InputType

enum InputType : Enum<InputType>

Different Neural Networks were trained on ImageNet dataset with different image preprocessing. The main types of preprocessing widely used in keras.applications are presented in this enumeration.

Entries

TORCH

TORCH()

This preprocessing will scale pixels between 0 and 1, then will normalize each channel with respect to the ImageNet dataset.

TF()

This preprocessing will scale pixels between -1 and 1, sample-wise.

CAFFE

CAFFE()

This preprocessing will convert the images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling.

Properties

name

val name: String

ordinal

val ordinal: Int