mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 23:07:09 +01:00
Krzysztof kuhy Rudnicki
ffa5dad02a
The 250-line cap applies to prose too, and the reports were the worst
offenders -- ENUME's projectA.tex alone was 1,876 lines. Each is now a
preamble plus one \input{} per section, which is how a long LaTeX document is
normally organised; not one byte of prose was rewritten.
"The PDF is unchanged" is checked by a script rather than by eye, because
hashing the PDF cannot work: pdflatex stamps a /CreationDate and an /ID into
every build, so two runs of the SAME source already differ. tex_fingerprint.sh
compares what a reader sees instead -- page count plus a hash of the extracted
text -- and it is stable across rebuilds of untouched sources, which is the
property that makes it usable as a gate.
It earned its keep immediately. Both ECOTE reports quote an example LaTeX
document inside an lstlisting block, so \end{document} appears in the middle
of the file; splitting on the FIRST one stranded everything after it. Same
page count, different text, caught automatically. EOPSY lab3 exposed a second
bug: a \section{} title that runs onto the next line.
Result: 19 .tex over the cap -> 1. The survivor,
ELAC/.../03-building-nfa-...tex, is 418 lines of consecutive tikz figures
with no subsection to split on and needs a hand-placed boundary.
Verified: 29 splits across two passes (section, then subsection for the
pieces still over), every one reporting `unchanged` from
scripts/tex_fingerprint.sh --check.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
48 lines
2.0 KiB
TeX
48 lines
2.0 KiB
TeX
\section{Implementation}
|
|
Program can be ran by installing python, moving to project directory and issuing command:
|
|
\begin{lstlisting}[language=bash]
|
|
python main.py
|
|
\end{lstlisting}
|
|
Results will be displayed on three 2d scatter plots. \\
|
|
Plots Title is filled with parameters used abbreviated for space sake \\
|
|
Abbreviatons meaning:
|
|
\begin{itemize}
|
|
\item lr - Learning Rate
|
|
\item bs - Batch Size
|
|
\item hl - Number of Hidden Layers
|
|
\item w - Width
|
|
\item Adam or SGD or SGD\_Momentum - Optimizer type
|
|
\end{itemize}
|
|
Plot types:
|
|
\begin{itemize}
|
|
\item Loss value for learning step
|
|
\item Train Accuracy for epoch
|
|
\item Validation Accuracy for epoch
|
|
\end{itemize}
|
|
|
|
\begin{figure}[H]
|
|
\caption{Exemplary plot of loss for learning Step \\ lr0.001-bs64-hl1-w128-Adam }
|
|
\includegraphics[width=\textwidth]{testsResults/loss/def.png}
|
|
\centering
|
|
\end{figure}
|
|
\begin{figure}[H]
|
|
\caption{Exemplary plot of Validation Accuracy for epoch \\ lr0.001-bs64-hl1-w128-Adam }
|
|
\includegraphics[width=\textwidth]{testsResults/validationAccuracy/validationAccuracy-lr0.001-bs64-hl2-w64-Adam.png}
|
|
\centering
|
|
\end{figure}
|
|
\begin{figure}[H]
|
|
\caption{Exemplary plot of Train Accuracy for epoch \\ lr0.001-bs64-hl1-w128-Adam }
|
|
\includegraphics[width=\textwidth]{testsResults/trainAccuracy/trainAccuracy-lr0.001-bs64-hl2-w64-Adam.png}
|
|
\centering
|
|
\end{figure}
|
|
Results will be displayed and saved in the same folder as code directory for further inspection, with file name containing information about input parameters \\
|
|
Additionaly speed it took for neural network to run will be saved to results.txt along with what parameters were used \\
|
|
We decided to run 19 tests in total:
|
|
\begin{enumerate}
|
|
\item learning rate [0.1, 0.01, 0.001] (3 tests)
|
|
\item mini-batch size [1, 64, 128, 256] (4 tests)
|
|
\item number of hidden layers [0, 1, 2, 3] (4 tests)
|
|
\item width [64, 128, 256, 512, 1024] (5 tests)
|
|
\item optimizer type [SGD, SGD\_Momentum, Adam] (3 tests)
|
|
\end{enumerate}
|