This variational block consists in two dense layers which take as input the previous layer and a sampling layer. More specifically, these layers aim to represent the mean and the log variance of the learned distribution in a variational autoencoder.
variational_block(units, epsilon_std = 1, seed = NULL)
Number of units
Standard deviation for the normal distribution used for sampling
A seed for the random number generator. Setting a seed is required if you want to save the model and be able to load it correctly
A construct with class
variational_block(3)#> Network structure: #> variational(3 units)