LossSSD: Loss function for the SSD deep learning architecture.
In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

LossSSD

R Documentation

Loss function for the SSD deep learning architecture.

Description

Creates an R6 class object for use with the SSD deep learning architecture based on the paper

Details

W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C-Y. Fu, A. Berg. SSD: Single Shot MultiBox Detector.

available here:

 \url{https://arxiv.org/abs/1512.02325}

Value

an SSD loss function

Usage

ssdLoss <- LossSSD$new( dimension = 2L, backgroundRatio = 3L,
  minNumberOfBackgroundBoxes = 0L,  alpha = 1.0,
  numberOfClassificationLabels )

ssdLoss$smooth_l1_loss( y_true, y_pred )
ssdLoss$log_loss( y_true, y_pred )
ssdLoss$compute_loss( y_true, y_pred )

Arguments

ssdLoss: A process object.
dimension: image dimensionality.
backgroundRatio: The maximum ratio of background to foreround for weighting in the loss function. Is rounded to the nearest integer. Default is 3.
minNumberOfBackgroundBoxes: The minimum number of background boxes to use in loss computation per batch. Should reflect a value in proportion to the batch size. Default is 0.
alpha: Weighting factor for the localization loss in total loss computation.
numberOfClassificationLabels: number of classes including background.