block_resnet: ResNet Block

In neuroimaginador/dl4ni: Deep Learning Flows for Neuroimaging

Description

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

Usage

block_resnet(object, hidden_layers = NULL, hidden_activation = "relu",
  hidden_dropout = 0, params = NULL)

Arguments

object	(keras object) The object where to append the block.
hidden_layers	(list) List of layers, with types and corresponding parameters.
hidden_activation	(character) Activation function to use in the hidden layers of the block.
hidden_dropout	(numeric in [0, 1]) The dropout to use in the hidden layers.
params	(list) List of parameters to apply, if not listed in the previous ones.

Details

A ResNet block consists on a set of hidden layers, and ended by a dense layer with the same number of units as output units in object and a final layer that adds object and the last layer.

Value

The object composed with the ResNet block.

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