2martens/masterthesis-latex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Changed title of section 2.2 to something more generic

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-09-19 13:59:35 +02:00
parent 59b09c45ff
commit 561bf6d65d
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
body.tex
View File

@ -293,7 +293,7 @@ moments in neural networks which eliminates gradient variance, and
a hierarchical prior for parameters and an empirical Bayes procedure to select a hierarchical prior for parameters and an empirical Bayes procedure to select
prior variances. prior variances.
\section{Background for Bayesian SSD} \section{Background for Dropout Sampling}
\begin{table} \begin{table}
\centering \centering
@ -484,7 +484,7 @@ layers in the SSD model. Entropy thresholding takes place before
the per-class confidence threshold is applied. the per-class confidence threshold is applied.
The Bayesian variant was not fine-tuned and operates with the same The Bayesian variant was not fine-tuned and operates with the same
weights that vanilla SSD uses as well. weights that vanilla SSD uses as well.
\section{Decoding Pipelines} \section{Decoding Pipelines}