ContextualAttentionLayer2D: Contextual attention layer (2-D)

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Contextual attention layer (2-D)

Description

Contextual attention layer for generative image inpainting described in

Details

Jiahui Yu, et al., Generative Image Inpainting with Contextual Attention, CVPR 2018.

available here:

    \code{https://arxiv.org/abs/1801.07892}

Value

output tensor with the same shape as the input.

Usage

layer <- ContextualAttentionLayer2D$new( scale )

layer$call( x, mask = NULL )
layer$build( input_shape )
layer$compute_output_shape( input_shape )

Arguments

layer

A process object.

scale

feature scale. Default = 20

x

mask

input_shape

Details

$initialize instantiates a new class.

$build

$call main body.

$compute_output_shape computes the output shape.

Author(s)

Tustison NJ

Examples

x = ContextualAttentionLayer2D$new()
x$build()

ANTsX/ANTsRNet documentation built on Nov. 21, 2024, 4:07 a.m.