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

Cleaned chapter structure

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-08-14 11:49:39 +02:00
parent dfa9d72474
commit 5cda3089c9
1 changed files with 9 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
body.tex
View File

@ -492,7 +492,13 @@ has been modified to work inside a Python package architecture and
with eager mode. It is stored as a Git submodule inside the package with eager mode. It is stored as a Git submodule inside the package
repository. repository.
\section{Preparation of data sets} \chapter{Experimental Setup and Results}
\label{chap:experiments-results}
\section{Data sets}
% TODO: reword
Usually, data sets are not perfect when it comes to neural Usually, data sets are not perfect when it comes to neural
networks: they contain outliers, invalid bounding boxes, and similar networks: they contain outliers, invalid bounding boxes, and similar
@ -539,6 +545,8 @@ all trajectories: a list of lists of lists.
\section{Replication of Miller et al.} \section{Replication of Miller et al.}
% TODO rework
Miller et al. use SSD for the object detection part. They compare Miller et al. use SSD for the object detection part. They compare
vanilla SSD, vanilla SSD with entropy thresholding, and the vanilla SSD, vanilla SSD with entropy thresholding, and the
Bayesian SSD with each other. The Bayesian SSD was created by Bayesian SSD with each other. The Bayesian SSD was created by
@ -571,32 +579,6 @@ between trajectories: some classes are only present in some
trajectories. This makes training with SSD on SceneNet practically trajectories. This makes training with SSD on SceneNet practically
impossible. impossible.
\section{Implementing an auto-encoder}
Pidhorskyi et al.~\cite{Pidhorskyi2018} released their source code
but it is for
PyTorch; I had to adapt the code for Tensorflow. For the proof of
concept, a simpler model of encoder and generator was used; the
adversarial parts were disabled for this. The encoder starts with
a sigmoid-activated convolutional layers, followed by two
convolutional layers with ReLU as activation function. It ends
with a Flatten and Dense layer.
Decoding starts with a Dense layer, followed by three transposed
convolutional layers with ReLU as activation function; the last
layer is a transposed convolutional layer with sigmoid as
activation function.
The auto-encoder works on the MNIST data set, as expected. It
works very well for COCO as well, with one caveat: it is equally
good for all classes, even when trained only on one. Novelty
detection is out of the question under theses circumstances.
\chapter{Experimental Setup and Results}
\label{chap:experiments-results}
\section{Data sets}
\section{Experimental Setup} \section{Experimental Setup}
\section{Results} \section{Results}