block_categorical: Categorical Block

In neuroimaginador/dl4ni: Deep Learning Flows for Neuroimaging

Description

This function is used to append a multivalued block to a previously existing object.

Usage

block_categorical(object, hidden_layers = NULL, num_classes = 2,
  units = 1, concatenate = FALSE)

Arguments

object	(keras object) The object where to append the block.
hidden_layers	(list) List of layers, with types and corresponding parameters.
num_classes	(integer) The number of classes in the output of the block.
units	(integer) Number of output units of the block.

Details

A categorical block consists on units different paths, with the common input object, each path is composed by a set of hidden layers (all with the same architecture defined in the arguments of this function), and ended by a dense layer with num_classes units and "softmax" activation.

The final output is the concatenation of these units independent paths.

Value

The object composed with the categorical block.

neuroimaginador/dl4ni documentation built on May 3, 2019, 5:47 p.m.