L2NormalizationLayer3D: L2 3-D normalization layer for SSD300/512 architecture.

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

L2 3-D normalization layer for SSD300/512 architecture.

Description

L2 3-D normalization layer for SSD300/512 architecture described in

Details

Wei Liu, Andrew Rabinovich, and Alexander C. Berg. ParseNet: Looking Wider to See Better.

available here:

    \code{https://arxiv.org/abs/1506.04579}

Value

output tensor with the same shape as the input.

Usage

layer <- L2NormalizationLayer3D$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 = L2NormalizationLayer3D$new()
## Not run: 
x$build(input_shape = c(20, 20, 20, 20, 4))

## End(Not run)

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