Function for creating a symmetric autoencoder model.

Source: R/createAutoencoderModel.R

Builds an autoencoder based on the specified array definining the number of units in the encoding branch. Ported to Keras R from the Keras python implementation here:

createAutoencoderModel(
  numberOfUnitsPerLayer,
  activation = "relu",
  initializer = "glorot_uniform"
)

Arguments

numberOfUnitsPerLayer

vector defining the number of units in the encoding branch
activation

activation type for the dense layers
initializer

initializer type for the dense layers

Value

two models: the encoder and auto-encoder

Details

https://github.com/XifengGuo/DEC-keras

Author

Tustison NJ

Examples


library( ANTsRNet )
library( keras )

ae <- createAutoencoderModel( c( 784, 500, 500, 2000, 10 ) )

#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist