layer_contextual_attention_2d: Contextual attention layer (2-D and 3-D)

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Contextual attention layer (2-D and 3-D)

Description

Contextual attention layer for generative image inpainting described in

Usage

layer_contextual_attention_2d(
  object,
  kernelSize = 3L,
  stride = 1L,
  dilationRate = 1L,
  fusionKernelSize = 0L,
  name = NULL,
  trainable = FALSE
)

layer_contextual_attention_3d(
  object,
  kernelSize = 3L,
  stride = 1L,
  dilationRate = 1L,
  fusionKernelSize = 0L,
  name = NULL,
  trainable = FALSE
)

Arguments

object	Object to compose layer with. This is either a keras::keras_model_sequential to add the layer to, or another Layer which this layer will call.
kernelSize	integer specifying convolution size
stride	integer for specifyingstride length for sampling the tensor
dilationRate	ingeger specifying dilation
fusionKernelSize	Enhance saliency of large patches
name	The name of the layer
trainable	Whether the layer weights will be updated during training.

Details

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

available here:

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

Value

a keras layer tensor

Examples

layer_contextual_attention_2d()
layer_contextual_attention_3d()
keras::keras_model_sequential() %>%
    layer_contextual_attention_2d(fusionKernelSize = 2)
keras::keras_model_sequential() %>%
    layer_contextual_attention_3d()

ANTsX/ANTsRNet documentation built on April 28, 2024, 12:16 p.m.