2-D implementation of the deep back-projection network.

Creates a keras model of the deep back-project network for image super resolution. More information is provided at the authors' website:

createDeepBackProjectionNetworkModel2D(
  inputImageSize,
  numberOfOutputs = 1,
  numberOfBaseFilters = 64,
  numberOfFeatureFilters = 256,
  numberOfBackProjectionStages = 7,
  convolutionKernelSize = c(12, 12),
  strides = c(8, 8),
  lastConvolution = c(3, 3),
  numberOfLossFunctions = 1
)

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).
numberOfOutputs	number of outputs (e.g., 3 for RGB images).
numberOfBaseFilters	number of base filters.
numberOfFeatureFilters	number of feature filters.
numberOfBackProjectionStages	number of up-/down-projection stages. This number includes the final up block.
convolutionKernelSize	kernel size for certain convolutional layers. This and strides are dependent on the scale factor discussed in original paper. Factors used in the original implementation are as follows: 2x --> convolutionKernelSize = c( 6, 6 ), 4x --> convolutionKernelSize = c( 8, 8 ), 8x --> convolutionKernelSize = c( 12, 12 ). We default to 8x parameters.
strides	strides for certain convolutional layers. This and the convolutionKernelSize are dependent on the scale factor discussed in original paper. Factors used in the original implementation are as follows: 2x --> strides = c( 2, 2 ), 4x --> strides = c( 4, 4 ), 8x --> strides = c( 8, 8 ). We default to 8x parameters.
lastConvolution	the kernel size for the last convolutional layer
numberOfLossFunctions	the number of data targets, e.g. 2 for 2 targets

Value

a keras model defining the deep back-projection network.

Details

    \url{https://www.toyota-ti.ac.jp/Lab/Denshi/iim/members/muhammad.haris/projects/DBPN.html}

with the paper available here:

    \url{https://arxiv.org/abs/1803.02735}

This particular implementation was influenced by the following keras (python) implementation:

    \url{https://github.com/rajatkb/DBPN-Keras}

with help from the original author's Caffe and Pytorch implementations:

    \url{https://github.com/alterzero/DBPN-caffe}
    \url{https://github.com/alterzero/DBPN-Pytorch}

Author

Tustison NJ

Examples

model = createDeepBackProjectionNetworkModel2D(c(25, 25, 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
rm(model); gc()
#> Warning: object 'model' not found
#>           used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
#> Ncells 2501655 133.7    4570014 244.1         NA  4570014 244.1
#> Vcells 4404614  33.7   10146329  77.5      65536  6714963  51.3