This commit is contained in:
parent
31f9d64b47
commit
4b48afaffb
@ -78,12 +78,12 @@
|
||||
\vspace*{\fill}
|
||||
\section*{Acknowledgements}
|
||||
I would like to take this opportunity to thank my supervisor Rizwan Asghar that helped me from the
|
||||
start of the project till the end.
|
||||
I am honestly thankful to him for sharing his honest and educational views on a number of issues related
|
||||
start of the project until the end.
|
||||
I am honestly thankful to him for sharing his honest and educational views on several issues related
|
||||
to this report.
|
||||
Additionally, I would like to thank my parents and friends for their continued support and
|
||||
encouragement from the first day of the university. They always have been motivating, inspiring and
|
||||
helping me to achieve my life goals
|
||||
encouragement from the first day of the university. They have always been motivating, inspiring and
|
||||
helping me to achieve my life goals.
|
||||
\vspace*{\fill}
|
||||
\end{center}
|
||||
\newpage
|
||||
@ -91,9 +91,9 @@
|
||||
\begin{center}
|
||||
\vspace*{\fill}
|
||||
\section*{Abstract}
|
||||
Currently there are few automatic image calssificication platforms.
|
||||
Currently there are few automatic image classification platforms.
|
||||
This project hopes to work as a guide for the creating a new image automatic classification platform.
|
||||
The project goes through all the requirmenets for creating a platform service as well as all of its needs.
|
||||
The project goes through all the requirements for creating a platform service, and all of its needs.
|
||||
\vspace*{\fill}
|
||||
\end{center}
|
||||
\newpage
|
||||
@ -178,7 +178,7 @@
|
||||
|
||||
These models can be used in two ways in the system, they can be used to generate the models via transfer learning and by using the model structure as a basis to generate a complete new model.
|
||||
|
||||
\subsection{Current Known Models}
|
||||
\subsection{Well-known models}
|
||||
% TODO compare the models
|
||||
|
||||
This section will compare the different models that did well in the image net challenge.
|
||||
@ -197,7 +197,7 @@
|
||||
|
||||
% EfficientNet
|
||||
EfficientNet \cite{efficient-net} is a deep convolution neural network that was able to achieve $84.3\%$ top-1 accuracy while ``$8.4x$ smaller and $6.1x$ faster on inference than the best existing ConvNet''. EfficientNets\footnote{the family of models that use the thecniques that described in \cite{efficient-net}} are models that instead of the of just increasing the depth or the width of the model, we increase all the parameters at the same time by a constant value. By not scaling only depth EfficientNets can acquire more information about the images specially the image size is considered.
|
||||
To test their results the EfficientNet team created a baseline model which as a building block used the mobile inverted bottleneck MBConv \cite{inverted-bottleneck-mobilenet}. The baseline model was then scaled using the compound method which resulted in better top-1 and top-5 accuracy.
|
||||
To test their results, the EfficientNet team created a baseline model which as a building block used the mobile inverted bottleneck MBConv \cite{inverted-bottleneck-mobilenet}. The baseline model was then scaled using the compound method which resulted in better top-1 and top-5 accuracy.
|
||||
While EfficientNets are smaller than their non-EfficientNet counterparts they are more computational intensive, a ResNet-50 scaled using the EfficientNet compound scaling method is $3\%$ more computational intensive than a ResNet-50 scaled using only depth while only improving the top-1 accuracy by $0.7\%$, and as the model will be trained and run multiple times decreasing the computational cost might be a better overall target for sustainability then being able to offer higher accuracies.
|
||||
Even though scaling using the EfficientNet compound method might not yield the best results using some EfficientNets what were optimized by the team to would be optimal, for example, EfficientNet-B1 is both small and efficient while still obtaining $79.1\%$ top-1 accuracy in ImageNet, and realistically the datasets that this system will process will be smaller and more scope specific than ImageNet.
|
||||
|
||||
@ -229,8 +229,13 @@
|
||||
\item{Model Management}
|
||||
\end{itemize}
|
||||
|
||||
\subsection{Resourses}
|
||||
The system needs manage what server are available to it in various cases
|
||||
\subsection{Overall structure}
|
||||
The system needs to have some level of distributivity, this requirement exists because the expensive nature of machine learning training.
|
||||
It would be unwise to perform machine learning training on the same machine that the main web server is running, as it would starve that server of resources.
|
||||
|
||||
\subsection{Resources}
|
||||
The system has to manage what servers are available to do machine learning tasks.
|
||||
The system needs to be aware and manage all GPU servers, servers that have GPUs available, and run the possible models.
|
||||
|
||||
\subsection{Web platform}
|
||||
The web app is where users manage models, and data. The user will access the web app and configure the model, and manage that data set.
|
||||
@ -248,13 +253,13 @@
|
||||
For example, when training, send training jobs to the same server to prevent the server from having to reload the data again.
|
||||
|
||||
\subsection{Dataset Management}
|
||||
Without data the system can not train models. And management of data is important as this data might contain some data that is private.
|
||||
Such as biometrics the system will need to be able to safely handle this data.
|
||||
Without data, the system cannot train models. And management of data is important as this data might contain some private data.
|
||||
Such as biometrics, the system will need to be able to safely handle this data.
|
||||
The system will also have to decide when to clear data, since storage space is also a resource that the system needs to manage.
|
||||
|
||||
\subsection{Model Management}
|
||||
Once the model has been created the system needs to keep track of the model, as well as the actual acuracy of the model.
|
||||
It needs to keep track of the how much it the model used so it can distribute the load from in different gpu servers.
|
||||
Once the model has been created, the system has to keep track of the model, as well as the actual accuracy of the model.
|
||||
It has to keep track of how much the model used so it can distribute the load from in different GPU servers.
|
||||
|
||||
|
||||
\pagebreak
|
||||
@ -377,5 +382,3 @@
|
||||
|
||||
% TODO add my job title
|
||||
\end{document}
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user