EfficientNetB4

class EfficientNetB4(noTop: Boolean) : 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).

Instantiates the EfficientNetB4 architecture.

The model have

  • an input with the shape (1x380x380x3)

  • an output with the shape (1x1000)

  • an output for noTop model with the shape (1x11x11x1792)

NOTE: This model is converted from Keras.applications, the last two layers in the noTop model have been removed so that the user can fine-tune the model for his specific task.

See also

Constructors

EfficientNetB4
Link copied to clipboard
fun EfficientNetB4(noTop: Boolean = false)

Functions

model
Link copied to clipboard
open fun model(modelHub: ModelHub): OnnxInferenceModel
preInit
Link copied to clipboard
open override fun preInit(): InferenceModel
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): ImageRecognitionModel

Properties

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