layer_attention_augmentation_2d: Attention augmentation layer (2-D)

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Attention augmentation layer (2-D)

Description

Wraps the AttentionAugmentation2D layer.

Usage

layer_attention_augmentation_2d(
  object,
  depthOfQueries,
  depthOfValues,
  numberOfHeads,
  isRelative,
  trainable = TRUE
)

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.
depthOfQueries	number of filters for queries.
depthOfValues	number of filters for values.
numberOfHeads	number of attention heads to use. It is required that depthOfQueries/numberOfHeads > 0.
isRelative	whether or not to use relative encodings.
trainable	Whether the layer weights will be updated during training.

Value

a keras layer tensor

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