createResNetSuperResolutionModel2D: 2-D implementation of the ResNet image super resolution...

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

2-D implementation of the ResNet image super resolution architecture.

Description

Creates a keras model of the expanded image super resolution deep learning framework based on the following python implementation:

Usage

createResNetSuperResolutionModel2D(
  inputImageSize,
  convolutionKernelSize = c(3, 3),
  numberOfFilters = 64,
  numberOfResidualBlocks = 5,
  numberOfResNetBlocks = 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). The batch size (i.e., number of training images) is not specified a priori.
convolutionKernelSize	a vector specifying the kernel size for convolution.
numberOfFilters	the number of filters for each encoding layer.
numberOfResidualBlocks	the number of residual blocks.
numberOfResNetBlocks	the number of resNet blocks. Each block will double the upsampling amount.

Details

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

Value

a keras model for ResNet image super resolution

Author(s)

Tustison NJ

Examples

createResNetSuperResolutionModel2D(c(256, 256, 3))

ANTsX/ANTsRNet documentation built on April 23, 2024, 1:24 p.m.