Fan2d106

This model is a neural network for face alignment that take RGB images of faces as input and produces coordinates of 106 faces landmarks.

The model have

  • an input with the shape (1x3x192x192)

  • an output with the shape (1x212)

Functions

model
Link copied to clipboard
open fun model(modelHub: ModelHub): OnnxInferenceModel
preInit
Link copied to clipboard
open override fun preInit(): OnnxInferenceModel
preprocessInput
Link copied to clipboard
open fun preprocessInput(imageFile: File, preprocessing: Preprocessing): FloatArray
open override fun preprocessInput(data: FloatArray, tensorShape: LongArray): FloatArray
pretrainedModel
Link copied to clipboard
open override fun pretrainedModel(modelHub: ModelHub): Fan2D106FaceAlignmentModel

Properties

channelsFirst
Link copied to clipboard
open override val channelsFirst: Boolean
modelRelativePath
Link copied to clipboard
open override val modelRelativePath: String