2-D implementation of the image super resolution deep learning architecture.

Creates a keras model of the image super resolution deep learning framework. based on the paper available here:

createImageSuperResolutionModel2D(
  inputImageSize,
  convolutionKernelSizes = list(c(9, 9), c(1, 1), c(5, 5)),
  numberOfFilters = c(64, 32)
)

Arguments

inputImageSize	Used for specifying the input tensor shape. The shape (or dimension) of that tensor is the image dimensions followed by the number of channels (e.g., red, green, and blue). The batch size (i.e., number of training images) is not specified a priori.
convolutionKernelSizes	a list of 2-D vectors specifying the kernel size at each convolution layer. Default values are the same as given in the original paper. The length of kernel size vectors must be 1 greater than the vector length of the number of filters.
numberOfFilters	a vector containing the number of filters for each convolutional layer. Default values are the same as given in the original paper.

Value

a keras model for image super resolution

Details

    \url{https://arxiv.org/pdf/1501.00092}

This particular implementation is based on the following python implementation:

    \url{https://github.com/titu1994/Image-Super-Resolution}

Author

Tustison NJ

Examples

createImageSuperResolutionModel2D(c( 100, 100, 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
gc()
#>           used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
#> Ncells 2516569 134.4    4570014 244.1         NA  4570014 244.1
#> Vcells 4433207  33.9   12255594  93.6      65536 10006078  76.4