hiddenBlock: hiddenBlock

In resautonet: Autoencoder-based Residual Deep Network with Keras Support

Description

This function is to construct the hidden block .

Usage

hiddenBlock(inlayer, nodes, acts, idepth, orginlayer = NULL,
  reg = NULL, dropout = 0, batchnorm = TRUE)

Arguments

inlayer	input layer, keras layer
nodes	list of integers, list of the number of nodes for all the hidden layers
acts	list of strings, list of activations for hidden layers
idepth	integer, index of the hidden layer
orginlayer	keras layer, original layer to be added to decoding layer (default: NULL)
reg	string, regularization (default: NULL)
dropout	double, dropout rate for the target hidden layer (default 0)
batchnorm	bool, flag to conduct batch normalization (default: TRUE)

Value

keras layer, block of a hidden layer (with addtion of actionvation or/and batch normalization)

resautonet documentation built on May 2, 2019, 8:55 a.m.