Dekker1/ResearchMethods
Archived
1
0
Fork 0
Code

benchmarks y'all

Browse Source
This commit is contained in:
Silver-T 2018-05-25 17:43:37 +10:00
parent d57c73be04
commit 8e367726a2
3 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
mini_proj/benchmark_results.csv
View File

@ -3,3 +3,6 @@ svm,7.871559143066406,0.8446601941747572
tree,0.25446152687072754,0.7087378640776699
naive_bayes,0.12949371337890625,0.8252427184466019
forest,0.2792677879333496,0.9514563106796117
lenet,58.12968325614929,0.8980582524271845
cnn,113.81168508529663,0.9563106796116505
fcn,117.69003772735596,0.9466019417475728
1 name time accuracy
3 tree 0.25446152687072754 0.7087378640776699
4 naive_bayes 0.12949371337890625 0.8252427184466019
5 forest 0.2792677879333496 0.9514563106796117
6 lenet 58.12968325614929 0.8980582524271845
7 cnn 113.81168508529663 0.9563106796116505
8 fcn 117.69003772735596 0.9466019417475728

BIN
mini_proj/report/LeNet.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

8
mini_proj/report/waldo.tex
View File

@ -167,7 +167,13 @@
The Fully Convolutional Network (FCN) contains only one dense layer for the final binary classification step.
The FCN instead consists of an extra convolutional layer, resulting in an increased ability for the network to abstract the input data relative to the other two configurations.
\\
\todo{Insert image of LeNet from slides if time}
\begin{figure}[H]
\includegraphics[scale=0.50]{LeNet}
\centering
\captionsetup{width=0.90\textwidth}
\caption{Representation of the LeNet Neural Network model architecture including convolutional layers and pooling (subsampling) layers\cite{726791}}
\label{fig:LeNet}
\end{figure}
\section{Method} \label{sec:method}