Function for creating a 3-D symmetric convolutional autoencoder model.

Builds a convolutional 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:

createConvolutionalAutoencoderModel3D(
  inputImageSize,
  numberOfFiltersPerLayer = c(32, 64, 128, 10),
  convolutionKernelSize = c(5, 5, 5),
  deconvolutionKernelSize = c(5, 5, 5)
)

Arguments

inputImageSize	vector definining spatial dimensions + channels
numberOfFiltersPerLayer	vector defining the number of convolutional filters in the encoding branch per layer
convolutionKernelSize	kernel size fo the convolutional filters
deconvolutionKernelSize	kernel size fo the convolutional transpose filters

Value

two models: the convolutional encoder and convolutional auto-encoder

Details

https://github.com/XifengGuo/DCEC

Author

Tustison NJ

Examples

library( ANTsRNet )
library( keras )

ae <- createConvolutionalAutoencoderModel2D( c( 32, 32, 1 ) )
#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist