Fan2d106
object Fan2d106 : ONNXModels.FaceAlignment<OnnxInferenceModel, Fan2D106FaceAlignmentModel>
Content copied to clipboard
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
preInit
Link copied to clipboard
preprocessInput
Link copied to clipboard
open fun preprocessInput(imageFile: File, preprocessing: Preprocessing): FloatArray
Content copied to clipboard
open override fun preprocessInput(data: FloatArray, tensorShape: LongArray): FloatArray
Content copied to clipboard
pretrainedModel
Link copied to clipboard
open override fun pretrainedModel(modelHub: ModelHub): Fan2D106FaceAlignmentModel
Content copied to clipboard