From bca499f2d2554076ddaa5fece1adb7d6ec1c1ad4 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 2 Oct 2019 15:47:43 +0200 Subject: [PATCH] Properly introduced anchor boxes Signed-off-by: Jim Martens --- body.tex | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/body.tex b/body.tex index 4615052..7fc5026 100644 --- a/body.tex +++ b/body.tex @@ -438,8 +438,8 @@ This chapter explains the functionality of \gls{vanilla} \gls{SSD}, Bayesian \gl Vanilla \gls{SSD} is based upon the VGG-16 network (see figure \ref{fig:vanilla-ssd}) and adds extra feature layers. The entire -image (always size 300x300) is divided up into anchor boxes. During -training, each of these boxes is mapped to a ground truth box or +image (always size 300x300) is divided up into so called anchor boxes. +During training, each of these boxes is mapped to a ground truth box or background. For every anchor box both the offset to the object and the class confidences are calculated. The output of the \gls{SSD} network are the predictions with class confidences, offsets to the