ResNet50custom

object ResNet50custom : ONNXModels.CV<OnnxInferenceModel>

This model is a neural network for image classification that take images as input and classify the major object in the image into a set of 1000 different classes (labels are available via org.jetbrains.kotlinx.dl.api.core.util.loadImageNetClassLabels method).

This model has 50 layers with ResNetv1 architecture.

The model have

an input with the shape (1x224x224x3)
an output with the shape (1x1000)

NOTE: This model is converted from Keras.applications and could be used to be compared with the ResNet50noTopCustom model.

See also

Official ResNet model from Keras.applications.

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