? = null
Content copied to clipboard

High-level description of the model. Used for model summary printing. For the model hub models it equals to the string representation of the OnnxModelType

preprocessing
Link copied to clipboard
common
abstract val preprocessing: <ERROR CLASS><I, <ERROR CLASS><FloatArray, <ERROR CLASS>>>
Content copied to clipboard

Preprocessing operation specific to this model.

Inheritors

Fan2D106FaceAlignmentModel
Link copied to clipboard

Extensions

detectLandmarks
Link copied to clipboard
fun FaceAlignmentModelBase<Bitmap>.detectLandmarks(imageProxy: ImageProxy): List<Landmark>
Content copied to clipboard

Detects Landmark objects on the given imageProxy.