createDenseModel: Simple multilayer dense network.

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Simple multilayer dense network.

Description

Simple multilayer dense network.

Usage

createDenseModel(
  inputVectorSize,
  numberOfFiltersAtBaseLayer = 512,
  numberOfLayers = 2,
  mode = "classification",
  numberOfOutputs = 1000
)

Arguments

inputVectorSize	Specifies the length of the input vector.
numberOfFiltersAtBaseLayer	Number of filters at the initial dense layer. This number is halved for each subsequent layer.
numberOfLayers	Number of dense layers defining the model.
mode	'classification' or 'regression'.
numberOfOutputs	Specifies number of units in final layer

Value

a keras model

Author(s)

Tustison NJ

Examples

library( ANTsRNet )

model <- createDenseModel( 166 )

ANTsX/ANTsRNet documentation built on April 23, 2024, 1:24 p.m.