Super resolution GAN model

Super resolution generative adverserial network from the paper:

Details

https://arxiv.org/abs/1609.04802

and ported from the Keras (python) implementation:

https://github.com/eriklindernoren/Keras-GAN/blob/master/srgan/srgan.py

Arguments

lowResolutionImageSize

numberOfResidualBlocks

Details

$initialize instantiates a new class and builds the generator and discriminator. $buildGeneratorbuild generator. $buildGeneratorbuild discriminator.

Author

Tustison NJ

Examples

if (FALSE) {

library( keras )
library( ANTsRNet )

keras::backend()$clear_session()

ganModel <- SuperResolutionGanModel$new(
   lowResolutionImageSize = c( 112, 112, 3 ) )
testthat::expect_error({
 ganModel <- SuperResolutionGanModel$new(
   lowResolutionImageSize = c( 64, 65, 3 ) )
 })
}