notxia/unibo-ai-notes
1
0
Fork 0
mirror of https://github.com/NotXia/unibo-ai-notes.git synced 2025-12-16 03:21:48 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fix typos <noupdate>

Browse Source
This commit is contained in:
Tian Cheng (Riccardo) Xia
2024-06-23 10:03:26 +02:00
parent 0f10df50fb
commit d7b3402116
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/year1/image-processing-and-computer-vision/module2/sections/_architectures.tex
View File

@ -683,7 +683,7 @@ It has the following properties:
Variant of residual blocks that uses more layers with approximately the same number of parameters and FLOPs of the standard residual block. Variant of residual blocks that uses more layers with approximately the same number of parameters and FLOPs of the standard residual block.
Instead of using two $3 \times 3$ convolutions, bottleneck residual network has the following structure: Instead of using two $3 \times 3$ convolutions, bottleneck residual network has the following structure:
\begin{itemize} \begin{itemize}
\item $1 \times 1$ convolution to compress the channels of the input by an order of $4$ (and the spatial dimension by $2$ if it is the first block of a stage, as in the normal ResNet). \item $1 \times 1$ convolution to compress the channels of the input by an order of $4$ (and the spatial dimension by $2$ if it is the first block of a stage, as in normal ResNet).
\item $3 \times 3$ convolution. \item $3 \times 3$ convolution.
\item $1 \times 1$ convolution to match the shape of the skip connection. \item $1 \times 1$ convolution to match the shape of the skip connection.
\end{itemize} \end{itemize}

2
src/year1/image-processing-and-computer-vision/module2/sections/_classification.tex
View File

@ -271,7 +271,7 @@ where the $\texttt{logits} \in \mathbb{R}^{c}$ vector contains a score for each
The prediction is obtained as the index of the maximum score. The prediction is obtained as the index of the maximum score.
\begin{remark} \begin{remark}
Predicting directly the integer encoded classes is not ideal as it would give a (probably) inexistent semantic ordering Directly predicting the integer encoded classes is not ideal as it would give a (probably) inexistent semantic ordering
(e.g. if $2$ encodes bird and $3$ encodes cat, $2.5$ should not mean half bird and half cat). (e.g. if $2$ encodes bird and $3$ encodes cat, $2.5$ should not mean half bird and half cat).
\end{remark} \end{remark}

2
src/year1/image-processing-and-computer-vision/module2/sections/_image_formation.tex
View File

@ -7,7 +7,7 @@
\item[Camera reference frame (CRF)] \marginnote{Camera reference frame (CRF)} \item[Camera reference frame (CRF)] \marginnote{Camera reference frame (CRF)}
Coordinate system $(X_C, Y_C, Z_C)$ that characterizes a camera. Coordinate system $(X_C, Y_C, Z_C)$ that characterizes a camera.
\item[Image reference frame (IRF)] \marginnote{Image reference frame} \item[Image reference frame (IRF)] \marginnote{Image reference frame (IRF)}
Coordinate system $(U, V)$ of the image. Coordinate system $(U, V)$ of the image.
They are obtained as a perspective projection of CRF coordinates as: They are obtained as a perspective projection of CRF coordinates as:
\[ \[