Lenet

class Lenet : ONNXModels.CV<OnnxInferenceModel>

This model is a neural network for digit classification that take grey-scale images of digits as input and classify the major object in the image into a set of 10 different classes.

This model is just an implementation of the famous LeNet-5 model.

The model have

an input with the shape (1x1x28x28)
an output with the shape (1x10)

Constructors

Lenet

fun Lenet()

Functions

model

open fun model(modelHub: ModelHub): OnnxInferenceModel

preInit

open override fun preInit(): InferenceModel

preprocessInput

open fun preprocessInput(imageFile: File, preprocessing: Preprocessing): FloatArray

open override fun preprocessInput(data: FloatArray, tensorShape: LongArray): FloatArray

pretrainedModel

open override fun pretrainedModel(modelHub: ModelHub): ImageRecognitionModel

Properties

channelsFirst

open override val channelsFirst: Boolean

modelRelativePath

open override val modelRelativePath: String