AnchorBoxLayer3D: Anchor box layer for SSD architecture (3-D).

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Anchor box layer for SSD architecture (3-D).

Description

Anchor box layer for SSD architecture (3-D).

Value

a 6-D tensor with shape batchSize \times widthSize \times heightSize \times depthSize \times numberOfBoxes \times 12 In the last dimension, the first 6 values correspond to the 3-D coordinates of the bounding boxes and the other 6 are the variances.

Usage

anchorBoxGenerator <- AnchorBoxLayer3D$new( imageSize,
     scale, nextScale, aspectRatios = c( '1:1:1', '2:1:1', '1:2:1', '1:1:2' ),
     variances = 1.0 )

anchorBoxGenerator$call( x, mask = NULL )
anchorBoxGenerator$compute_output_shape( input_shape )

Arguments

anchorBoxGenerator

A process object.

imageSize

size of the input image.

scale

scale of each box (in pixels).

nextScale

next scale of each box (in pixels).

aspectRatios

vector describing the geometries of the anchor boxes for this layer.

variances

a list of 6 floats > 0 with scaling factors for the encoded predicted box coordinates. A variance value of 1.0 would apply no scaling at all to the predictions, while values in (0,1) upscale the encoded predictions and values greater than 1.0 downscale the encoded predictions. Defaults to 1.0.

x

mask

input_shape

Details

$initialize instantiates a new class.

$call main body.

$compute_output_shape computes the output shape.

Author(s)

Tustison NJ

Examples

x = AnchorBoxLayer3D$new(imageSize = c(20, 20, 20),
scale = 2, nextScale = 2)
x$build()

ANTsX/ANTsRNet documentation built on April 18, 2024, 8 a.m.