Compare commits

...

90 Commits

Author SHA1 Message Date
10ca099809 finished report I think
All checks were successful
continuous-integration/drone/push Build is passing
2024-05-15 05:22:33 +01:00
50bb49f822 starting adding images
All checks were successful
continuous-integration/drone/push Build is passing
2024-05-10 02:12:02 +01:00
a1f7365c3f more work on report
All checks were successful
continuous-integration/drone/push Build is passing
2024-05-02 01:19:25 +01:00
b5f61c5e20 more work done on the report 2024-04-29 20:59:12 +01:00
15d4de3b45 chore: updated report
All checks were successful
continuous-integration/drone/push Build is passing
2024-04-28 14:06:02 +01:00
5fa89aec1d Started working on results
All checks were successful
continuous-integration/drone/push Build is passing
2024-04-24 19:50:53 +01:00
46cc4e4a06 fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2024-04-24 14:38:47 +01:00
65a0d95ecb Added ethical and legal issues
Some checks failed
continuous-integration/drone/push Build is failing
2024-04-24 14:32:47 +01:00
4e33430550 more work on introduction
All checks were successful
continuous-integration/drone/push Build is passing
2024-04-24 11:38:42 +01:00
d86c4a7ba7 more work on the repport
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-15 14:08:41 +00:00
b43abe74d9 more work on report
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-14 17:23:49 +00:00
80012a14cd more work on report
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-13 22:26:48 +00:00
e59cdd33e6 chore: more work on the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-12 11:15:05 +00:00
a02acd9b4f chore: more work on the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-11 23:56:43 +00:00
db08e53a8f chore: more work on the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-11 12:53:30 +00:00
73dc08a782 chore: fix two sidepaper
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-10 00:13:00 +00:00
479d7b6f39 chore: added some diagrams
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-10 00:09:12 +00:00
18571cbc5e update
All checks were successful
continuous-integration/drone/push Build is passing
2024-03-04 21:23:35 +00:00
3a6220eaf4 chore: more work done
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-29 15:38:41 +00:00
4b48afaffb chore: more work done
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-28 22:51:31 +00:00
31f9d64b47 chore: fixed the not advancing on the discounts register page
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-28 15:28:21 +00:00
6fae1aaa38 chore: written more of the report
Some checks failed
continuous-integration/drone/push Build is failing
2024-02-28 15:23:47 +00:00
99a2b8ce77 center some pages
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-27 21:54:14 +00:00
e19875c241 center some pages
Some checks failed
continuous-integration/drone/push Build is failing
2024-02-27 21:49:27 +00:00
87fab390c7 chore: reformated and updated diagram
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-27 21:41:04 +00:00
4721c3d305 added image on first page
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-27 16:25:49 +00:00
4a2a45abb7 add more sections
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-27 10:27:47 +00:00
7505dc25e8 Merge branch 'main' of git.andr3h3nriqu3s.com:andr3/fyp-report
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-27 10:09:49 +00:00
8d6ffce44d chore: more work on report 2024-02-27 10:05:17 +00:00
b2c5d29d2b Added a bit more to the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-16 14:08:50 +00:00
d65dfcda69 chore: some work on the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-15 16:48:09 +00:00
f5080ddcc0 moved the images to the appendix
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-01 12:39:05 +00:00
0202c06afe fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-01 12:01:20 +00:00
ee2dba33af fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-01 11:53:38 +00:00
ad41ce2b1d fix last commit
Some checks failed
continuous-integration/drone/push Build is failing
2024-02-01 11:44:01 +00:00
d83e015d46 added meeting documentation
Some checks failed
continuous-integration/drone/push Build is failing
2024-02-01 11:32:27 +00:00
7323be8dbc added work table
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-01 11:05:01 +00:00
16aafe65b8 wrote more on efficientnet
All checks were successful
continuous-integration/drone/push Build is passing
2024-02-01 10:05:34 +00:00
e0d93ea366 started: working on the efficient net literature review
All checks were successful
continuous-integration/drone/push Build is passing
2024-01-25 14:17:13 +00:00
2223b3e302 feat: talked about resnet
All checks were successful
continuous-integration/drone/push Build is passing
2024-01-24 19:51:41 +00:00
4c5320b9e8 chore: fixed some spelling mistakes
All checks were successful
continuous-integration/drone/push Build is passing
2024-01-23 18:21:12 +00:00
4547229dfc fix: some fixes to the report
All checks were successful
continuous-integration/drone/push Build is passing
2024-01-04 11:05:25 +00:00
3834b7b289 fix: some errors on the fyp report
All checks were successful
continuous-integration/drone/push Build is passing
2024-01-03 14:55:38 +00:00
f3d8b02114 Update report
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-28 14:04:50 +00:00
a1143f7e3e More work on the paper
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-25 11:20:58 +00:00
94ac62fefa More work on the literature review
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-23 14:35:46 +00:00
f50c55b748 More work on the literature review
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-22 17:15:46 +00:00
61fad3a5c4 Fix citing types
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-20 17:15:11 +00:00
11b956894c Talking about the google vision
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-20 16:07:27 +00:00
186d515a21 Updated amazon
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-18 21:33:53 +00:00
3afd2844b2 Fix main.bib
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-18 20:32:09 +00:00
6e467e6e73 Started writting about amazon rekognition
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-18 20:29:08 +00:00
6ae1fb7b3c Change diagram generator
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 11:33:44 +00:00
d05d3eac98 Change report.tex
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 11:31:37 +00:00
7a6aabbf98 Modified diagrams so they are more visible
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 11:27:51 +00:00
6d91bec4c2 try to make the image fit
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 10:43:30 +00:00
0df1f3f3fb try as images from d2
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 10:41:14 +00:00
d9dc7ff43b try as images from d2
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-04 10:40:25 +00:00
ac5935e578 try as images
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 10:39:00 +00:00
8eed92b968 fix diagram
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 10:33:24 +00:00
5162d41bcc fix diagram
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-04 10:30:47 +00:00
97cde3e72b fix diagram
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-04 10:27:57 +00:00
d133535009 fix ci
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-04 10:26:28 +00:00
5e37f62771 fix svg
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-04 10:25:55 +00:00
7ab1abc783 fix svg
All checks were successful
continuous-integration/drone/push Build is passing
2023-12-01 14:20:34 +00:00
33803262b2 Added svg
Some checks failed
continuous-integration/drone/push Build is failing
2023-12-01 14:06:42 +00:00
07267ae9d3 fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-30 14:29:06 +00:00
fb5fa39e63 removed unnacenary parts and updaged generation
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-30 14:28:10 +00:00
74ff0ce10f added report to release
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-30 14:03:17 +00:00
bc1aeca3da added report to generation
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-30 14:02:22 +00:00
eea7e0cdb2 started rewriting the thecnical overview
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-30 12:56:29 +00:00
0a0cd29a3d added keep for images for report
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-30 11:49:53 +00:00
133b793f8c fix ci
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-30 11:48:52 +00:00
8bfecc95d9 try adding diagrams
Some checks reported errors
continuous-integration/drone/push Build encountered an error
2023-11-30 11:47:09 +00:00
9c5e178e05 Updated drone ci 2023-11-05 13:16:57 +00:00
884b8e42f9 Updated drone ci
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-05 13:16:39 +00:00
3f5831d0ec Updated drone ci 2023-11-05 13:15:35 +00:00
4f05bad1f0 Finished project synopisis
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-05 13:15:00 +00:00
79272112c8 Updated project synoposis
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-05 13:09:59 +00:00
90d4b0e4bb update project synopsis
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-02 13:11:40 +00:00
a683485b70 Fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-01 17:19:46 +00:00
d9c06cdf0e worked on the work plan
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-01 17:09:50 +00:00
7075234b35 fix last commit
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-01 16:20:44 +00:00
c38f32b37d fix last commit
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-01 16:19:13 +00:00
1575fa8756 Work done literature review
Some checks failed
continuous-integration/drone/push Build is failing
2023-11-01 16:15:47 +00:00
b084e3c249 Updated the introduction
All checks were successful
continuous-integration/drone/push Build is passing
2023-11-01 14:05:38 +00:00
0e22cb362b update project synopsis
All checks were successful
continuous-integration/drone/push Build is passing
2023-10-26 09:56:52 +01:00
8be295378e fix ci
All checks were successful
continuous-integration/drone/push Build is passing
2023-10-22 17:29:38 +01:00
d7b6d25171 fixed last commit
Some checks failed
continuous-integration/drone/push Build is failing
2023-10-20 15:31:04 +01:00
45bdff9109 started writing project synopsis
Some checks failed
continuous-integration/drone/push Build is failing
2023-10-20 15:24:08 +01:00
54 changed files with 6556 additions and 333 deletions

View File

@ -8,7 +8,16 @@ steps:
commands:
- bash linting.sh
- name: Build UPDS-1
- name: Build diagrams
commands:
- cd diagrams
- ls | grep d2 | sed 's/.d2//' | xargs -I{} d2 --layout=elk {}.d2 {}.svg
- ls | grep d2 | sed 's/.d2//' | xargs -I{} d2 --layout=elk {}.d2 {}.png
- mv *.svg '../report'
- mv *.png '../images for report'
- cd -
- name: Build Project synopsis
commands:
- cd projectsynopsis
- pdflatex project-synopsis.tex
@ -18,17 +27,27 @@ steps:
- pdflatex project-synopsis.tex
- cd -
# - name: Build Report
# commands:
# - cd report
# - cp ../upds-1/UPDS-content.tex UPDS-1-content.tex
# - cp ../upds-2/UPDS-content.tex UPDS-2-content.tex
# - pdflatex report.tex
# # Prepare bib
# - /usr/bin/vendor_perl/biber report
# # Compile twice for the table of contents and for bib text
# - pdflatex report.tex
# - cd -
- name: Build Report
commands:
- cd report
- pdflatex --shell-escape report.tex
# Prepare bib
- /usr/bin/vendor_perl/biber report
# Compile twice for the table of contents and for bib text
- pdflatex --shell-escape report.tex
- pdflatex --shell-escape report.tex
- cd -
- name: Build Meeting
commands:
- cd meeting
- pdflatex --shell-escape meeting.tex
# Prepare bib
- /usr/bin/vendor_perl/biber meeting
# Compile twice for the table of contents and for bib text
- pdflatex --shell-escape meeting.tex
- pdflatex --shell-escape meeting.tex
- cd -
#
# - name: Generate text
# commands:
@ -43,7 +62,18 @@ steps:
- tea login add --url https://git.andr3h3nriqu3s.com --token "$TOKEN"
- tea r rm -y current || echo "Release not found"
# - tea r c --title "Latest Report" --asset report/report.pdf --asset upds-1/UPDS12-1.pdf --asset upds-2/UPDS12-2.pdf --asset results.txt --asset poster/poster.pdf current
- tea r c --title "Latest Report" --asset projectsynopsis/project-synopsis.pdf current
- tea r c --title "Latest Report" --asset projectsynopsis/project-synopsis.pdf --asset report/report.pdf current
- name: gitea_release meeting
environment:
TOKEN:
from_secret: token
commands:
# no need to login again
# - tea login add --url https://git.andr3h3nriqu3s.com --token "$TOKEN"
- tea r rm -y meeting1 || echo "Release not found"
# - tea r c --title "Latest Report" --asset report/report.pdf --asset upds-1/UPDS12-1.pdf --asset upds-2/UPDS12-2.pdf --asset results.txt --asset poster/poster.pdf current
- tea r c --title "Meeting" --asset meeting/meeting.pdf meeting1
- name: Remove current on failure
environment:

1
diagrams/.gitignore vendored Normal file
View File

@ -0,0 +1 @@
*.svg

View File

@ -0,0 +1,131 @@
indata: "Input data" {
shape: cylinder
}
model-generation: Model Generation {
hidden-layers-generator: Hidden Layers Model Generator
hidden-layers-generator<->generator: Request/Accept Model
head-generator: Head Models Generator {
_.head-generator->model1: Create
_.head-generator->model2: Create
_.head-generator->modeln: Create
model1
model2
modeln: "Model..."
model1<->_.generator: Request/Accept Model
model2<->_.generator: Request/Accept Model
modeln<->_.generator: Request/Accept Model
model1->_.head-generator: Accept Model
model2->_.head-generator: Accept Model
modeln->_.head-generator: Accept Model
}
generator: Generator {
_.generator->model-search: Start
model-search: Model Search {
database-search: Database search
autoML: Automl
}
model-search->model-training: Propose model
model-training->model-search: Reject model and request new one
model-training: Model Traning {
_.model-training->node: Start Training
node: Node
_.model-training<-node: End Training
}
model-training->_.generator: Accept Model
}
}
node-manager: Node Manager {
node1
node2
noden: "node..."
node-manager->node1: Manage
node-manager->node2: Manage
node-manager->noden: Manage
}
model-generation.generator.model-training.node<->node-manager: Request/Gives node to train
model-database: Model database {
shape: cylinder
}
model-runner: Model Runner {
node: Node
headless: Obatin Headless Model
_.model-runner->headless: Start
headless<->_.model-database: Request/Get Model
headless<->node: Run/Result
headless->model-search: Results
model-search: Model Search {
}
model-search<->_.model-database: Request Head Models
head-model: Head Model
model-search->head-model: Obtain
head-model<->node: Run/Result
head-model->model-search: Unsatatisfary results, request new model
head-model->results-cache: Unsatatisfary results, save results
results-cache: Results Cache
combine: Combine
head-model->combine: Satisfary Results/No more options
combine<-results-cache: Cached results Results
combine->_.model-runner: Results
}
model-runner.node<->node-manager: Request/Gives node to run model
User.shape: Person
User->indata: Uploads data
User->model-generation: Requests Model
User->model-database: Manages Models
User->model-runner: Request image for classification
model-runner->User: Give class of image
model-generation.generator <-> indata: Requests Data
model-generation->model-generation.hidden-layers-generator: Start
model-generation.hidden-layers-generator->model-generation.head-generator: Strip head and give base model to Head Generator
model-generation.head-generator->model-database: Save hidden layers model and heads

View File

@ -0,0 +1,71 @@
model-generation: Model Generation {
hidden-layers-generator: Hidden Layers Model Generator
hidden-layers-generator<->generator: Request/Accept Model
head-generator: Head Models Generator {
_.head-generator->model1: Create
_.head-generator->model2: Create
_.head-generator->modeln: Create
model1
model2
modeln: "Model..."
model1<->_.generator: Request/Accept Model
model2<->_.generator: Request/Accept Model
modeln<->_.generator: Request/Accept Model
model1->_.head-generator: Accept Model
model2->_.head-generator: Accept Model
modeln->_.head-generator: Accept Model
}
generator: Generator {
_.generator->model-search: Start
model-search: Model Search {
database-search: Database search
autoML: Automl
}
model-search->model-training: Propose model
model-training->model-search: Reject model and request new one
model-training: Model Traning {
_.model-training->node: Start Training
node: Node
_.model-training<-node: End Training
}
model-training->_.generator: Accept Model
}
}
User.shape: Person
User->model-generation: Requests Model
model-generation.generator <-> indata: Requests Data
model-generation->model-generation.hidden-layers-generator: Start
model-generation.hidden-layers-generator->model-generation.head-generator: Strip head and give base model to Head Generator
model-generation.head-generator->model-database: Save hidden layers model and heads
indata: "Input data" {
shape: cylinder
}
model-database: "Model Database" {
shape: cylinder
}

View File

@ -0,0 +1,70 @@
indata: "Input data" {
shape: cylinder
}
node-manager: Node Manager {
node1
node2
noden: "node..."
node-manager->node1: Manage
node-manager->node2: Manage
node-manager->noden: Manage
}
model-database: Model database {
shape: cylinder
}
model-runner: Model Runner {
node: Node
headless: Obatin Headless Model
_.model-runner->headless: Start
headless<->_.model-database: Request/Get Model
headless<->node: Run/Result
headless->model-search: Results
model-search: Model Search {}
model-search<->_.model-database: Request Head Models
head-model: Head Model
model-search->head-model: Obtain
head-model<->node: Run/Result
head-model->model-search: Unsatatisfary results, request new model
head-model->results-cache: Unsatatisfary results, save results
results-cache: Results Cache
combine: Combine
head-model->combine: Satisfary Results/No more options
combine<-results-cache: Cached results Results
combine->_.model-runner: Results
}
model-runner.node<->node-manager: Request/Gives node to run model
User.shape: Person
User->indata: Uploads data
User->model-database: Manages Models
User->model-runner: Request image for classification
model-runner->User: Give class of image
model-generation: Model Generation {}
User->model-generation: Requests Model
model-generation <-> indata: Requests Data
model-generation<->node-manager: Request/Gives node to train

View File

@ -0,0 +1,27 @@
direction: right
User: "Authenticated User" {
shape: Person
}
ModelCreation: "Model Creation"
ImageUpload: "Image Upload"
TrainModel: "Train Model"
EvaluateModel: "Infer an Image"
Expand: "Expand a model"
User->ModelCreation: "User creates the model"
ModelCreation->ImageUpload
User->ImageUpload: "User uploads Images"
ImageUpload->TrainModel
User->TrainModel: "Requests the training of the model"
TrainModel->TrainModel: Failed to train
TrainModel->EvaluateModel
User->EvaluateModel: "Request class for an image"
EvaluateModel->Expand
User->Expand: "User uploads new images"
Expand->TrainModel

23
diagrams/models_flow.d2 Normal file
View File

@ -0,0 +1,23 @@
direction: right
User: "Authenticated User" {
shape: Person
}
ModelCreation: "Model Creation"
ImageUpload: "Image Upload"
TrainModel: "Train Model"
EvaluateModel: "Infer an Image"
User->ModelCreation: "User creates the model"
ModelCreation->ImageUpload
User->ImageUpload: "User uploads Images"
ImageUpload->TrainModel
User->TrainModel: "Requests the training of the model"
TrainModel->TrainModel: Failed to train
TrainModel->EvaluateModel
User->EvaluateModel: "Request class for an image"

View File

@ -0,0 +1,25 @@
direction: right
User.shape: Person
User->Login: "User Signs In"
User->Register: "User Registers"
App: "Web APP"
Login->App: "User uses the App"
Register->App: "User uses the App"
Token: "Generate API Token"
Login->Token
Register->Token
Server: "User' Servers" {
shape: Cloud
}
Token->Server: "User Provides Token"
User->Server: "User controls Server"
Server->API: "Users' Servers Interact with API"

69
diagrams/simple_models.d2 Normal file
View File

@ -0,0 +1,69 @@
indata: "Input data" {
shape: cylinder
}
model_generation: Model Generation {
_.generator->model_search: Start
model_search: Model Search {
database_search: Database search
autoML: Automl
}
model_search->model_training: Propose model
model_training->model_search: Reject model and request new one
model_training: Model Traning {
_.model_training->node: Start Training
node: Node
_.model_training<-node: End Training
}
model_training->_.generator: Accept Model
}
node_manager: Node_Manager {
node1
node2
noden: "node..."
node_manager->node1: Manage
node_manager->node2: Manage
node_manager->noden: Manage
}
model_generation.generator.model_training.node<->node_manager: Request/Gives node to train
model_database: Model database {
shape: cylinder
}
model_runner: Model Runner {
node: Node
model: Model
model<->_.model_database: Request/Get Model
model<->node: Run/Result
node->_.model_runner: Results
}
model_runner.node<->node_manager: Request/Gives node to run model
User.shape: Person
User->indata: Uploads data
User->model_generation: Requests Model
User->model_database: Manages Models
User->model_runner: Request image for classification
model_runner->User: Give class of image
model_generation <-> indata: Requests Data

View File

@ -0,0 +1,33 @@
User.shape: Person
Server: "User Server" {
shape: Cloud
}
Proxy.shape: Hexagon
Api: "API Server" { }
Web: "Web Server" { }
Runner: "Model Runner" {
style.multiple: true
}
Train: "Model Trainer" {
style.multiple: true
}
database: "Database" {
shape: cylinder
}
User<->Proxy
Server<->Proxy
Proxy<->Api
Proxy<->Web
Api<->Database
Api<->Runner
Api<->Train
Database<->Runner
Database<->Train

View File

@ -0,0 +1,53 @@
database: "Database" {
shape: cylinder
}
Model: "Model Data" {
shape: cylinder
style.multiple: true
}
Dataset: "Dataset Data" {
shape: cylinder
style.multiple: true
}
Api: "API Server" { }
Runner: "Model Runner" {
style.multiple: true
}
Train: "Model Trainer" {
style.multiple: true
}
static_server: "Web App Static Server" { }
User.shape: Person
Server.shape: Cloud
static_server->User: Send control webpage
User->Api: Manage Models, Accounts, Permissions
Server->Api: Request processing of images
Api->database
Api->Model: Manage Models
Api->Dataset: Manage Datasets
Api<->Runner: Run the model
Api<->Train: Train the model
Model->Runner: Load Models
Dataset->Runner: Load Datasets
Runner->Api: Update status of task
Train<->Model: Load and Save Models
Train->Dataset: Load Datasets
Model->Train: Load Models
Dataset->Train: Load Datasets
Train->Model: Save Models
Train->Api: Update status of task

0
images for report/.keep Normal file
View File

Binary file not shown.

After

Width:  |  Height:  |  Size: 38 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 40 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 155 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1013 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 949 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 174 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 75 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 101 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 286 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 46 KiB

BIN
images for report/max.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 31 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 45 KiB

BIN
images for report/mean.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 30 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 148 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 276 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 158 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 263 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 65 KiB

BIN
images for report/stl_1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 12 KiB

BIN
images for report/stl_2.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 21 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 42 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 179 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 85 KiB

607
main.bib
View File

@ -1,289 +1,394 @@
@misc{confluence,
author = {Atlassian},
title = {{C}onfluence | {Y}our {R}emote-{F}riendly {T}eam {W}orkspace | {A}tlassian --- atlassian.com},
howpublished = {\url{https://www.atlassian.com/software/confluence}},
year = {},
note = {(Accessed 26-Jun-2023)},
@online{google-vision-api,
author ={Google},
title ={Vision {AI} | Google Cloud},
year ={2023},
url ={https://cloud.google.com/vision?hl=en}
}
@misc{jira,
author = {Atlassian},
title = {{J}ira | {I}ssue \& {P}roject {T}racking {S}oftware | {A}tlassian --- atlassian.com},
howpublished = {\url{https://www.atlassian.com/software/jira}},
year = {},
note = {(Accessed 26-Jun-2023)},
@misc{amazon-rekognition,
title = {{What Is Amazon Rekognition? (1:42)}},
journal = {Amazon Web Services, Inc},
year = {2023},
month = dec,
note = {[Online; accessed 18. Dec. 2023]},
url = {https://aws.amazon.com/rekognition}
}
@misc{ldap,
series = {Request for Comments},
number = 5058,
howpublished = {RFC 5058},
publisher = {RFC Editor},
doi = {10.17487/RFC5058},
url = {https://www.rfc-editor.org/info/rfc5058},
author = {Dirk Ooms and Nancy Feldman and Yuji Imai and Wim P. Livens and Dr. Richard H. Boivie},
title = {{Explicit Multicast (Xcast) Concepts and Options}},
pagetotal = 35,
year = 2007,
month = nov,
abstract = {While traditional IP multicast schemes (RFC 1112) are scalable for very large multicast groups, they have scalability issues with a very large number of distinct multicast groups. This document describes Xcast (Explicit Multi-unicast), a new multicast scheme with complementary scaling properties: Xcast supports a very large number of small multicast sessions. Xcast achieves this by explicitly encoding the list of destinations in the data packets, instead of using a multicast group address. This document discusses Xcast concepts and options in several areas; it does not provide a complete technical specification. This memo defines an Experimental Protocol for the Internet community.},
@article{lecun1989handwritten,
title={Handwritten digit recognition with a back-propagation network},
author={LeCun, Yann and Boser, Bernhard and Denker, John and Henderson, Donnie and Howard, Richard and Hubbard, Wayne and Jackel, Lawrence},
journal={Advances in neural information processing systems},
volume={2},
year={1989}
}
@misc{sky,
author = {},
title = {{S}ky {G}roup - {E}uropes leading direct-to-consumer media and entertainment company --- skygroup.sky},
howpublished = {\url{https://www.skygroup.sky}},
year = {},
note = {(Accessed 26-Jun-2023)},
@article{krizhevsky2012imagenet,
title={Imagenet classification with deep convolutional neural networks},
author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
journal={Advances in neural information processing systems},
volume={25},
year={2012}
}
@misc{gitlab,
author = {},
title = {The DevSecOps Platform | GitLab},
howpublished = {\url{https://about.gitlab.com/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@article{fukushima1980neocognitron,
title={Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position},
author={Fukushima, Kunihiko},
journal={Biological cybernetics},
volume={36},
number={4},
pages={193--202},
year={1980},
publisher={Springer}
}
@misc{jenkins,
author = {},
title = {Jenkins},
howpublished = {\url{https://www.jenkins.io/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{tensorflow2015-whitepaper,
title={ {TensorFlow}: Large-Scale Machine Learning on Heterogeneous Systems},
url={https://www.tensorflow.org/},
note={Software available from tensorflow.org},
author={
Mart\'{i}n~Abadi and
Ashish~Agarwal and
Paul~Barham and
Eugene~Brevdo and
Zhifeng~Chen and
Craig~Citro and
Greg~S.~Corrado and
Andy~Davis and
Jeffrey~Dean and
Matthieu~Devin and
Sanjay~Ghemawat and
Ian~Goodfellow and
Andrew~Harp and
Geoffrey~Irving and
Michael~Isard and
Yangqing Jia and
Rafal~Jozefowicz and
Lukasz~Kaiser and
Manjunath~Kudlur and
Josh~Levenberg and
Dandelion~Man\'{e} and
Rajat~Monga and
Sherry~Moore and
Derek~Murray and
Chris~Olah and
Mike~Schuster and
Jonathon~Shlens and
Benoit~Steiner and
Ilya~Sutskever and
Kunal~Talwar and
Paul~Tucker and
Vincent~Vanhoucke and
Vijay~Vasudevan and
Fernanda~Vi\'{e}gas and
Oriol~Vinyals and
Pete~Warden and
Martin~Wattenberg and
Martin~Wicke and
Yuan~Yu and
Xiaoqiang~Zheng},
year={2015},
}
@misc{ansible,
author = {},
title = {Ansible is Simple IT Automation},
howpublished = {\url{https://www.ansible.com/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{chollet2015keras,
title={Keras},
author={Chollet, Fran\c{c}ois and others},
year={2015},
howpublished={\url{https://keras.io}},
}
@misc{htmx,
title = {{{$<$}/{$>$} htmx - high power tools for html}},
year = {2023},
month = nov,
note = {[Online; accessed 1. Nov. 2023]},
url = {https://htmx.org}
}
@misc{grafana,
author = {},
title = {Grafana: The open observability platform | Grafana Labs},
howpublished = {\url{https://grafana.com/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{go,
title = {{The Go Programming Language}},
year = {2023},
month = nov,
note = {[Online; accessed 1. Nov. 2023]},
url = {https://go.dev}
}
@misc{ffmpeg,
author = {},
title = {FFmpeg},
howpublished = {\url{https://ffmpeg.org/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{node-to-go,
title = {{A journey from Node to GoLang}},
year = {2023},
month = nov,
note = {[Online; accessed 5. Nov. 2023]},
url = {https://www.loginradius.com/blog/engineering/a-journey-from-node-to-golang}
}
@misc{keepass,
author = {},
title = {KeePassXC Password Manager},
howpublished = {\url{https://keepassxc.org/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{amazon-machine-learning,
title = {{An overview of AI and machine learning services from AWS}},
journal = {Amazon Web Services, Inc},
year = {2023},
month = dec,
note = {[Online; accessed 18. Dec. 2023]},
url = {https://aws.amazon.com/machine-learning}
}
@misc{cyberark,
author = {},
title = {Identity Security and Access Management Leader | CyberArk},
howpublished = {\url{https://www.cyberark.com/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{amazon-rekognition-custom-labels,
title = {{What is Amazon Rekognition Custom Labels? - Rekognition}},
year = {2023},
month = dec,
note = {[Online; accessed 18. Dec. 2023]},
url = {https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/what-is.html?pg=ln&sec=ft}
}
@misc{docker,
author = {},
title = {Docker: Accelerated, Containerized Application Development},
howpublished = {\url{https://www.docker.com/}},
month = {},
year = {},
note = {(Accessed on 06/26/2023)}
@misc{amazon-rekognition-custom-labels-training,
title = {{Training an Amazon Rekognition Custom Labels model - Rekognition}},
year = {2023},
month = dec,
note = {[Online; accessed 18. Dec. 2023]},
url = {https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/training-model.html#tm-console}
}
@misc{opsview,
author = {},
title = {Opsview > Monitoring},
month = {},
year = {},
% TODO check this later
note = {Image generated, (Accessed on 06/29/2023), not accessible outside Sky UK}
@misc{google-vision-price-sheet,
title = {{Pricing {$\vert$} Vertex AI Vision {$\vert$} Google Cloud}},
journal = {Google Cloud},
year = {2023},
month = dec,
note = {[Online; accessed 20. Dec. 2023]},
url = {https://cloud.google.com/vision-ai/pricing}
}
@misc{grafana_charts,
author = {},
title = {Grafana - Files in Flight Dashboard Graphs},
month = {},
year = {},
% TODO check this later
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@misc{google-vision-product-recognizer-guide,
title = {{Product Recognizer guide}},
year = {2023},
month = dec,
note = {[Online; accessed 20. Dec. 2023]},
url = {https://cloud.google.com/vision-ai/docs/product-recognizer}
}
@misc{actual-intake,
author = {},
title = {Dashboard [Jenkins]},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@article{mnist,
title={The mnist database of handwritten digit images for machine learning research},
author={Deng, Li},
journal={IEEE Signal Processing Magazine},
volume={29},
number={6},
pages={141--142},
year={2012},
publisher={IEEE}
}
@article{mist-high-accuracy,
author = {Sanghyeon An and
Min Jun Lee and
Sanglee Park and
Heerin Yang and
Jungmin So},
title = {An Ensemble of Simple Convolutional Neural Network Models for {MNIST}
Digit Recognition},
journal = {CoRR},
volume = {abs/2008.10400},
year = {2020},
url = {https://arxiv.org/abs/2008.10400},
eprinttype = {arXiv},
eprint = {2008.10400},
timestamp = {Fri, 28 Aug 2020 12:11:44 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-10400.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{test-intake,
author = {},
title = {Dashboard [Jenkins]},
howpublished = {},
month = {},
year = {},
note = {Screenshot of the page locally hosted page, (Accessed on 06/29/2023), not accessible}
@article {lecun-98,
original = "orig/lecun-98.ps.gz",
author = "LeCun, Y. and Bottou, L. and Bengio, Y. and Haffner, P.",
title = "Gradient-Based Learning Applied to Document Recognition",
journal = "Proceedings of the IEEE",
month = "November",
volume = "86",
number = "11",
pages = "2278-2324",
year = 1998
}
@misc{spoglight-api,
author = {},
title = {Swagger UI},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@inproceedings{imagenet,
title={Imagenet: A large-scale hierarchical image database},
author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
booktitle={2009 IEEE conference on computer vision and pattern recognition},
pages={248--255},
year={2009},
organization={Ieee}
}
@misc{spotlight,
author = {},
title = {Spotlight},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@article{resnet-152,
author = {Qilong Wang and
Banggu Wu and
Pengfei Zhu and
Peihua Li and
Wangmeng Zuo and
Qinghua Hu},
title = {ECA-Net: Efficient Channel Attention for Deep Convolutional Neural
Networks},
journal = {CoRR},
volume = {abs/1910.03151},
year = {2019},
url = {http://arxiv.org/abs/1910.03151},
eprinttype = {arXiv},
eprint = {1910.03151},
timestamp = {Mon, 04 Dec 2023 21:30:01 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-03151.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{spog,
author = {},
title = {Spog},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@article{efficientnet,
author = {Mingxing Tan and
Quoc V. Le},
title = {EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
journal = {CoRR},
volume = {abs/1905.11946},
year = {2019},
url = {http://arxiv.org/abs/1905.11946},
eprinttype = {arXiv},
eprint = {1905.11946},
timestamp = {Mon, 03 Jun 2019 13:42:33 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-11946.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{spog-report,
author = {},
title = {Spog},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@misc{resnet,
title={Deep Residual Learning for Image Recognition},
author={Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
year={2015},
eprint={1512.03385},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@misc{launchpad,
author = {},
title = {Launchpad page},
month = {},
year = {},
note = {Screenshot of the page, (Accessed on 06/29/2023), not accessible outside Sky UK}
@misc{going-deeper-with-convolutions,
title={Going Deeper with Convolutions},
author={Christian Szegedy and Wei Liu and Yangqing Jia and Pierre Sermanet and Scott Reed and Dragomir Anguelov and Dumitru Erhan and Vincent Vanhoucke and Andrew Rabinovich},
year={2014},
eprint={1409.4842},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@misc{launchpad-code,
author = {Andre Henriques},
title = {Screenshot of the Code},
@misc{very-deep-convolution-networks-for-large-scale-image-recognition,
title={Very Deep Convolutional Networks for Large-Scale Image Recognition},
author={Karen Simonyan and Andrew Zisserman},
year={2015},
eprint={1409.1556},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@misc{devops-vault,
author = {},
title = {Devops Vault},
howpublished = {},
month = {},
year = {},
note = {Screenshot of the page locally hosted page, (Accessed on 06/29/2023), not accessible}
@misc{efficient-net,
title={EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
author={Mingxing Tan and Quoc V. Le},
year={2020},
eprint={1905.11946},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@misc{typescript,
author = {},
title = {TypeScript: JavaScript With Syntax For Types.},
howpublished = {\url{https://www.typescriptlang.org/}},
month = {},
year = {},
note = {(Accessed on 08/07/2023)}
@INPROCEEDINGS{inverted-bottleneck-mobilenet,
author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
booktitle={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
title={MobileNetV2: Inverted Residuals and Linear Bottlenecks},
year={2018},
volume={},
number={},
pages={4510-4520},
keywords={Manifolds;Neural networks;Computer architecture;Standards;Computational modeling;Task analysis},
doi={10.1109/CVPR.2018.00474}
}
@misc{react,
author = {},
title = {React},
howpublished = {\url{https://react.dev/}},
month = {},
year = {},
note = {(Accessed on 08/07/2023)}
@article{json-api-usage-stats,
author = {Hnatyuk, Kolya},
title = {{130+ API Statistics: Usage, Growth {\&} Security}},
journal = {MarketSplash},
year = {2023},
month = oct,
publisher = {MarketSplash},
url = {https://marketsplash.com/api-statistics}
}
@misc{prisma,
author = {},
title = {Prisma | Next-generation ORM for Node.js \& TypeScript},
howpublished = {\url{https://www.prisma.io/}},
month = {},
year = {},
note = {(Accessed on 08/07/2023)}
@misc{svelte,
title = {{Svelte {\ifmmode\bullet\else\textbullet\fi} Cybernetically enhanced web apps}},
year = {2024},
month = mar,
note = {[Online; accessed 12. Mar. 2024]},
url = {https://svelte.dev}
}
@misc{postgres,
author = {},
title = {PostgreSQL: The world's most advanced open source database},
howpublished = {\url{https://www.postgresql.org/}},
month = {},
year = {},
note = {(Accessed on 08/07/2023)}
@misc{state-of-js-2022,
title = {{State of JavaScript 2022: Front-end Frameworks}},
year = {2023},
month = nov,
note = {[Online; accessed 12. Mar. 2024]},
url = {https://2022.stateofjs.com/en-US/libraries/front-end-frameworks}
}
@misc{js-frontend-frameworks-performance,
title = {{Interactive Results}},
year = {2024},
month = mar,
note = {[Online; accessed 12. Mar. 2024]},
url = {https://krausest.github.io/js-framework-benchmark/current.html}
}
@misc{svelte-kit,
title = {{SvelteKit {\ifmmode\bullet\else\textbullet\fi} Web development, streamlined}},
year = {2024},
month = mar,
note = {[Online; accessed 12. Mar. 2024]},
url = {https://kit.svelte.dev}
}
@misc{nginx,
author = {},
title = {Advanced Load Balancer, Web Server, \& Reverse Proxy - NGINX},
howpublished = {\url{https://www.nginx.com/}},
month = {},
year = {},
note = {(Accessed on 08/07/2023)}
title = {{Advanced Load Balancer, Web Server, {\&} Reverse Proxy - NGINX}},
journal = {NGINX},
year = {2024},
month = feb,
note = {[Online; accessed 12. Mar. 2024]},
url = {https://www.nginx.com}
}
@misc{dockerlogo,
author = {},
title = {Press and Media Resources - Docker},
howpublished = {\url{https://www.docker.com/company/newsroom/media-resources/}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@article{bycrpt,
author = {Provos, Niels and Mazieres, David},
year = {2001},
month = {03},
pages = {},
title = {A Future-Adaptable Password Scheme}
}
@misc{jenkinslogo,
author = {},
title = {jenkins.png (742×1024)},
howpublished = {\url{https://www.jenkins.io/images/logos/jenkins/jenkins.png}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@TECHREPORT{cifar10,
author = {Alex Krizhevsky},
title = {Learning multiple layers of features from tiny images},
institution = {},
year = {2009}
}
@misc{typescriptlogo,
author = {},
title = {TypeScript: Branding},
howpublished = {\url{https://www.typescriptlang.org/branding/}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@misc{stl10,
title = {{STL-10 dataset}},
year = {2015},
month = nov,
note = {[Online; accessed 11. May 2024]},
url = {https://cs.stanford.edu/~acoates/stl10}
}
@misc{ansiblelogo,
author = {},
title = {logos/logos/ansible.svg at main · gilbarbara/logos},
howpublished = {\url{https://github.com/gilbarbara/logos/blob/main/logos/ansible.svg}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@misc{caltech256, title={Caltech 256}, DOI={10.22002/D1.20087}, abstractNote={We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 was collected by choosing a set of object categories, downloading examples from Google Images and then manually screening out all images that did not fit the category. Caltech-256 is collected in a similar manner with several improvements: a) the number of categories is more than doubled, b) the minimum number of images in any category is increased from 31 to 80, c) artifacts due to image rotation are avoided and d) a new and larger clutter category is introduced for testing background rejection. We suggest several testing paradigms to measure classification performance, then benchmark the dataset using two simple metrics as well as a state-of-the-art spatial pyramid matching algorithm. Finally we use the clutter category to train an interest detector which rejects uninformative background regions.}, publisher={CaltechDATA}, author={Griffin, Gregory and Holub, Alex and Perona, Pietro}, year={2022}, month={Apr} }
@techreport{fgvca,
title = {Fine-Grained Visual Classification of Aircraft},
author = {S. Maji and J. Kannala and E. Rahtu
and M. Blaschko and A. Vedaldi},
year = {2013},
archivePrefix = {arXiv},
eprint = {1306.5151},
primaryClass = "cs-cv",
}
@misc{reactlogo,
author = {},
title = {React},
howpublished = {\url{https://react.dev/}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@article{fooddataset,
title={{FoodX-251: A Dataset for Fine-grained Food Classification}},
author={Kaur, Parneet and Sikka, Karan and Wang, Weijun and Belongie, serge and Divakaran, Ajay},
journal={arXiv preprint arXiv:1907.06167},
year={2019}
}
@misc{gitlablogo,
author = {},
title = {Press kit | GitLab},
howpublished = {\url{https://about.gitlab.com/press/press-kit/}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@incollection{pytorch,
title = {PyTorch: An Imperative Style, High-Performance Deep Learning Library},
author = {Paszke, Adam and Gross, Sam and Massa, Francisco and Lerer, Adam and Bradbury, James and Chanan, Gregory and Killeen, Trevor and Lin, Zeming and Gimelshein, Natalia and Antiga, Luca and Desmaison, Alban and Kopf, Andreas and Yang, Edward and DeVito, Zachary and Raison, Martin and Tejani, Alykhan and Chilamkurthy, Sasank and Steiner, Benoit and Fang, Lu and Bai, Junjie and Chintala, Soumith},
booktitle = {Advances in Neural Information Processing Systems 32},
pages = {8024--8035},
year = {2019},
publisher = {Curran Associates, Inc.},
url = {http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf}
}
@misc{pytorch-vs-tensorflow-1,
title = {{PyTorch vs TensorFlow: Deep Learning Frameworks [2024]}},
year = {2023},
month = dec,
note = {[Online; accessed 14. May 2024]},
url = {https://www.knowledgehut.com/blog/data-science/pytorch-vs-tensorflow}
}
@misc{atlassianlogo,
author = {},
title = {Logo library - Resources - Atlassian Design System},
howpublished = {\url{https://atlassian.design/resources/logo-library}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@article{pytorch-vs-tensorflow-2,
author = {O'Connor, Ryan},
title = {{PyTorch vs TensorFlow in 2023}},
journal = {News, Tutorials, AI Research},
year = {2023},
month = apr,
publisher = {News, Tutorials, AI Research},
url = {https://www.assemblyai.com/blog/pytorch-vs-tensorflow-in-2023}
}
@misc{flasklogo,
author = {},
title = {Welcome to Flask — Flask Documentation (1.1.x)},
howpublished = {\url{https://flask.palletsprojects.com/en/1.1.x/}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
@article{artbench,
title={The ArtBench Dataset: Benchmarking Generative Models with Artworks},
author={Liao, Peiyuan and Li, Xiuyu and Liu, Xihui and Keutzer, Kurt},
journal={arXiv preprint arXiv:2206.11404},
year={2022}
}
@misc{skyaboutus,
author = {},
title = {About Us | Sky Group},
howpublished = {\url{https://www.skygroup.sky/about-us}},
month = {},
year = {},
note = {(Accessed on 08/10/2023)}
https://www.assemblyai.com/blog/pytorch-vs-tensorflow-in-2023/
https://www.knowledgehut.com/blog/data-science/pytorch-vs-tensorflow
@misc{postgressql,
title = {{PostgreSQL}},
journal = {PostgreSQL},
year = {2024},
month = may,
note = {[Online; accessed 14. May 2024]},
url = {https://www.postgresql.org}
}

88
meeting/meeting.tex Normal file
View File

@ -0,0 +1,88 @@
%%% Preamble
\documentclass[11pt, a4paper]{article}
\usepackage[english]{babel} % English language/hyphenation
\usepackage{url}
\usepackage{tabularx}
\usepackage{pdfpages}
\usepackage{float}
\usepackage{graphicx}
\graphicspath{ {../images for report/} }
\usepackage[margin=2cm]{geometry}
\usepackage{hyperref}
\hypersetup{
colorlinks,
citecolor=black,
filecolor=black,
linkcolor=black,
urlcolor=black
}
\usepackage{cleveref}
%%% Custom headers/footers (fancyhdr package)
\usepackage{fancyhdr}
\pagestyle{fancyplain}
\fancyhead{} % No page header
\fancyfoot[L]{} % Empty
\fancyfoot[C]{\thepage} % Pagenumbering
\fancyfoot[R]{} % Empty
\renewcommand{\headrulewidth}{0pt} % Remove header underlines
\renewcommand{\footrulewidth}{0pt} % Remove footer underlines
\setlength{\headheight}{13.6pt}
% numeric
\usepackage[style=ieee,sorting=none,backend=biber]{biblatex}
\addbibresource{../main.bib}
% Write the approved title of your dissertation
\title{Automated image classification with expandable models}
% Write your full name, as in University records
\author{Andre Henriques, 6644818}
\date{}
%%% Begin document
\begin{document}
\subsection*{Minute Mittings}
\begin{itemize}
\item Discussed progress so far.
\item Discussed code work vs documentation work.
\item Discussed formating of the document.
\item Discussed next steps.
\end{itemize}
\subsection*{Workplan}
\begin{tabular}{ |m{0.5\textwidth}|m{0.5\textwidth}| }
\hline
Month & Goals \\
\hline
Feburary & \begin{itemize}
\item Add api support.
\item Start working on expandable models generation
\item Start documenting the design process
\item Improve Literature review
\item Start documenting results
\end{itemize} \\
\hline
March & \begin{itemize}
\item Create systems to expand the expandable models and contract models
\item Continue documenting the design process
\item Review draft submissions
\end{itemize} \\
\hline
April & \begin{itemize}
\item Basic final report finish
\item Create systems to expand and reduce expandable models
\end{itemize} \\
\hline
May & \begin{itemize}
\item Finish and submit final report
\end{itemize} \\
\hline
\end{tabular}
\end{document}

View File

@ -1,12 +0,0 @@
Change title to Sky -> Sky UK Limited
Say something about diferent devisions at Sky
Add pictures of campus
Change pictures to make readble
Make sure the images have references
Subscript images
Make better distigisable bettween projects and case sutdies
new pages bettween sections
more details in the case studies less in the naratives
in cases studies talked about problems that I had to over come
https://www.youtube.com/watch?v=PKfR6bAXr-c

29
papers.txt Normal file
View File

@ -0,0 +1,29 @@
Non papers, industry resources:
- https://www.clarifai.com/company/customers
- https://cloud.google.com/vision
- Model generation Base model generation
- Database search
- results for imagenet: https://paperswithcode.com/sota/image-classification-on-imagenet
- Comparasion of different classification methods https://ieeexplore.ieee.org/abstract/document/9687944
- EfficientNet: https://arxiv.org/pdf/1905.11946.pdf
- Imagenet dataset: https://ieeexplore.ieee.org/abstract/document/5206848
- AutoMl
- A survey of state of the art in ml - https://www.sciencedirect.com/science/article/pii/S0950705120307516
- AutoMl benchmark: https://arxiv.org/abs/1907.00909
- Transfer learning / Chaging Output layer / Multi model approach
- https://journalofbigdata.springeropen.com/articles/10.1186/s40537-016-0043-6
- https://ieeexplore.ieee.org/abstract/document/9134370
- Cost of machine training / Efficiency
- https://ieeexplore.ieee.org/abstract/document/8622396
- https://ieeexplore.ieee.org/abstract/document/9770050
- Node Management
- Cache invalidation: https://dl.acm.org/doi/abs/10.1145/70082.68205
- Federation Learning: https://www.sciencedirect.com/science/article/abs/pii/S0950705121000381
- Transfer learning
- https://link.springer.com/chapter/10.1007/978-3-319-97982-3_16

View File

@ -9,6 +9,7 @@
\usepackage{graphicx}
\graphicspath{ {../images for report/} }
\usepackage[margin=2cm]{geometry}
\usepackage{hyperref}
\hypersetup{
@ -32,18 +33,16 @@
\renewcommand{\footrulewidth}{0pt} % Remove footer underlines
\setlength{\headheight}{13.6pt}
\usepackage[style=numeric,sorting=none,backend=biber]{biblatex}
% numeric
\usepackage[style=ieee,sorting=none,backend=biber]{biblatex}
\addbibresource{../main.bib}
\title{
\normalfont \normalsize \textsc{University of Surrey} \\ %[25pt]
\Huge Final year project \\
}
\author{
\normalfont \normalsize
Andre Henriques\\[-3pt] \normalsize
\today
}
% Write the approved title of your dissertation
\title{Automated image classification with expandable models}
% Write your full name, as in University records
\author{Andre Henriques, 6644818}
\date{}
%%% Begin document
@ -55,11 +54,145 @@
\tableofcontents
\newpage
\section{Introduction}
\section{Introduction}
% This section should contain an introduction to the problem aims and objectives (0.5 page)
Currently, there are many classification tasks that are being done manually. These tasks could be done more effectively if there was tooling that would allow the easy creation of classification models, without the knowledge of data analysis and machine learning models creation.
The aim of this project is to create a classification service that requires zero user knowledge about machine learning, image classification or data analysis.
The system should allow the user to create a reasonable accurate model that can satisfy the users' need.
The system should also allow the user to create expandable models; models where classes can be added after the model has been created.
\subsection{Project Aim}
The project aims to create a platform where users can create different types of classification models without the users having any knowledge of image classification.
\subsection{Project Objectives}
This project's primary objectives are to:
\begin{itemize}
\item Create platform where the users can create and manage their models.
\item Create a system to automatically create and train models.
\item Create a system to automatically expand and reduce models without fully retraining the models.
\item Create an API so that users can interact programatically with the system.
\end{itemize}
This project extended objectives are to:
\begin{itemize}
\item Create a system to automatically to merge modules to increase efficiency.
\item Create a system to distribute the load of training the model's among multiple services.
\end{itemize}
\section{Literature and Techincal Review}
% 1 page of background and literature review. Here you will need to references things. Gamal et al.~\cite{gamal} introduce the concept of \ldots
\subsection{Alternatives to my Project}
There currently exist systems that do image classification, like Google Vision AI \cite{google-vision-api}, and Amazon's Rekoginition \cite{amazon-rekognition}.
Their tools, while providing similar services to what my project is supposed to do, it mostly focusses on general image classification rather than specific image classification, i.e. Car vs Boat, vs, Car model X vs Car model Y.
\subsection{Creation Models}
The models that I will be creating will be Convolutional Neural Network(CNN) \cite{lecun1989handwritten,fukushima1980neocognitron}.
The system will be creating two types of models that cannot be expanded and models that can be expanded. For the models that can be expanded, see the section about expandable models.
The models that cannot be expanded will use a simple convolution blocks, with a similar structure as the AlexNet \cite{krizhevsky2012imagenet} ones, as the basis for the model. The size of the model will be controlled by the size of the input image, where bigger images will generate more deep and complex models.
The models will be created using TensorFlow \cite{tensorflow2015-whitepaper} and Keras \cite{chollet2015keras}. These theologies are chosen since they are both robust and used in industry.
\subsection{Expandable Models}
The current most used approach for expanding a CNN model is to retrain the model. This is done by, recreating an entire new model that does the new task, using the older model as a base for the new model\cite{amazon-rekognition}, or using a pretrained model as a base and training the last few layers.
There are also unsupervised learning methods that do not have a fixed number of classes. While this method would work as an expandable model method, it would not work for the purpose of this project. This project requires that the model has a specific set of labels which does not work with unsupervised learning which has unlabelled data. Some technics that are used for unsupervised learning might be useful in the process of creating expandable models.
\section{Technical overview}
% technological free overview
\subsection{Web Interface}
The user will interact with the platform form via a web portal. % why the web portal
The web platform will be designed using HTML and a JavaScript library called HTMX \cite{htmx} for the reactivity that the pagers requires.
The web server that will act as controller will be implemented using go \cite{go}, due to its ease of use.
Go was chosen has the programming language used in the server due to its performance, i.e. \cite{node-to-go}, and ease of implementation. As compiled language go, outperforms other server technologies such as Node.js.
Go also has easy support for C ABI, which might be needed if there is a need to interact with other tools that are implemented using C.
The web server will also interact with python to create models. Then to run the models, it will use the libraries that are available to run TensorFlow \cite{tensorflow2015-whitepaper} models for that in go.
\subsection{Creating Models}
The models will be created using TensorFlow \cite{tensorflow2015-whitepaper}.
TensorFlow was chosen because, when using frameworks like Keras \cite{chollet2015keras}, it allows the easy development of machine learning models with little code. While tools like PyTorch might provide more advanced control options for the model, like dynamic graphs, it comes at the cost of more complex python code. Since that code is generated by the go code, the more python that needs to be written, the more complex the overall program gets, which is not desirable.
The original plan was to use go and TensorFlow, but the go library was lacking that ability. Therefore, I chose to use python to create the models.
The go server starts a new process, running python, that creates and trains the TensorFlow model. Once the training is done, the model is saved to disk which then can be loaded by the go TensorFlow library.
\subsection{Expandable Models}
The approach would be based on multiple models. The first model is a large model that will work as a feature traction model, the results of this model are then given to other smaller models. These model's purpose is to classify the results of the feature extraction model into classes.
The first model would either be an already existent pretrained model or a model that is automatically created by the platform.
The smaller models would all be all generated by the platform, this model's purpose would be actually classification.
This approach would offer a lot of expandability, as it makes the addition of a new class as easy as creating a new small model.
\section{Workplan}
\subsection{Timeline}
% bold the headres
% The following work plan is what I will be using for the project is shown in Figure~\ref{fig:sample2}.
\begin{tabular}{ |m{0.5\textwidth}|m{0.5\textwidth}| }
\hline
Month & Goals \\
\hline
September & \begin{itemize}
\item Experimenting with web development frameworks.
\item Started working on code development.
\end{itemize} \\
\hline
October & \begin{itemize}
\item Starting working on Project Synopsis.
\item Continue working on project development.
\item Finish user management system and basic ui decisions.
\item Finish data upload section of the website.
\end{itemize} \\
\hline
November & \begin{itemize}
\item Finish writing on Project Synopsis.
\item Finish coding the basic model generation and training.
\end{itemize} \\
\hline
December & \begin{itemize}
\item Improve basic model generation.
\end{itemize} \\
\hline
January & \begin{itemize}
\item Add api support.
\item Started working on the final report
\end{itemize} \\
\hline
Feburary & \begin{itemize}
\item Start working on expandable models generation
\end{itemize} \\
\hline
March & \begin{itemize}
\item Create systems to expand the expandable models and contract models
\item Review draft submissions
\end{itemize} \\
\hline
April & \begin{itemize}
\item Basic final report finish
\item Create systems to expand and reduce expandable models
\end{itemize} \\
\hline
May & \begin{itemize}
\item Finish and submit final report
\end{itemize} \\
\hline
\end{tabular}
\subsection{Risks}
\begin{tabular}{ |m{0.5\textwidth}|m{0.5\textwidth}| }
\hline
Risk & Mitigation \\
\hline
Automatic model generation is not feasable & Other methods for creation of model can be used i.e. transfer learning, or semi-unsupervised learning\\
\hline
Easy model expancion is not feasble & Other methods of updating the models need to be implemented i.e. retratinng the entire model.\\
\hline
Not enough compute power to train models fast enough to develop the program & Free credits from online cloud providers like google or amazon\\
\hline
\end{tabular}
\appendix
\newpage
\section{References}
\printbibliography[heading=none]
% TODO add my job title
\end{document}

112
report/design.tex Normal file
View File

@ -0,0 +1,112 @@
\section{Service Design} \label{sec:sd}
This chapter presents an idealised design, such design is open-ended to allow for multiple possible implementations that still meet the project requirements.
This idealised design is also envisioned to not be limited by time or engineering constraints.
The chapter \ref{sec:si} will discuss in more details how this design was further scoped to be able to be implemented in the timeframe available.
This chapter will transform the requirements discussed in the previous chapter into a more specialized technical design that can be used as a guide to implement such a service.
\subsection{Structure of the Service}
The service is designed to be a 4 tier structure:
\begin{itemize}
\item{Presentation Layer}
\item{API Layer}
\item{Worker Layer}
\item{Data Layer}
\end{itemize}
This structure was selected because it allows separation of concerns.
The layers were separated based on what resources are required by that layer.
The presentation layer requires interactivity of the user, and therefore it needs to be accessible from the outside, and be simple to use.
The presentation layer was limited from being any interaction method to be a web page.
The web page can a separate server, or as part of the main API application, if it is in the same.
The API layer, is one of the most important parts of the service.
As it will be the most used way to interact with the service.
The user can use the API to control their entire model process from importing, to classification of images.
The Worker layer, consists of a set of servers available to perform GPU loads.
The Data layer, consists of stored images, models, and user data.
\subsection{Interacting with the service}
As a software platform, this project requires a way for users to interact with the service.
This interface is mainly intended to be as a control and monitoring interface.
The user would use the interface to set up and manage the models, then most of the interactions would happen via the API.
While there were no specific restrictions on what the interface can be, it makes most sense for it to be a web page.
This is because most software as a service applications are controlled with web pages, and the API is already a web-based application.
Independently of the kind of the application is, it needs to allow users to fully control their data in an easy to use and understand way.
The application should allow users to:
%TODO add more
\begin{multicols}{2}
\begin{itemize}
\item Manage access tokens.
\item Upload images for training.
\item Delete images.
\item Request training model.
\item Delete models.
\item Classify Images.
\item See previous classification results
\item Keep track of model accuracy
\end{itemize}
\end{multicols}
Aside from being able to perform the above tasks, there are no restrictions on how the application needs to be architected.
\subsection{API}
As a SaaS, one of the main requirements is to be able to communicate with other services.
The API provides the simplest way for other services to interact with this service.
The API needs to be able to perform all the tasks that the application can do, which include:
% TODO maybe remove
\begin{multicols}{2}
\begin{itemize}
\item Manage access tokens.
\item Upload images for training.
\item Delete images.
\item Request training model.
\item Delete models.
\item Classify Images.
\item See previous classification results
\item Keep track of model accuracy
\end{itemize}
\end{multicols}
While implementing all the features that mentioned above, the API has to handle multiple simultaneous requests.
Ideally, those requests should be handled as fast as possible.
The API should be implemented such that it can be easily expandable and maintainable, so that future improvements can happen.
It should be consistent and easy to use, information on how to use the API should also be available to possible users.
The API should be structured as a REST JSON API, per the requirements.
The API should only accept inputs via the URL parameters of GET requests or via JSON on POST requests.
Binary formats can also be used to handle file upload and downloads, as transferring files via JSON extremely inefficient.
\subsection{Generation of Models}
The service should use any means available to generate models, such means can be:
\begin{multicols}{2}
\begin{itemize}
\item Templating.
\item Transfer Learning.
\item Database Search.
\item Pretrained Models with classification heads.
\end{itemize}
\end{multicols}
\subsection{Models Training}
% The Training process follows % TODO have a flow diagram
Model Training should be independent of image classification. A model training should not affect any current classification. The system could use multiple ways to achieve this, such as:
\begin{multicols}{2} % TODO think of more ways
\begin{itemize}
\item Separating the training to different machines.
\item Control the number of resources that training machine can utilise
\item Control the time when the shared training and inference machine can be used for training.
\item Allow users to have their own ``Runners'' where the training tasks can happen.
\end{itemize}
\end{multicols}
\subsection{Summary}
This chapter introduced multiple possible designs options for a service, that intends to achieve automated image classification, can follow to implement a robust system. The next chapter will be discussing how the system was implemented and which of the possible design options were chosen when implementing the system.
\pagebreak

221
report/eval.tex Normal file
View File

@ -0,0 +1,221 @@
\section{Service Evaluation} \label{sec:se}
This section will discuss how the service can be evaluated from a technical standpoint and its results.
With the goals of the project, there are two kinds of tests that need to be accounted for.
User testing tests that relate to the experience of the user while using the project and tests that quantitive test the project.
Such as accuracy of the generated models, response time to queries.
\subsection{Testing the model creation}
To test the system, a few datasets were selected.
The datasets were selected to represent different possible sizes of models, and sizes of output labels.
The ImageNet\cite{imagenet} was not selected as one of the datasets that will be tested, as it does not represent the target problem that this project is trying to tackle.
The tests will measure:
\begin{itemize}
\item Time to process and validate the entire dataset upon upload
\item Time to train the dataset
\item Time to classify the image once the dataset has been trained
\item Time to extend the model
\item Accuracy of the newly created model
\end{itemize}
The results will be placed in the results table.
\subsubsection*{MNIST}
The MNIST \cite{mnist} is a large dataset of handwritten digits, that is commonly used to trains and test machine learning systems.
This dataset was selected due to its size. It is a small dataset that can be trained quickly and can be used to verify other internal systems of the service.
During testing, only the 9 out of 10 classes are trained and the 10th is added during the retraining process.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.2\linewidth]{minst_1}}}
\qquad
\subfloat{{\includegraphics[width=.2\linewidth]{minst_2}}}
\caption{Examples of the images in the MNIST dataset}
\end{figure}
\subsubsection*{CIFAR-10}
The CIFAR-10 \cite{cifar10} dataset contains various images that are commonly used to train and test machine learning algorithms.
This dataset was selected due to its size. It is a small dataset that can be trained quickly, but it has bigger, and coloured images, which makes it harder than MNIST.
During testing, only the 9 out of 10 classes are trained and the 10th is added during the retraining process.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.2\linewidth]{cifar_1}}}
\qquad
\subfloat{{\includegraphics[width=.2\linewidth]{cifar_2}}}
\caption{Examples of the images in the CIFAR-10 dataset}
\end{figure}
\subsubsection*{STL-10}
The STL-10 \cite{stl10} dataset that was inspired by the CIFAR-10 \cite{cifar10}, but it has bigger images.
This dataset was selected because of the bigger image. The images are bigger than both CIFAR-10 and MNIST which makes the model harder to create, and train.
During testing, only the 9 out of 10 classes are trained and the 10th is added during the retraining process.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.2\linewidth]{stl_1}}}
\qquad
\subfloat{{\includegraphics[width=.2\linewidth]{stl_2}}}
\caption{Examples of the images in the STL-10 dataset}
\end{figure}
\subsubsection*{ArtBench}
The ArtBench \cite{artbench} dataset is a dataset that contains artworks annotated with their art style that is intended to train generative models.
This dataset was selected due to the even bigger images than the previously tested models.
During testing, only the 9 out of 10 classes are trained and the 10th is added during the retraining process.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.2\linewidth]{artbench1}}}
\qquad
\subfloat{{\includegraphics[width=.2\linewidth]{artbench2}}}
\caption{Examples of the images in the ArtBench dataset}
\end{figure}
\subsubsection*{Incompatible datasets}
There were attempts to test other datasets against the system, but those datasets were incompatible.
The datasets had irregular images sizes, which, as it was mentioned previously, the system does not support.
This caused a large section of images inputted being rejected, which means that it would have not trained.
A list of datasets that are incompatible because of this are:
\begin{multicols}{2}
\begin{itemize}
\item Caltech 256 \cite{caltech256}
\item FGVC-Aircraft \cite{fgvca}
\item IFood 2019 \cite{fooddataset}
\end{itemize}
\end{multicols}
\subsubsection*{Results}
\begin{longtable}{ | c | c | c | c | c | c |}
\hline
Dataset & Import Time & Train Time & Classification Time & Extend Time & Accuracy \\ \hline
MNIST & $8s$ & $2m$ & $>1s$ & $50s$ & $98\%$ \\ \hline
CIFAR-10 & $6s$ & $41m 38s$ & $>1s$ & $1m 11s$ & $95.2\%$ \\ \hline
STL-10 & $1s$ & $37m 50s$ & $>1s$ & $1m 10s$ & $95.3\%$ \\ \hline
Art Bench & $10s$ & $4h 20m 31$ & $>1s$ & $1m 41s$ & $41.86\%$ \\ \hline
\caption{Evaluation Results}
\label{tab:eval-results}
\end{longtable}
The system was able to easily import all the datasets provided in an incredibly fast time, this included the incompatible datasets.
While the system was able to load and verify the images of the incompatible datasets, it correctly marked the images as incompatible, which can be seen in Figure \ref{fig:incompatible_images}.
Which would make them not being able to be used for training, which would mean the model would have not had any data to train, which would obviously result in terrible accuracy results.
\begin{figure}[h!]
\centering
\includegraphics[width=0.7\textheight]{incompatible_images}
\caption{Screenshot of a web application showing many images that do not have the correct format.}
\label{fig:incompatible_images}
\end{figure}
The system was able to train, classify, and extend the MNIST, CIFAR-10, and STL-10 datasets, with high accuracy rates.
This is expected as these models are models that are commonly known for being easy to train.
The system could also train these models in a relatively short, small amount of time.
The classification time is optimal, with all datasets being able to classify an image in less than a second.
The time to extend is also very promising, and the system could extend a new set of classes fairly quickly.
The system was unable to achieve a high level of accuracy while training for the ArtBench dataset.
And the training time to achieve that lower level of accuracy was also much higher than the other datasets.
The longer training time can be attributed to the larger images, which make the model harder to train, as the model has to make more computations.
Another factor for the increased training time is the necessity for the model to train longer to achieve a higher accuracy, due to the model's decreased learning rate.
As for the low accuracy ratting, I hypothesise that this is caused by the nature of the dataset.
The dataset is categorized into various art styles.
Even within a single art style, artists' individual styles can vary significantly.
Given the relatively small sample size of only 5000 training images per art style, this variability poses a challenge for the model's ability to discern between distinct styles.
Another option is that the system did not generate a good enough model for this dataset.
The system was still able to fairly quickly classify and image, with the classification time still being under less than a second.
The expansion time was also fairy quick, being on par with the other models.
\subsubsection*{Testing limitations}
There are some limitations caused by this testing.
The biggest problem is in the training, classification and expansion timings, this value will depend on what hardware the system that is running the model has.
The small sample size of the datasets is also limiting, as it does not fully prove that the system can create generalized models.
% api benchmarking if there is time
\subsection{API Performance Testing}
The application performance was also tested.
To test the performance of the API, a small program was written that would simultaneously request an image to be classified.
The selected image was one of the sample images provided in the MNIST dataset.
The program tries to perform 1, 10, 100, 1000, 10000 simultaneous requests, and waits 2 seconds between each set.
The program would then record how much time it would take for the image classification task to be completed.
And after all requests are completed, the program call calculates the mean and max requests times.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.5\linewidth]{max}}}
\subfloat{{\includegraphics[width=.5\linewidth]{mean}}}
\caption{Results of the API testing}
\label{fig:results-api}
\end{figure}
The values shown in Figure \ref{fig:results-api} show that if you configure the system to only have one runner, it will struggle to handle large amounts of simultaneous requests.
This is expected, as only having one process trying to classify large amounts of images would be unwise.
In reality this would never be set up this way since only having one runner in a production environment would never be acceptable.
\begin{figure}[H]
\centering
\subfloat{{\includegraphics[width=.5\linewidth]{max-no-1}}}
\subfloat{{\includegraphics[width=.5\linewidth]{mean-no-1}}}
\caption{Results of the API testing}
\label{fig:results-api-no-one}
\end{figure}
Figure \ref{fig:results-api-no-one} shows the same graph as Figure \ref{fig:results-api} but with the results for the test where the API only had one runner removed.
The graph indicates that the system was able to handle, 10000 simultaneous requests in less than 30 seconds, which more than exceeds the expectations of the project.
The results also indicate that the numbers of runners have demising returns, as the values maximum and mean request time are within a small range.
This can be caused by multiple reasons.
One such reason is that were not enough requests to show a significant difference between then number of runners.
Another reason is that the amount of work that the system has to perform to manage all the runners outweighs the benefits of having more runners.
While testing, the ram usage was monitored but not recorded.
As expected, the memory usage significant increased with the number of runners, but did not exceed 5 GiB.
The higher memory usage is a result of the runners caching the model used.
The memory footprint of the system limited by the model selected as the model generated for MNIST dataset is not large.
And larger models are expected to generate larger memory footprints.
When deploying the application, an administrator should take considerations the expected model sizes as well as the usage frequency expected and configure the application accordingly.
These results are very positive since the project was running on my personal computer and not on professional server hardware.
This indicates that when deployed to a production environment the service is most likely to perform extremely well.
\subsubsection*{Testing limitations}
As with the previous testing, this test has also some limitations.
Including the same hardware limitation where different hardware will give different results for this test.
Another limiting factor is that the test did not use different models or images which could cause the service to have to reload models from disk, affecting performance.
\subsection{Usability}
While if a service is usable differs vastly from user to user, the implemented system is simple enough where a user who does not know anything about image classification could upload images, and obtain a working classification model.
This simplicity may pose limitations for users with advanced knowledge, which would fall short of optimal usability standards for that user.
As this user might choose not to use the system because it does not allow the level of control that they might want.
The administrator area is less user-friendly than the rest of the application, but that is less critical.
An administrator is not the target user of the application, and is expected to manage this system, which requires prior knowledge about the system.
\subsection{Summary}
The service can create models, and train models that service the user's needs.
These models will most likely be able to achieve high accuracy targets, but in some cases the system might fail to generate a good enough model for the provided dataset.
During testing, the limitations of the strict image size requirements were also shown, as the system, would have failed to train those datasets because most of the images would have been removed before the model started training.
While classifying images, the service performed extremely well.
The API performance tests showed that if configured correctly, a single server configuration can handle a large amount of simultaneous images extremely fast.
These results indicate that the system has the performance required to be put in a production environment and perform well.
As for the usability of the service the system, the system is usable by beginners, but might detract more advanced users from using it.
Overall, the service evaluation is positive, as the system was able to create and train new models, as well as being user-friendly to users who might not have the skills to perform image classification.
\pagebreak

70
report/intro.tex Normal file
View File

@ -0,0 +1,70 @@
\section{Introduction} \label{sec:introduction}
The purpose of this dissertation is to design and implement an automated image classification service that will empower users to connect their existing services that required image classification with the one being implemented in this project.
This report will detail what requirements such service might have.
How those requirements can be turned into a design for such a service, and how that design can be implemented into software with limited time and resources.
This chapter will service as an introduction to the project, and will discuss the background, motivations, aims, goals, and success criteria for the project.
This chapter will end with an overview of the project structure.
\subsection{Project Background}
There are many automatable tasks that are currently being done manually.
If those tasks can be done automatically, a lot of productivity could be gained by having the computers perform those tasks, allowing humans to perform tasks that only humans can do.
Moreover, recently, machine learning models have become as good, or even better than humans in tasks such image classification. This project will focus on image classification, as it is an area where automation is still required, and there are few other images automated systems that are easy to use. It is also an area that has not been saturated with new products such as the natural language processing space has.
\subsection{Project Motivations}
This project allows for the improvement of my learned skills, while being an interesting, complex piece of software to develop.
The topics, skills, and knowledge required to build this project, cover all my years in the university, from the simple applications developed in the first year; the soft skills learned during placement; and the complexity of distributed systems and deep learning of the third year.
I also wanted to use the opportunity that this project provides to gain experience in emerging technologies such as Go, and improve all my previous abilities and skills.
\subsection{Project Aim}
The project aims to create an easy-to-use software platform, where users can create image classification models without having prior knowledge about machine learning.
The user should only need to upload the images and confirm, and the system should be able to perform all the steps necessary to create and manage the machine learning model.
\subsection{Project Objectives}
This project will have two different objectives.
Primary objectives are objectives that are required for the project to be considered a success.
Secondary objectives are objectives that are not required for the project to be considered a success, but they would provide a better experience for the user of the service.
This project's primary objectives are to design and implement:
\begin{itemize}
\item a system to upload images that will be assigned to a model.
\item a system to automatically create and train models.
\item a platform where users can manage their models.
% \item a system to automatically expand and reduce models without fully retraining the models.
\item a system to automatically expand models without fully retraining the models.
\item an Application Programming Interface (API) that users can interact programmatically with the service.
\end{itemize}
This project's secondary objectives are to:
\begin{itemize}
% \item Create a system to automatically to merge modules to increase efficiency.
\item Create a system to distribute the load of training the model among multiple servers.
\end{itemize}
\subsection{Success Criteria}
As it was mentioned before, the project can be considered a success when the primary objectives have been completed.
Therefore, the success criteria of this project can be defined as:
\begin{itemize}
\item A user can upload images, train a model on those images, and evaluate images using a user interface.
\item A user can perform the same tasks, via the API service.
\end{itemize}
\subsection{Project Structure}
The report on the project shows the development and designs stages of the project. With each chapter addressing a part of the design and development process.
\renewcommand*{\arraystretch}{2}
\begin{longtable}{p{7cm} p{8cm}}
\hyperref[sec:introduction]{Introduction} & The introduction chapter will do a brief introduction of the project and its objectives. \\
\hyperref[sec:lit-tech-review]{Literature and Technical Review} & The Literature and Technical Review chapter will introduce some current existing projects that are similar to this one, and introduce some technologies that can be used to implement this project. \\
\hyperref[sec:sanr]{Service Analysis and Requirements} & This chapter will analyse the project requirements. The chapter will define design requirements that the service will need to implement to be able to achieve the goals that were set up. \\
\hyperref[sec:sd]{Service Design} & This chapter will discuss how a service could be designed that it matches the requirements of the service. \\
\hyperref[sec:sd]{Service Implementation} & Information on how the design of the system was turned into software is in this chapter. \\
\hyperref[sec:lsec]{Legal, Societal, Ethical, Professional Considerations} & This chapter will cover potential legal, societal, ethical and professional, issues that might arise from the service and how they are mitigated. \\
\hyperref[sec:se]{Service Evaluation} & In this chapter, the model will be tested and the results of the tests will be analysed. \\
\hyperref[sec:crpo]{Critical Review of Project Outcomes} & In this chapter, will compare the project goals with what was achieved. Then, according to the results, the project will either be deemed successful or not.
\end{longtable}
\pagebreak

111
report/lit.tex Normal file
View File

@ -0,0 +1,111 @@
\section{Literature and Technical Review} \label{sec:lit-tech-review}
This chapter reviews existing technologies in the market that do image classification. It also reviews current image classification technologies, which meet the requirements for the project. This review also analyses methods that are used to distribute the learning between various physical machines, and how to spread the load so minimum reloading of the models is required when running the model.
\subsection{Existing Classification Platforms}
There are currently some existing software as a service (SaaS) platforms that do provide similar services to the ones this will project will be providing.
%Amazon provides bespoque machine learning services that if were contacted would be able to provide image classification services. Amazon provides general machine learning services \cite{amazon-machine-learning}.
Amazon provides an image classification service called ``Rekognition'' \cite{amazon-rekognition}. This service provides multiple services from face recognition, celebrity recognition, object recognition and others. One of these services is called custom labels \cite{amazon-rekognition-custom-labels} that provides the most similar service, to the one this project is about. The custom labels service allows the users to provide custom datasets and labels and using AutoML the Rekognition service would generate a model that allows the users to classify images according to the generated model.
The models generated using Amazon's Rekognition do not provide ways to update the number of labels that were created, without generating a new project. This will involve retraining a large part of the model, which would involve large downtime between being able to add new classes. Training models also could take 30 minutes to 24 hours, \cite{amazon-rekognition-custom-labels-training}, which could result in up to 24 hours of lag between the need of creating a new label and being able to classify that label. A problem also arises when the uses need to add more than one label at the same time. For example, the user sees the need to create a new label and starts a new model training, but while the model is training a new label is also needed. The user now either stops the training of the new model and retrains a new one, or waits until the one currently running stops and trains a new one. If new classification classes are required with frequency, this might not be the best platform to choose.
%https://aws.amazon.com/machine-learning/ml-use-cases/
%https://aws.amazon.com/rekognition/image-features/
Similarly, Google also has ``Cloud Vision API'' \cite{google-vision-api} which provides similar services to Amazon's Rekognition. But Google's Vision API appears to be more targeted at videos than images, as indicated by their price sheet \cite{google-vision-price-sheet}. They have tag and product identifiers, where every image only has one tag or product. The product identifier system seams to work differently than the Amazon's Rekognition and worked based on K neighbouring giving the user similar products on not classification labels \cite{google-vision-product-recognizer-guide}.
This method is more effective at allowing users to add new types of products, but as it does not give defined classes as the output, the system does not give the target functionality that this project is aiming to achieve.
\subsection{Requirements of Image Classification Models}
One of the main objectives of this project are to be able to create models that can give a class given an image for any dataset. Which means that there will be no ``one solution fits all to the problem''. While the most complex way to solve a problem would most likely result in success, it might not be the most efficient way to achieve the results.
This section will analyse possible models that would obtain the best results. The models for this project have to be the most efficient as possible while resulting in the best accuracy as possible.
A classical example is the MNIST Dataset \cite{mnist}. Models for the classification of the MNIST dataset can be both simple or extremely complex and achieve different levels of complexity.
For example, in \cite{mist-high-accuracy} an accuracy $99.91\%$, by combining 3 Convolutional Neural Networks (CNNs), with different kernel sizes and by changing hyperparameters, augmenting the data, and in \cite{lecun-98} an accuracy of $95\%$ was achieved using a 2 layer neural network with 300 hidden nodes. Both these models achieve the accuracy that is required for this project, but \cite{mist-high-accuracy} are more computational intensive to run. When deciding when to choose what models they create, the system should choose to create the model that can achieve the required accuracy while taking the leas amount of effort to train.
% TODO fix the inglish in these sentance
The models for this system to work as indented should be as small as possible while obtaining the required accuracy required to achieve the task of classification of the classes.
As the service might need to handle many requests, it needs to be able to handle as many requests as possible. This would require that the models are easy to run, and smaller models are easier to run; therefore the system requires a balance between size and accuracy.
% TODO talk about storage
\subsection{Method of Image Classification Models}
There are all multiple ways of achieving image classification, the requirements of the system are that the system should return the class that an image that belongs to. Which means that we will be using supervised classification methods, as these are the ones that meet the requirements of the system.
% TODO find some papers to proff this
The system will use supervised models to classify images, using a combination of different types of models, using neural networks, convolution neural networks, deed neural networks and deep convolution neural networks.
These types were decided as they have had a large success in the past in other image classification challenges, for example in the ImageNet challenges \cite{imagenet}, which has ranked different models in classifying a 14 million images. The contest has been running since 2010 to 2017.
The models that participated in the contest tended to use more and more Deep convolution neural networks, out of the various models that were generated there are a few landmark models that were able to achieve high accuracies, including AlexNet \cite{krizhevsky2012imagenet}, ResNet-152 \cite{resnet-152}, EfficientNet \cite{efficientnet}.
% TODO find vgg to cite
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{Well-known models}
% TODO compare the models
This section will compare the different models that did well in the image net challenge.
AlexNet \cite{krizhevsky2012imagenet} is a deep convolution neural network that participated in the ImageNet ILSVRC-2010 contest, it achieved a top-1 error rate of $37.5\%$, and a top-5 error rate of $37.5\%$. A variant of this model participated in the ImageNet LSVRC-2012 contest and achieved a top-5 error rate of $15.3\%$. The architecture of AlexNet consists of 5 convolution layers that are run separately followed by 3 dense layers, some layers are followed by Max pooling. The training the that was done using multiple GPUs, one GPU would run the part of each layer, and some layers are connected between GPUs. The model during training also contained data argumentation techniques such as label preserving data augmentation and dropout.
While using AlexNet would probably yield desired results, it would complicate the other parts of the service. As a platform as a service, the system needs to manage the number of resources available, and requiring to use 2 GPUs to train a model would limit the number of resources available to the system by 2-fold.
% TODO talk more about this
ResNet \cite{resnet} is a deep convolution neural network that participated in the ImageNet ILSVRC-2015 contest, it achieved a top-1 error rate of $21.43\%$ and a top-5 error rate of $5.71\%$. ResNet was created to solve a problem, the problem of degradation of training accuracy when using deeper models. Close to the release of the ResNet paper, there was evidence that deeper networks result in higher accuracy results, \cite{going-deeper-with-convolutions, very-deep-convolution-networks-for-large-scale-image-recognition}. but the increasing the depth of the network resulted in training accuracy degradation.
% This needs some work in terms of gramar
ResNet works by creating shortcuts between sets of layers, the shortcuts allow residual values from previous layers to be used on the upper layers. The hypothesis being that it is easier to optimize the residual mappings than the linear mappings.
The results proved that the using the residual values improved training of the model, as the results of the challenge prove.
It's important to note that using residual networks tends to give better results, the more layers the model has. While this could have a negative impact on performance, the number of parameters per layer does not grow that steeply in ResNet when comparing it with other architectures as it uses other optimisations such as $1x1$ kernel sizes, which are more space efficient. Even with these optimisations, it can still achieve incredible results. Which might make it a good contender to be used in the service as one of the predefined models to use to try to create the machine learning models.
% MobileNet
% 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.
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 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 optimised 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.
% \subsection{Efficiency of transfer learning}
% \subsection{Creation Models}
% The models that I will be creating will be Convolutional Neural Network(CNN) \cite{lecun1989handwritten,fukushima1980neocognitron}.
% The system will be creating two types of models that cannot be expanded and models that can be expanded. For the models that can be expanded, see the section about expandable models.
% The models that cannot be expanded will use a simple convolution blocks, with a similar structure as the AlexNet \cite{krizhevsky2012imagenet} ones, as the basis for the model. The size of the model will be controlled by the size of the input image, where bigger images will generate more deep and complex models.
% The models will be created using TensorFlow \cite{tensorflow2015-whitepaper} and Keras \cite{chollet2015keras}. These theologies are chosen since they are both robust and used in industry.
% \subsection{Expandable Models}
% The current most used approach for expanding a CNN model is to retrain the model. This is done by, recreating an entire new model that does the new task, using the older model as a base for the new model \cite{amazon-rekognition}, or using a pretrained model as a base and training the last few layers.
% There are also unsupervised learning methods that do not have a fixed number of classes. While this method would work as an expandable model method, it would not work for the purpose of this project. This project requires that the model has a specific set of labels which does not work with unsupervised learning which has unlabelled data. Some technics that are used for unsupervised learning might be useful in the process of creating expandable models.
\subsection{Machine learning libraries}
While there are various machine learning libraries, the two bigger ones are Tensorflow and PyTorch.
This section will compare the two different libraries.
TensorFlow \cite{tensorflow2015-whitepaper} is an open-source machine learning platform created by Google to develop their production and research systems.
PyTorch \cite{pytorch} is an open-source machine learning library developed by Meta to power their systems.
While both libraries can achieve the same tasks with similar level of accuracy \cite{pytorch-vs-tensorflow-1}, PyTorch is mostly used in research oriented applications rather than applications that might require deployment \cite{pytorch-vs-tensorflow-1,pytorch-vs-tensorflow-2}.
This is generally attributed to the maturity of TensorFlow and TensorFlow's ability to create static graphs, which are optimised for inference.
More important for the project is compatibility with other technologies that the project will use.
In this case, TensorFlow has native support for Go while PyTorch does not.
Which due to Tensorflow's advanced in deployment and compatibility the clear choice for the project.
\subsection{Summary}
The technical review of current systems, shows that there are current systems that exist that can perform image classification tasks, but they are not friendly in ways to easily expand currently existing models.
The current methods that exist for image classification seem to have reached a classification accuracy and efficiency that make a project like this feasible.
Model architectures such as ResNet, and EfficientNet have been able to perform image classification on large sets of models and achieve higher than human performances.
Taking these architectures in mind the system should be able to create machine learning models that perform equally well.
As for what technologies to use to build such models TensorFlow seams to be the correct choice as it has better performance when deploying to production, and can more easily integrate with the chosen web technologies.
\pagebreak

1343
report/report.bbl Normal file

File diff suppressed because it is too large Load Diff

2429
report/report.bcf Normal file

File diff suppressed because it is too large Load Diff

19
report/report.blg Normal file
View File

@ -0,0 +1,19 @@
[0] Config.pm:307> INFO - This is Biber 2.19
[0] Config.pm:310> INFO - Logfile is 'report.blg'
[28] biber:340> INFO - === Wed May 15, 2024, 05:17:32
[34] Biber.pm:419> INFO - Reading 'report.bcf'
[59] Biber.pm:979> INFO - Found 37 citekeys in bib section 0
[65] Biber.pm:4419> INFO - Processing section 0
[69] Biber.pm:4610> INFO - Looking for bibtex file '../main.bib' for section 0
[70] bibtex.pm:1713> INFO - LaTeX decoding ...
[82] bibtex.pm:1519> INFO - Found BibTeX data source '../main.bib'
[181] UCollate.pm:68> INFO - Overriding locale 'en-US' defaults 'variable = shifted' with 'variable = non-ignorable'
[181] UCollate.pm:68> INFO - Overriding locale 'en-US' defaults 'normalization = NFD' with 'normalization = prenormalized'
[181] Biber.pm:4239> INFO - Sorting list 'none/global//global/global' of type 'entry' with template 'none' and locale 'en-US'
[181] Biber.pm:4245> INFO - No sort tailoring available for locale 'en-US'
[190] bbl.pm:660> INFO - Writing 'report.bbl' with encoding 'UTF-8'
[195] bbl.pm:763> INFO - Output to report.bbl
[195] Biber.pm:131> WARN - legacy month field 'November' in entry 'lecun-98' is not an integer - this will probably not sort properly.
[195] Biber.pm:131> WARN - legacy month field 'Apr' in entry 'caltech256' is not an integer - this will probably not sort properly.
[195] Biber.pm:131> WARN - BibTeX subsystem: /tmp/biber_tmp_nCQC/3b92c3a43883b50258e417775889aed6_1391351.utf8, line 387, warning: 130 characters of junk seen at toplevel
[195] Biber.pm:133> INFO - WARNINGS: 3

55
report/report.out Normal file
View File

@ -0,0 +1,55 @@
\BOOKMARK [1][-]{section.1}{\376\377\000I\000n\000t\000r\000o\000d\000u\000c\000t\000i\000o\000n}{}% 1
\BOOKMARK [2][-]{subsection.1.1}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000B\000a\000c\000k\000g\000r\000o\000u\000n\000d}{section.1}% 2
\BOOKMARK [2][-]{subsection.1.2}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000M\000o\000t\000i\000v\000a\000t\000i\000o\000n\000s}{section.1}% 3
\BOOKMARK [2][-]{subsection.1.3}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000A\000i\000m}{section.1}% 4
\BOOKMARK [2][-]{subsection.1.4}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000O\000b\000j\000e\000c\000t\000i\000v\000e\000s}{section.1}% 5
\BOOKMARK [2][-]{subsection.1.5}{\376\377\000S\000u\000c\000c\000e\000s\000s\000\040\000C\000r\000i\000t\000e\000r\000i\000a}{section.1}% 6
\BOOKMARK [2][-]{subsection.1.6}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000S\000t\000r\000u\000c\000t\000u\000r\000e}{section.1}% 7
\BOOKMARK [1][-]{section.2}{\376\377\000L\000i\000t\000e\000r\000a\000t\000u\000r\000e\000\040\000a\000n\000d\000\040\000T\000e\000c\000h\000n\000i\000c\000a\000l\000\040\000R\000e\000v\000i\000e\000w}{}% 8
\BOOKMARK [2][-]{subsection.2.1}{\376\377\000E\000x\000i\000s\000t\000i\000n\000g\000\040\000C\000l\000a\000s\000s\000i\000f\000i\000c\000a\000t\000i\000o\000n\000\040\000P\000l\000a\000t\000f\000o\000r\000m\000s}{section.2}% 9
\BOOKMARK [2][-]{subsection.2.2}{\376\377\000R\000e\000q\000u\000i\000r\000e\000m\000e\000n\000t\000s\000\040\000o\000f\000\040\000I\000m\000a\000g\000e\000\040\000C\000l\000a\000s\000s\000i\000f\000i\000c\000a\000t\000i\000o\000n\000\040\000M\000o\000d\000e\000l\000s}{section.2}% 10
\BOOKMARK [2][-]{subsection.2.3}{\376\377\000M\000e\000t\000h\000o\000d\000\040\000o\000f\000\040\000I\000m\000a\000g\000e\000\040\000C\000l\000a\000s\000s\000i\000f\000i\000c\000a\000t\000i\000o\000n\000\040\000M\000o\000d\000e\000l\000s}{section.2}% 11
\BOOKMARK [2][-]{subsection.2.4}{\376\377\000W\000e\000l\000l\000-\000k\000n\000o\000w\000n\000\040\000m\000o\000d\000e\000l\000s}{section.2}% 12
\BOOKMARK [2][-]{subsection.2.5}{\376\377\000M\000a\000c\000h\000i\000n\000e\000\040\000l\000e\000a\000r\000n\000i\000n\000g\000\040\000l\000i\000b\000r\000a\000r\000i\000e\000s}{section.2}% 13
\BOOKMARK [2][-]{subsection.2.6}{\376\377\000S\000u\000m\000m\000a\000r\000y}{section.2}% 14
\BOOKMARK [1][-]{section.3}{\376\377\000S\000e\000r\000v\000i\000c\000e\000\040\000A\000n\000a\000l\000y\000s\000i\000s\000\040\000a\000n\000d\000\040\000R\000e\000q\000u\000i\000r\000e\000m\000e\000n\000t\000s}{}% 15
\BOOKMARK [2][-]{subsection.3.1}{\376\377\000S\000e\000r\000v\000i\000c\000e\000\040\000S\000t\000r\000u\000c\000t\000u\000r\000e}{section.3}% 16
\BOOKMARK [2][-]{subsection.3.2}{\376\377\000R\000e\000s\000o\000u\000r\000c\000e\000s}{section.3}% 17
\BOOKMARK [3][-]{subsubsection.3.2.1}{\376\377\000C\000o\000m\000p\000u\000t\000e\000\040\000R\000e\000s\000o\000u\000r\000c\000e\000s}{subsection.3.2}% 18
\BOOKMARK [3][-]{subsubsection.3.2.2}{\376\377\000S\000t\000o\000r\000a\000g\000e}{subsection.3.2}% 19
\BOOKMARK [2][-]{subsection.3.3}{\376\377\000U\000s\000e\000r\000\040\000i\000n\000t\000e\000r\000f\000a\000c\000e}{section.3}% 20
\BOOKMARK [2][-]{subsection.3.4}{\376\377\000A\000P\000I}{section.3}% 21
\BOOKMARK [2][-]{subsection.3.5}{\376\377\000D\000a\000t\000a\000\040\000M\000a\000n\000a\000g\000e\000m\000e\000n\000t}{section.3}% 22
\BOOKMARK [2][-]{subsection.3.6}{\376\377\000S\000u\000m\000m\000a\000r\000y}{section.3}% 23
\BOOKMARK [1][-]{section.4}{\376\377\000S\000e\000r\000v\000i\000c\000e\000\040\000D\000e\000s\000i\000g\000n}{}% 24
\BOOKMARK [2][-]{subsection.4.1}{\376\377\000S\000t\000r\000u\000c\000t\000u\000r\000e\000\040\000o\000f\000\040\000t\000h\000e\000\040\000S\000e\000r\000v\000i\000c\000e}{section.4}% 25
\BOOKMARK [2][-]{subsection.4.2}{\376\377\000I\000n\000t\000e\000r\000a\000c\000t\000i\000n\000g\000\040\000w\000i\000t\000h\000\040\000t\000h\000e\000\040\000s\000e\000r\000v\000i\000c\000e}{section.4}% 26
\BOOKMARK [2][-]{subsection.4.3}{\376\377\000A\000P\000I}{section.4}% 27
\BOOKMARK [2][-]{subsection.4.4}{\376\377\000G\000e\000n\000e\000r\000a\000t\000i\000o\000n\000\040\000o\000f\000\040\000M\000o\000d\000e\000l\000s}{section.4}% 28
\BOOKMARK [2][-]{subsection.4.5}{\376\377\000M\000o\000d\000e\000l\000s\000\040\000T\000r\000a\000i\000n\000i\000n\000g}{section.4}% 29
\BOOKMARK [2][-]{subsection.4.6}{\376\377\000S\000u\000m\000m\000a\000r\000y}{section.4}% 30
\BOOKMARK [1][-]{section.5}{\376\377\000S\000e\000r\000v\000i\000c\000e\000\040\000I\000m\000p\000l\000e\000m\000e\000n\000t\000a\000t\000i\000o\000n}{}% 31
\BOOKMARK [2][-]{subsection.5.1}{\376\377\000S\000t\000r\000u\000c\000t\000u\000r\000e\000\040\000o\000f\000\040\000t\000h\000e\000\040\000S\000e\000r\000v\000i\000c\000e}{section.5}% 32
\BOOKMARK [2][-]{subsection.5.2}{\376\377\000W\000e\000b\000\040\000A\000p\000p\000l\000i\000c\000a\000t\000i\000o\000n}{section.5}% 33
\BOOKMARK [2][-]{subsection.5.3}{\376\377\000A\000P\000I}{section.5}% 34
\BOOKMARK [2][-]{subsection.5.4}{\376\377\000G\000e\000n\000e\000r\000a\000t\000i\000o\000n\000\040\000a\000n\000d\000\040\000T\000r\000a\000i\000n\000i\000n\000g\000\040\000o\000f\000\040\000M\000o\000d\000e\000l\000s}{section.5}% 35
\BOOKMARK [2][-]{subsection.5.5}{\376\377\000M\000o\000d\000e\000l\000\040\000I\000n\000f\000e\000r\000e\000n\000c\000e}{section.5}% 36
\BOOKMARK [2][-]{subsection.5.6}{\376\377\000R\000u\000n\000n\000e\000r}{section.5}% 37
\BOOKMARK [2][-]{subsection.5.7}{\376\377\000S\000u\000m\000m\000a\000r\000y}{section.5}% 38
\BOOKMARK [1][-]{section.6}{\376\377\000L\000e\000g\000a\000l\000,\000\040\000S\000o\000c\000i\000e\000t\000a\000l\000,\000\040\000E\000t\000h\000i\000c\000a\000l\000\040\000a\000n\000d\000\040\000P\000r\000o\000f\000e\000s\000s\000i\000o\000n\000a\000l\000\040\000C\000o\000n\000s\000i\000d\000e\000r\000a\000t\000i\000o\000n\000s}{}% 39
\BOOKMARK [2][-]{subsection.6.1}{\376\377\000L\000e\000g\000a\000l\000\040\000I\000s\000s\000u\000e\000s}{section.6}% 40
\BOOKMARK [2][-]{subsection.6.2}{\376\377\000S\000o\000c\000i\000a\000l\000\040\000I\000s\000s\000u\000e\000s}{section.6}% 41
\BOOKMARK [2][-]{subsection.6.3}{\376\377\000E\000t\000h\000i\000c\000a\000l\000\040\000I\000s\000s\000u\000e\000s}{section.6}% 42
\BOOKMARK [2][-]{subsection.6.4}{\376\377\000P\000r\000o\000f\000e\000s\000s\000i\000o\000n\000a\000l\000\040\000I\000s\000s\000u\000e\000s}{section.6}% 43
\BOOKMARK [1][-]{section.7}{\376\377\000S\000e\000r\000v\000i\000c\000e\000\040\000E\000v\000a\000l\000u\000a\000t\000i\000o\000n}{}% 44
\BOOKMARK [2][-]{subsection.7.1}{\376\377\000T\000e\000s\000t\000i\000n\000g\000\040\000t\000h\000e\000\040\000m\000o\000d\000e\000l\000\040\000c\000r\000e\000a\000t\000i\000o\000n}{section.7}% 45
\BOOKMARK [2][-]{subsection.7.2}{\376\377\000A\000P\000I\000\040\000P\000e\000r\000f\000o\000r\000m\000a\000n\000c\000e\000\040\000T\000e\000s\000t\000i\000n\000g}{section.7}% 46
\BOOKMARK [2][-]{subsection.7.3}{\376\377\000U\000s\000a\000b\000i\000l\000i\000t\000y}{section.7}% 47
\BOOKMARK [2][-]{subsection.7.4}{\376\377\000S\000u\000m\000m\000a\000r\000y}{section.7}% 48
\BOOKMARK [1][-]{section.8}{\376\377\000C\000r\000i\000t\000i\000c\000a\000l\000\040\000R\000e\000v\000i\000e\000w\000\040\000o\000f\000\040\000P\000r\000o\000j\000e\000c\000t\000\040\000O\000u\000t\000c\000o\000m\000e\000s}{}% 49
\BOOKMARK [2][-]{subsection.8.1}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000O\000b\000j\000e\000c\000t\000i\000v\000e\000s}{section.8}% 50
\BOOKMARK [2][-]{subsection.8.2}{\376\377\000A\000\040\000r\000e\000t\000r\000o\000s\000p\000e\000c\000t\000i\000v\000e\000\040\000a\000n\000a\000l\000y\000s\000i\000s\000\040\000o\000f\000\040\000t\000h\000e\000\040\000d\000e\000v\000e\000l\000o\000p\000m\000e\000n\000t\000\040\000p\000r\000o\000c\000e\000s\000s}{section.8}% 51
\BOOKMARK [2][-]{subsection.8.3}{\376\377\000P\000r\000o\000j\000e\000c\000t\000\040\000S\000h\000o\000r\000t\000c\000o\000m\000i\000n\000g\000s\000\040\000a\000n\000d\000\040\000I\000m\000p\000r\000o\000v\000e\000m\000e\000n\000t\000s}{section.8}% 52
\BOOKMARK [2][-]{subsection.8.4}{\376\377\000F\000u\000t\000u\000r\000e\000\040\000W\000o\000r\000k}{section.8}% 53
\BOOKMARK [2][-]{subsection.8.5}{\376\377\000C\000o\000n\000c\000l\000u\000s\000i\000o\000n}{section.8}% 54
\BOOKMARK [1][-]{section.9}{\376\377\000R\000e\000f\000e\000r\000e\000n\000c\000e\000s}{}% 55

87
report/report.run.xml Normal file
View File

@ -0,0 +1,87 @@
<?xml version="1.0" standalone="yes"?>
<!-- logreq request file -->
<!-- logreq version 1.0 / dtd version 1.0 -->
<!-- Do not edit this file! -->
<!DOCTYPE requests [
<!ELEMENT requests (internal | external)*>
<!ELEMENT internal (generic, (provides | requires)*)>
<!ELEMENT external (generic, cmdline?, input?, output?, (provides | requires)*)>
<!ELEMENT cmdline (binary, (option | infile | outfile)*)>
<!ELEMENT input (file)+>
<!ELEMENT output (file)+>
<!ELEMENT provides (file)+>
<!ELEMENT requires (file)+>
<!ELEMENT generic (#PCDATA)>
<!ELEMENT binary (#PCDATA)>
<!ELEMENT option (#PCDATA)>
<!ELEMENT infile (#PCDATA)>
<!ELEMENT outfile (#PCDATA)>
<!ELEMENT file (#PCDATA)>
<!ATTLIST requests
version CDATA #REQUIRED
>
<!ATTLIST internal
package CDATA #REQUIRED
priority (9) #REQUIRED
active (0 | 1) #REQUIRED
>
<!ATTLIST external
package CDATA #REQUIRED
priority (1 | 2 | 3 | 4 | 5 | 6 | 7 | 8) #REQUIRED
active (0 | 1) #REQUIRED
>
<!ATTLIST provides
type (static | dynamic | editable) #REQUIRED
>
<!ATTLIST requires
type (static | dynamic | editable) #REQUIRED
>
<!ATTLIST file
type CDATA #IMPLIED
>
]>
<requests version="1.0">
<internal package="biblatex" priority="9" active="0">
<generic>latex</generic>
<provides type="dynamic">
<file>report.bcf</file>
</provides>
<requires type="dynamic">
<file>report.bbl</file>
</requires>
<requires type="static">
<file>blx-dm.def</file>
<file>blx-compat.def</file>
<file>biblatex.def</file>
<file>standard.bbx</file>
<file>numeric.bbx</file>
<file>numeric-comp.bbx</file>
<file>ieee.bbx</file>
<file>numeric.cbx</file>
<file>biblatex.cfg</file>
<file>english.lbx</file>
</requires>
</internal>
<external package="biblatex" priority="5" active="0">
<generic>biber</generic>
<cmdline>
<binary>biber</binary>
<infile>report</infile>
</cmdline>
<input>
<file>report.bcf</file>
</input>
<output>
<file>report.bbl</file>
</output>
<provides type="dynamic">
<file>report.bbl</file>
</provides>
<requires type="dynamic">
<file>report.bcf</file>
</requires>
<requires type="editable">
<file>../main.bib</file>
</requires>
</external>
</requests>

View File

@ -1,63 +1,499 @@
%%% Preamble
\documentclass[11pt, a4paper]{article}
\documentclass[11pt, a4paper, twoside]{article}
\usepackage[english]{babel} % English language/hyphenation
\usepackage{url}
\usepackage{tabularx}
\usepackage{pdfpages}
\usepackage{float}
\usepackage{graphicx}
\graphicspath{ {../images for report/} }
\include{settings.tex}
\usepackage{hyperref}
\hypersetup{
colorlinks,
citecolor=black,
filecolor=black,
linkcolor=black,
urlcolor=black
}
% Write the approved title of your dissertation
\title{Image Classification as a Software Platform}
\usepackage{cleveref}
% Write your full name, as in University records
\author{Andre Henriques}
%%% Custom headers/footers (fancyhdr package)
\usepackage{fancyhdr}
\pagestyle{fancyplain}
\fancyhead{} % No page header
\fancyfoot[L]{} % Empty
\fancyfoot[C]{\thepage} % Pagenumbering
\fancyfoot[R]{} % Empty
\renewcommand{\headrulewidth}{0pt} % Remove header underlines
\renewcommand{\footrulewidth}{0pt} % Remove footer underlines
\setlength{\headheight}{13.6pt}
\usepackage[style=numeric,sorting=none,backend=biber]{biblatex}
\addbibresource{../main.bib}
\title{
\normalfont \normalsize \textsc{University of Surrey} \\ %[25pt]
\Huge Final year project \\
}
\author{
\normalfont \normalsize
Andre Henriques\\[-3pt] \normalsize
\today
}
\date{}
%%% Begin document
\begin{document}
\include{start}
\include{intro}
\include{lit}
\include{sanr}
\include{design}
\maketitle
\newpage
\section{Service Implementation} \label{sec:si}
\tableofcontents
\newpage
This chapter will discuss how the service followed some possible designs to achieve a working system.
The design path that was decided matches what made sense for the scale and needs of the project.
\section{Introduction}
\subsection{Structure of the Service}
\newpage
The structure of the service matches the designed structure, as it can be seen in Figure \ref{fig:simplified_service_diagram}.
\begin{figure}[h!]
\centering
\includegraphics[height=0.4\textheight]{system_diagram}
\caption{Simplified diagram of the service}
\label{fig:simplified_service_diagram}
\end{figure}
The implementation contains: Web App; Web server, which serves the Web App; API; Training Runners; Model Runners.
This differs from the designed solution, as it contains an extra nginx reverse proxy server \cite{nginx}.
The reverse proxy is requireed as it allows for the API and the webpage to be accessible from them same domain.
The selected database was PostgresSQL \cite{postgressql} as it is one of the most advanced open source databases available.
The database stores all data required for the system to work, with the exeption of uploaded images and model files.
The rest of this chapter will discuss how each individual part of the system was implemented.
\subsection{Web Application} \label{web-app-design}
The web application (WEB App) is the chosen user interface to control the service.
This subsection discusses details of the user flows and implementation of the application.
\subsubsection*{Implementation Details}
The Web APP is a single-page application (SPA).
The SPA architecture is one of the most prevalent architectures that exists nowadays.
It allows for the fast transitions between pages without having a full reload of the website.
Since this implementation separated the API and the Web App, it makes the use of server-side rendering more complex and less efficient.
As, the server would have to first request the API for information to build the web page and then send it to the users' device.
Therefore, the system will use client-side rendering only, allowing for the users' device to request the API directly for more information.
There exist currently many frameworks to create SPAs.
I selected Svelte \cite{svelte} for this project.
I selected Svelte because it is been one of the most liked frameworks to work with in the last years, accordingly to the State of JS survey \cite{state-of-js-2022}.
It is also one of the best performant frameworks that is currently available that has extremity good performance \cite{js-frontend-frameworks-performance}.
I also already have experience with Svelte.
I will be using Svelte with the SvelteKit framework \cite{svelte-kit} which greatly improves the developer experience.
SvelteKit allows for the easy creation of SPAs with a good default web router.
When deploying into a production enviroment the static adapter can be used to generate a static HTML and JavaScript files.
This static files can be then hosted in a more efficient http server, other than the one running on NodeJs.
The web application uses the API to control the functionality of the service.
This implementation allows users of the application to do everything that the application does with the API, which is ideal in a SaaS project.
The communication with the API, when correcly consigured, uses HTTPS to make this communication encrypted and safe.
\subsubsection*{Service authentication} \label{sec:impl:service-auth}
\begin{figure}[h!]
\centering
\includegraphics[width=\textwidth]{service_authentication}
\caption{Simplified Diagram of User Authentication}
\label{fig:simplified_auth_diagram}
\end{figure}
%TODO task about the above image
The user uses an email and password to Sign In or Register with the application.
This is sent to the server and stored in a user account.
The Password is stored hashed using bcrypt \cite{bycrpt}.
In the future, other methods of authentication might be provided; like using Google's OAuth.
Once logged In, the user will be able to use the application and manage tokens that were emitted for this application.
This allows the user to manage what services have access to the account. % and the usage that those services have used.
On the web app, the user can manage existing tokens.
Guaranteeing that only the clients that should be accessing the information are.
In the management screen, which can be seen in Figure \ref{fig:token_page}, the user can remove, and create tokens.
\begin{figure}[H]
\centering
\includegraphics[width=0.5\textwidth]{token_page}
\caption{Screenshot of web application on the token control section.}
\label{fig:token_page}
\end{figure}
\subsubsection*{Model Management}
\begin{figure}[h!]
\centering
\includegraphics[width=\textwidth]{models_flow}
\caption{Simplified Diagram of Model management.}
\label{fig:simplified_model_diagram}
\end{figure}
Figure \ref{fig:simplified_model_diagram} shows the steps that the user takes to use a model.
First, the user creates the model.
In this step, the user uploads a sample image of what the model will be handling.
This image is used to define what the kinds of images the model will be able to intake.
This is done in the page shown in Figure \ref{fig:create_model}, the user provides a name for the model and an image and then presses the button create.
\begin{figure}[H]
\centering
\includegraphics[width=0.9\textwidth]{create_model}
\caption{Screenshot of web application on the page that allows the creation of a new model.}
\label{fig:create_model}
\end{figure}
The user is then shown the model page, which contains all the information about a model, which can be seen in Figure \ref{fig:model_page}.
\begin{figure}[H]
\centering
\includegraphics[width=0.9\textwidth]{base_model_page}
\caption{Screenshot of the web application on the page shows basic information about the model.}
\label{fig:model_page}
\end{figure}
This page contains a set of tabs a top.
Each tab gives different insight about the model.
The ``Model'' tab, contains only relevant actions that the user can take.
In Figure \ref{fig:model_page}, the user has created a model but has not added training data, so the page shows a section where the user can input training data.
The ``Model Data'' tab contains a more detailed view about data that has been updated.
Currently, the system does not support resizing of images that are different from the one uploaded at the creation step.
This was done to guarantee that the image that the user wants to classify is unmodified.
Moving the responsibility of cropping and resizing to the user.
In the future, systems could be implemented that allow the user to select how an image can be cropped.
The second step is uploading the rest of the dataset.
This can be done via the ``Model'' tab or via the ``Model Data'' tab that becomes available when the data of the model is first uploaded.
In this tab, the user can add and remove images, as well as create new classes for the model.
The page also shows some useful information, such as the distribution of the dataset, which can be seen in \ref{fig:model_data_tab}.
\begin{figure}[H]
\centering
\includegraphics[width=0.9\textwidth]{model_data_tab}
\caption{Screenshot of web application part of the ``Model Data'' tab.}
\label{fig:model_data_tab}
\end{figure}
This information can be useful to more advanced users that might decide to gather more data to balance the dataset.
To upload the reset of the data set, the user can upload a zip file that contains a set of classes and images corresponding to that class.
That zip file is processed and images and classes are created.
The user is given instruction on how to create the zip file so that the system can easily process the data, the upload set can be seen in Figure \ref{fig:upload_data_section}.
This process was original slow as the system did not have the capabilities to parallelize the process of importing the images, but this was implemented, and the import process was improved.
The improved process now takes a few seconds to process and verify the entirety of the dataset, making the experience for the end user better.
Alternatively, the user can use the API to create new classes and upload images.
\begin{figure}[H]
\centering
\includegraphics[width=0.9\textwidth]{upload_data_page}
\caption{Screenshot of web application upload zip step of the model page.}
\label{fig:upload_data_section}
\end{figure}
After all the images that are required for training are uploaded, the user can go to the training step.
This step will appear both in the main tab of the model page and in the dataset tab. Once the user instructs the system to start training, the model page will become the training page, and it will show the progress of the training of the model.
During this step, the system automatically trains the model.
After the system trains a model that meets the specifications set by the user, the service will make the model available for the user to use.
When the model is finished training, the user can use the model to run inference tasks on images.
To achieve this, the user can either use the API to submit a classification task or use the tasks tab in the web platform.
In the tasks tab, which can be seen in Figure \ref{fig:upload_data_section}, the user can see current and previous tasks.
The users can see what tasks were performed and their results.
The user can also inform the service if the task that was performed did return the correct results.
This information can be used to keep track of the real accuracy of the model.
The information can be used to see if the model needs refinement.
The system can add the classes that failed to return the correct result to a list of the original data, to be used in case of retraining the model.
\begin{figure}[H]
\centering
\includegraphics[height=0.95\textheight]{model_task_tab}
\caption{Screenshot of web application on the tasks tab.}
\label{fig:upload_data_section}
\end{figure}
\subsubsection*{Advanced Model Management}
\begin{figure}[H]
\centering
\includegraphics[width=\textwidth]{models_advanced_flow}
\caption{Simplified Diagram of Advanced Model management.}
\label{fig:simplified_model_advanced_diagram}
\end{figure}
Figure \ref{fig:simplified_model_advanced_diagram} shows the steps that the user takes to use a model.
The steps are very similar to the normal model management.
The user would follow all the steps that are required for normal model creation and training.
At the end of the process, the user will be able to add new data to the model and retrain it.
To achieve that, the user would simply go to the data tab and create a new class, which the Figure \ref{fig:expand_class_part} shows.
Once a new class is added, the webpage will inform the user that the model can be retrained.
The user might choose to retrain the model now or more new classes and retrain later.
\begin{figure}[H]
\centering
\includegraphics[width=0.6\textwidth]{expand_class_part}
\caption{Screenshot of web application on the expand part of the ``Model Data'' tab.}
\label{fig:expand_class_part}
\end{figure}
During the entire process of creating new classes in the model and retraining the model, the user can still perform all the classifications tasks they desire.
\subsubsection*{Task Management}
Task management is the section of the website is where uses can manage their tasks. This includes training and classification tasks.
Users in this tab can see what is the progress, and results of their tasks.
The webpage also provides nice, easy to see statistics on the task results, allowing the user to see how the model is performing.
Which is shown on Figure \ref{fig:upload_data_section}
On the administrator, users should be able to change the status of tasks as well as see a more comprehensive view on how the tasks are being performed.
Administrator users can see the current status of runners, as well as which task the runners are doing, the Figure \ref{fig:runner_page} shows the runner visualisation page.
\begin{figure}[H]
\centering
\includegraphics[width=0.6\textwidth]{runner_page}
\caption{Screenshot of web application on the runner administration page.}
\label{fig:runner_page}
\end{figure}
\subsection{API}
The API was implemented as a multithreaded Go \cite{go} server.
The application, on launch, loads a configuration file and connects to the database.
After connecting to the database, the application performs pre-startup checks to make sure no tasks that were interrupted via a server restart and were not left in an unrecoverable state.
Once the checks are done, the application creates workers, which will be explained in section \ref{impl:runner}, which when completed the API server is finally started up.
Information about the API is shown around the web page so that the user can see information about the API right next to where the user would normally do the action, providing a good user interface.
As, the user can get information about right where they would normally do the action, as it can be seen in Figure \ref{fig:code_demo}.
\begin{figure}[H]
\centering
\includegraphics[width=0.6\textwidth]{code_demo}
\caption{Screenshot of the web application that shows the explanation of the API call.}
\label{fig:code_demo}
\end{figure}
This server will take JSON and multipart form data requests, the requests are processed, and answered with a JSON response.
The multipart requests are required due to JSON's inability to transmit binary data, which will make the uploading of images extremely inefficient.
Those images would have to be transformed into binary data and then uploaded as a byte array or encoded as base64 and uploaded.
Either of those options is extremely inefficient.
Therefore, there is a need to use multipart form requests are required to allow the easy uploading of binary files.
Go was selected as the language to implement the backend due to various of its advantages.
Go has extremely fast compilations which allows for rapid development, and iteration.
It has a very minimal runtime which allows it to be faster, than heavy runtime languages such as JavaScript.
It is also a simple language, which helps maintain the codebase.
% TODO cite cgo tensorflow and torch
The Go language integrates well with C libraries, which allows it access to machine learning libraries like TensorFlow or Lib Torch.
\subsubsection*{Authentication}
The API allows users to login, which emits a token, and once logged in, manually create tokens.
While using the web application, this is done transparently, but it can also be manually done via the respective API calls.
During the login process, the service checks to see if the user is registered and if the password provided during the login matches the stored hash.
Upon verifying the user, a token is emitted.
Once a user is logged in they can then create more tokens as seen in section \ref{sec:impl:service-auth}.
While using the API the user should only use created tokens in the settings page as those tokens are named, and have controllable expiration dates.
This is advantageous from a security perspective, as the user can manage who has access to the API.
If the token gets leaked, the user can then delete the named token, to guarantee the safety of his access.
The token can then be used in the ``token'' header as proof to the API that the user is authenticated.
\subsection{Generation and Training of Models}
Model generation happens on the API server, the API server analyses what the image that was provided and generates several model candidates accordingly.
The number of model candidates is user defined.
The model generation subsystem decides the structure of the model candidates based on the image size, it prioritises the smaller models for smaller images and convolution networks with bigger images.
The depth is controlled both by the image size and number of outputs, models candidates that need to be expanded are generated with bigger values to account for possible new values.
It tries to generate the optimal size if only one model is requested.
If more than one is requested then the generator tries to generate models of various types and sizes, so if there is possible smaller model it will also be tested.
Model training happens in a runner, more information about runners will be explained in section \ref{impl:runner}.
% TODO explore this a bit more
Model training was implemented using TensorFlow. % \cite{tensorflow}.
Normally, when using go with machine learning, only the prediction is run in go and the training happens in python.
The training system was implemented that way.
The runner, when it needs to perform training it generates a python script tailored to the model candidate that needs to be trained, then runs the that python script, and monitors the result of the python script.
While the python script is running, it takes use of the API to inform the runner of epoch and accuracy changes.
The during train, the runner takes a round-robin approach.
It trains every model candidate for a few epochs, then compares the different models candidates.
If there is too much difference in accuracy, from the best model to the worst model, then the system might decide not to continue training a certain candidate and focus the training resources on candidates that are performing better.
Once one candidate archives the target accuracy, which is user defined, the training system stops training the models candidates.
The model candidate that achieved the target accuracy is then promoted to the model, and the other candidates are removed.
The model now can be used to predict the labels for any image that the user decides to upload.
\subsubsection*{Expandable Models}
Expandable models follow mostly the same process as the normal models.
First, bigger model candidates are generated.
Then the models are training using the same technic.
At the end, after the model candidate has been promoted to the full model, the system starts another python process that loads the just generated model and splits into a base model and a head model.
With these two separate models, the system is now ready to start classifying new images.
\subsubsection*{Expanding Expandable Models}
During the expanding process, the generation system creates a new head candidate that matches the newly added classes.
The base model, that was created in the original training process, is used with all available data to train the head candidate to perform the classification tasks.
The training process is similar to the normal training system, but this uses a different training script.
Once the model has finished training and the system meets the accuracy requirements, then makes the new head available for classification.
\subsection{Model Inference}
Model inference also runs inside a runner.
However, inference runs internally on go, instead of creating tailored scripts for training using python.
Once a classification request is received by the API, the uploaded image is checked to see if the model will accept it.
If the model is capable of accepting the image, it is temporarily saved to disk and then a classification task is created.
Eventually, a runner will pick up the classification task.
Upon pickup, the runner will load the model and run the image through it, the results are then matched with the stored classes in the database.
The system then stores the class with the highest probability of matching the image, according to the model, in the results of the task.
The user then can finally use the API to obtain the results of the model.
\subsubsection*{Expandable Models}
For expandable models, the inference step is very similar to the normal models.
The runner first loads the base model and runs the image through the model, the resultant features are then stored.
Once the features are obtained, the system then runs those features to the various possible heads, and the results are then matched with the stored classes, and the one with the height probability is then selected.
\subsection{Runner} \label{impl:runner}
Runners are the name used to reference to the software that can perform CPU or GPU intensive tasks without halting the main API server.
Architecturally, they were implemented as a controller and worker pattern.
When the application that runs the main application starts, the system creates an orchestrator, this orchestrator is a piece of software that decides what work each runner is doing.
The orchestrator runs on go routine created at startup.
During the startup, the orchestrator by obtaining values from the configuration file.
Those values define the number of local runners.
These runners, which are started up by the orchestrator, act as local runners, runners that are running on the same machine as the main server.
Local runners are useful when running the main server on a machine that also has GPU power available to it, and in testing.
Local runners, run inside a go routine, this allows the runners and the orchestrator to communicate using go channels, which are the easiest way to communicate between two go routines.
The orchestrator is constantly waiting to receive either for a timer-based event or a runner-based event.
Timer-based events happen when the orchestrator internal clock informs it of needing to check if tasks are available to run.
The time at which this clock ticks in configured in the settings of the app.
Upon receiving a timer-based event, the orchestrator then checks if there is a new task available for it to run and if there are any runners available for the task to run on.
If there are tasks available, then the orchestrator instructors the runner to pick up the task and run it.
Runner-based events happen when a runner finishes running a task or crashes while trying to do it.
Upon receiving a runner event, the orchestrator checks if it is a success or a failure message.
If it is a failure message and the runner is a local runner, then the orchestrator just restarts the runner.
Upon restart, it adds the runner to the list of available runners.
If the runner is a remote runner, the orchestrator marks the runner as failed and stops sending messages to the runner until the runner informs the service again that is available.
If the message is of success, then the orchestrator just adds the runner to the list of viable runners, independently if the runner is remote or not.
% TODO talk more about remote runners
% TODO talk about how the runner loads images
\subsection{Summary}
This chapter went into the details of how the designed was implemented.
The design was envisioned to be the best possible version of this service, but scope was restrained to the necessities of the system while it was being developed.
And possible features that would make the implemented application closer to the ideal design could have been implemented if there was higher need during the development timeline.
This will be more discussed in chapter \ref{sec:crpo}.
\pagebreak
\section{Legal, Societal, Ethical and Professional Considerations} \label{sec:lsec}
This section will address possible legal, societal, ethical and professional issues that might arise from the deployment of the software being designed.
The Self-Assessment for Governance and Ethics (SAGE) form has addressed, and it is submitted along with the report.
\subsection{Legal Issues}
Legal issues can occur due to the data being stored by the service.
The service collects, the least amount of sensitive information, from the users who directly use the service.
That data that is collected while being sensitive is required to be able to authenticate the user, such as name, email, and password.
To safeguard that information, the system will be using industry standards to guarantee data security of that data.
Legal issues might occur due to image uploaded images. For example, those images could be copyrighted, or the images could be confidential. The service is designed to provide ways to allow users to host their images without having to host the images itself, moving the legal requirement to the management of the data to the user of the system.
\subsubsection*{GDPR}
The General Data Protection Regulation (GDPR) (GDPR, 2018) is a data protection and privacy law in the European Union and the European Economic Area, that has also been implemented into British law.
The main objective of the GDPR is to minimise the data collected by the application for purposes that are not the used in the application, as well as giving users the right to be forgotten.
The application collects only personal data needed to authenticate the user, and data that is generated during the normal usage of the application.
All the data that is related to the user can be deleted.
The system will prevent any new work that is related to the data, that was requested to be deleted.
Once the there is no more work that requires the data being done, the system will remove all relevant identifiable references to that data.
\subsection{Social Issues}
The web application was designed to be easy to use and there tries to consider all accessibility requirements.
% TODO talk about this
% The service itself could raise issues of taking jobs that are currently done by humans.
% This is less problematic as time has shown that the jobs just change, instead of manually classifying the images, the job transforms from the classifying all the images that are needed to maintain and verifying that the data being input to the model is correct.
\subsection{Ethical Issues}
While the service itself does not raise any ethical concerns. The data that the service will process could raise ethical complications.
For example, if the service gets acquired by a company that also wants to use the data provided to the system for other reasons.
\subsection{Professional Issues}
As a member of the British Computer Society (BCS), it is important to follow the Code of Conduct practices. The code of conduit contains 4 key principles.
\subsubsection*{Public interest}
This project tries to consider the public health, privacy, and security of third parties and therefore follows the principle of public interest.
\subsubsection*{Professional Competence and Integrity}
This project has been an enormous undertaking that pushed the limits of my capabilities.
I am glad that I was able to use this opportunity to learn about distributed systems, image classification, go, and Svelte.
During this project, I also followed the best practices of software development, such as using source control software and having an audit to tasks and issues.
\subsubsection*{Duty to Relevant Authority}
For the duration of the project, all the guidelines provided by the University of Surrey were followed.
\subsubsection*{Duty to the Profession}
During the research, design, and implementation, and report state all interactions with the supervisor of the project have been professional, respectful, and honest.
To the best of my ability, I tried to design a system that would contribute to the field.
\pagebreak
\include{eval}
\include{review}
\pagebreak
%\section{appendix}
% \begin{figure}[h!]
% \begin{center}
% \includegraphics[height=0.8\textheight]{expandable_models_simple}
% \end{center}
% \caption{contains an overall view of the entire system}
% \label{fig:expandable_models_simple}
% \end{figure}
% \begin{figure}
% \begin{center}
% \includegraphics[height=0.8\textheight]{expandable_models_generator}
% \end{center}
% \caption{contains an overall view of the model generation system}
% \label{fig:expandable_models_generator}
% \end{figure}
\pagebreak
\section{References}
\printbibliography[heading=none]

136
report/review.tex Normal file
View File

@ -0,0 +1,136 @@
\section{Critical Review of Project Outcomes} \label{sec:crpo}
This chapter will go into details to see if the project was able to achieve the goals set forth in the introduction.
The chapter will be analysing if the goals of the project were met, then shortcomings and improvements off the implementation will be discussed. After analysing shortcomings and improvements, possible future work that be done to the project will be discussed.
The section will end with a general statement about the state of the project.
\subsection{Project Objectives}
In the introduction section of this project, some objectives were set for this project.
By the end of the project, the developed solution can achieve the goals set forth.
\subsubsection*{A system to upload images that will be assigned to a model}
This goal was achieved.
One of the abilities of both the API and the webpage are to be able to upload images to the service.
Which means that a system was created that allows users to upload images that will be linked with a model.
\subsubsection*{A system to automatically train and create models}
This goal was achieved.
The designed server can create models based only using the data provided by the user without any human interaction.
The model creation system is not as efficient, this inefficient will be discussed more in a future subsection it could be but can still achieve the desired goal.
\subsubsection*{Platform where users can manage their models}
This goal was achieved.
A web-based platform was developed where users can manage all the data related to machine learning models that were created.
The platform that was implemented allows users to create models, upload images related to the model, and then manage the submitted classification tasks.
The platform allows managing any models easily they create with within, meaning that the developed solution can achieve the first goal of the project.
\subsubsection*{A system to automatically expand models without fully retraining the models}
This goal was achieved.
A system was created that allows users to add more images and classes to models that were previously created.
And this is done without having to fully retrain the model.
\subsubsection*{An API that users can interact programmatically}
This goal was achieved.
The API implementation allows users to programmatically access the system.
The efficacy of the API is proved by its use in the front end application.
The front end application uses the API to fully control the service.
This means that everything that can be done in the frontend can be done via the API.
Which means that the API can satisfy every need that a possible user might have; therefore this goal was accomplished.
\subsection{A retrospective analysis of the development process}
This project was complex to implement, with many interconnected systems working together to achieve the goals of the project.
This complexity was a result of open-ended design and scope expansion.
If the scope of the project had been more limited, the project could have achieved higher overall results.
While there were no technical setbacks done during the development process.
There were times when software updates of libraries made the implementation unusable, which slowed considerably the development velocity, as those issues required fixing.
If actions such as creating OCI containers were done in the earlier stages of development, issues such as this could have been prevented.
One of these software updates, made it so that images were not being able to classified.
This then prompted me to try to use a different library to train and classify the images, but this ended up not being achievable, and ended up with just fixing the original library problem.
While the time used to try to integrate the different machine learning library helped the project improve, most of the effort put into this possible transition as spent inefficiently.
As far as tools aiding the development, this project followed industries norms by having the source code tracked in Git and issues tracked in an issue tracker.
Which greatly helped in the development process, by having one centrailized repository of both code and known issues of that code.
\subsection{Project Shortcomings and Improvements}
Although the project was able to achieve the desired goals, the project has some shortcomings that can be improved upon in future iterations.
This section will analyse some of those shortcoming and ways to improve the service.
\subsubsection*{Model Generation}
The model generation system is a complex, and due to all the moving parts that make the system work, it requires a large amount of to work to maintain.
It is also very inefficient due to the having to generate custom tailored python scripts, that cause the data to be reloaded every time a new a round-robin round needs to happen.
A way more efficient way is to perform all the training directly on go server.
Running the training directly in go would allow the service to be able to keep track of memory and GPU usage, move data from the GPU and CPU effortlessly between runs, and would remove uncertainty from the training system.
The model generation was originally implemented with TensorFlow, this ended up limiting the generation of the models in go as the bindings for TensorFlow were lacking in the tools used to train the model.
Using Lib Torch libraries would allow more control over data, and allow that control to be done in go, which would improve both control and speed of the process.
Unfortunately, when a version of the service was attempted to be implemented using Lib Torch, the system was too unstable.
Problems were encountered with the go bindings for the Lib Torch library or, the Lib Torch library was causing inconsistent behaviour with between runs.
That compounded with time limitations make it impossible for a Lib Torch implementation to come to fruition.
Having a full go implementation would make the system more maintainable and fast.
\subsubsection*{Image storage}
The image storage is all local, while this does not currently affect how remote runner works.
%TODO improve this
This is less problematic when the runner is on the same network as the main server, but if a possible user would like to provide their runners.
This would require a lot of bandwidth for the images to be transferred over the network every time the model needs to run.
A better solution for image storage would allow user provided runners to store images locally.
During the upload time, the API, instead of storing the images locally, would instruct the users' runner to store the images locally, therefore when the runner would need to perform any training tasks with local data instead of remote data.
This would not also not require modification of the current system.
The system was designed and implemented to be expanded.
The dataset system was designed to be able to handle different kinds of storage methods in the future, such as remote storage and Object Buckets, like Amazon S3.
\subsubsection*{User Interface}
The user interface is simplistic, this helps new users use the program but limits what advanced users might want to do.
The user interface also might need an overhaul as it not visually appealing.
A future improving for this project is definitely getting a professional graphical designer that can create a better-looking and recognizable application.
\subsection{Future Work}
This section will consider possible future work that can be built upon this project.
\subsubsection*{Image Processing Pipelines}
The current system does not allow for images of different sizes to be uploaded to the system, an interesting project would be to create a new subsystem that would allow the user to create image processing pipelines.
This new system would allow users to create a set of instructions that images would go through to be added to the system.
For example, automatically cropping, scaling, or padding the image.
A system like this would add versatility to the system and remove more work from the users of the service as they don't have to worry about handling the image processing on their side.
\subsubsection*{Different Kinds of Models}
The runner system could be used to train and manage different kinds of models, not just image classification models.
If the system was modified to have different kinds of models, it would allow the users to run different kinds of models.
Such as Natural Language Processing Models, or Multi Model Models.
This would increase the versatility of the service, and it would allow users to automate more tasks.
\subsection{Conclusion}
With the increase in automation recently, having a system that allows users to quickly build classification models for their tasks, would be incredibly useful.
This project provides exactly that, a simple-to-use system that allows the user to create models with ease.
The implemented system is able to accept images provided by the user, then create and train that model, and then allow user to classify the images with that created model.
To achieve this, the developed software is large and complex.
Developing such large and complex systems comes with compromises.
In this case the model generation, training, and classfication; and API systems were prioritized over other systems such as file management systems.
While there are still improvements that can be made, and more features, that can be added to the service to make it event better, such as image processing pipelines and diferent kinds of models.
The service is in a state that It could be deployed in a production enviroment and work.
Therefore this project is successful.

152
report/sanr.tex Normal file
View File

@ -0,0 +1,152 @@
\section{Service Analysis and Requirements} \label{sec:sanr}
Understanding the project that is being built is a critical step in the software deployment process.
This section will discuss what are the requirements that a service needs to implement for the project to be considered a success.
As a software as a service project, there are some required parts that the project needs to have:
\begin{itemize}
\item A way for the user to interact with the system
\item A way for programs to interact with the system
\item Management of images
\item Management of models
\item Management of compute resources
\end{itemize}
\subsection{Service Structure}
The service has to be structured so that users can interact with in two ways.
The first way is for the user to directly interface with the system using a user interface.
This interface does not have any strict form requirements, it could either be a desktop application, web application or even a command line application.
The main objective of this interface is for the user to quickly understand what the system is doing with their data, and if they can use the model they created to evaluate images.
The second way for the user to interface with the system needs to be an API.
This is required as it would not make sense for users to be able to quickly generate image classification models if they still had to evaluate all the images manually.
Therefore, there needs to be away for the user product to connect with the system, the API provides exactly that.
The system should also be structured in a way that allows easy scalability.
So that it can handle many requests at the same time.
The system should be able to scale, this could be achieved in many ways.
One way is by allowing the service to act as a cluster, where the same application is running multiple times and a load balancer, balances the load between the systems.
Another way is for the service to behave as a distributed system, where the services are split into smaller modules and those modules can be replicated.
Independently of how the system scales, it requires the ability to handle the fact that the data that the system uses not be available everywhere.
As a machine learning solution, the service requires the necessary computational power to handle the training of the models.
This means that the system needs to be structured in an away that it can decouple the training process from the main process.
Which guarantees that the compute requirements for training the model do not affect the main server running.
Ideally, the service should be able to divide the tasks from tasks that would require the GPU, and tasks that would require the CPU.
\subsection{Resources}
As a machine learning image classification service, the service has to manage various types of resources.
\subsubsection{Compute Resources}
As mentioned before, the service needs to be able to manage its compute resources.
This is required because, for example, if the system starts training a new model and that training uses all the GPU resources, it would impact the ability of the service to be able to evaluate images for other users.
As this example demonstrated, the system needs to keep track of the amount of GPU power available, so it can manage the actions it has to take accordingly.
Therefore, for optimal functionality, the service requires the management of various compute resources.
There should be a separation of the different kinds of compute power.
The two types of compute power are: CPU and GPU.
The CPU is needed to handle the multiple requests that the API might answer at the same time.
And the GPU resources are required to train models and evaluate the images.
As a result, the service needs a system to distribute these compute tasks.
The tasks have to be distributed between the application that is running the API and the various other places where that compute can happen.
An ideal system would distribute the tasks intelligently, to allow the maximisation of resources.
An example of this would be running image classification, on the same model, on the same place twice, this would allow the model to stay in memory and not need to be reloaded again from disk.
These kinds of optimisations would help the system to be more efficient and less wasteful.
Another way to reduce the load that the system goes through is to allow users to add their own compute power to the system.
That compute power would only use images and models that are owned by the user.
While allowing the compute power to run any image or model in the system would allow for an even more scalable system, it would be an incredible violation of privacy and security.
As it allows outsiders access to possible sensitive information.
Which makes the idea of a complete distributed network of user provided compute power not viable.
\subsubsection{Storage}
Another resource that it has to handle is storage.
As the service accepts user uploaded images, the service has to monitor how much storage those images take.
The service will need systems to handle when the user uploaded images take too much space.
There are many ways of handling this, such as allowing the user to store their images, compacting the images, deleting images that the system might no longer need, or allowing dynamic storage services such as Object Buckets.
If there is not enough space to store all the images from all the models, and the service needs to delete images.
There should be a system that removes the images in a manner that causes the less harm.
An example of this would be deleting images in a way that keeps the dataset balanced.
If there is a discrepancy of where compute and storage happen, the system needs to be able to handle that.
This can be accomplished in various methods.
The most aggressive one is not allowing to compute resources to access data that is far away.
The less aggressive and smarter way is to allow the system to move data to the optimal place.
\subsection{User interface}
A service such as this requires a way for the users to quickly get an understating of how their data is being used and how they can perform the actions they want.
As previously mentions, this application can take multiple forms, from web apps, to command line applications.
As long as the application is easy to use, and allows the user to perform the required tasks:
\begin{itemize}
\item{Configure model}
\item{Upload images}
\item{Manage images}
\item{Request model training}
\item{Request image evaluation}
\item{Configure access}
% \item{See API usage}
%TODO write more
\end{itemize}
The way that the application communicates with the service should be done, via the API.
If there was a requirement to physical access the computer that the service is running on, it would defeat the purpose of this project.
Therefore, being able to control the service via the API makes the most reasonable sense.
A second system could be developed that allows the application to control the service, but that would be terribly inefficient.
Allowing the application to control the system via the API, also improves the API, as the API now gets more features.
The application should also allow administrators of the service to control the resources that are available to the system, to see if there is any requirement to add more resources.
\subsection{API} \label{sec:anal-api}
As a SaaS platform, most of the requests made to the service would be made via the API, not the user interface.
This is the case because the users that would need this service would set up the model using the web interface and then do the image classifications requests via the API.
While there are no hard requirements for the user interface, that is not the case for the API.
The API must be implemented as an HTTPS REST API, this is because the most of the APIs that currently exist online are HTTPS REST APIs \cite{json-api-usage-stats}.
If the service wants to be easy to use, it needs to be implemented in away such that it has the lowest barrier to entry.
Making the type of the API a requirement would guarantee that the application would be the most compatible with other systems that already exist.
The API would also need to be able to do all the tasks that the application can do.
As it would allow a user who wants to interact with the service via the API the ability to do so.
The API also requires authentication because without authentication it would allow users who might have malicious intent to:
\begin{itemize}
\item{Modifying systems settings}
\item{Accessing other users' data}
\end{itemize}
Allowing such actions would be incredibly damaging for the system.
Therefore, the API must implement authentication methods to prevent those kinds of actions from happening.
\subsection{Data Management}
The service will store a large amount of user data.
This includes: user information, user images, user models.
\subsubsection*{User Information}
There are no hard requirements on how the user information needs to be stored, as long as it is done securely.
User information includes personal identifiable information such as username and email, and secret information such as passwords, and access tokens.
Future versions of the service could possible also store more sensitive information about the user, such, as payment information and addresses.
Such information is required if the user needs to be charged, but payment for the services provided is outside the scope of this project.
\subsubsection*{User Images}
Images are another kind of information that has to be stored.
As it was mentioned before, the system has to keep track of the images and the space they use.
The system should also guarantee that there is some level of security in accessing the images that were uploaded to the service.
\subsubsection*{Models}
The last kind of data that the service has to keep track of is model data.
Once the model is trained, it has to be saved on disk.
The service should implement a system that manages where the models are stored.
This is similar to the image situation, where the model should be as close as possible to the compute resource that is going to utilise it, even if this requires copying the model.
\subsection{Summary}
This section shows that there are requirements that need to be met for the system to work as indented. These requirements range from usability requirements, implementation details, to system-level resource management requirements.
The most important requirement is for the system to be easy to use by the user.
As if it is difficult to use, then the service already fails in one of its objectives.
The other requirements are significant as well, as without them, the quality of the service would be very degraded.
And even if the service was effortless to use, it is as bad as being difficult to use if it could not process the images quickly in a reasonable amount of time.
The next chapter will describe a design that matches a subset of the requirements.
\pagebreak

115
report/settings.tex Normal file
View File

@ -0,0 +1,115 @@
\usepackage[english]{babel} % English language/hyphenation
\usepackage{url}
\usepackage{tabularx}
\usepackage{pdfpages}
\usepackage{float}
\usepackage{longtable}
\usepackage{multicol}
\usepackage{subfig}
\usepackage{graphicx}
\usepackage{svg}
\graphicspath{ {../images for report/} }
\usepackage[margin=2cm]{geometry}
\usepackage{datetime}
\newdateformat{monthyeardate}{\monthname[\THEMONTH], \THEYEAR}
\usepackage{hyperref}
\hypersetup{
colorlinks,
citecolor=black,
filecolor=black,
linkcolor=black,
urlcolor=black
}
\usepackage{cleveref}
%%% Custom headers/footers (fancyhdr package)
\usepackage{fancyhdr}
\pagestyle{fancyplain}
% \fancyhead{}
\fancypagestyle{my_empty}{%
\fancyhf{}
\renewcommand{\headrulewidth}{0pt}
\renewcommand{\footrulewidth}{0pt}
}
\fancypagestyle{simple}{%
\fancyhf{}
\renewcommand{\headrulewidth}{0pt}
\renewcommand{\footrulewidth}{0pt}
\fancyfoot[L]{} % Empty
\fancyfoot[C]{\thepage} % Pagenmbering
\fancyfoot[R]{} % Empty
}
\fancypagestyle{full}{%
\fancyhf{}
\renewcommand{\headrulewidth}{0.5pt}
\renewcommand{\footrulewidth}{0pt}
\fancyfoot[L]{} % Empty
\fancyfoot[C]{\thepage} % Pagenmbering
\fancyfoot[R]{} % Empty
\fancyhead[RO,LE]{Andre Henriques}
}
\renewcommand{\headrulewidth}{0pt} % Remove header underlines
\renewcommand{\footrulewidth}{0pt} % Remove footer underlines
\setlength{\headheight}{13.6pt}
\newcommand*\NewPage{\newpage\null\thispagestyle{empty}\newpage}
\newcommand*\mydate{\monthyeardate\today}
% numeric
\usepackage[bibstyle=ieee, citestyle=numeric, sorting=none,backend=biber]{biblatex}
\addbibresource{../main.bib}
\raggedbottom
\makeatletter
\renewcommand{\maketitle}{
\begin{center}
\pagestyle{my_empty}
\phantom{.} %necessary to add space on top before the title
\vspace{3cm}
{\huge \bf \@title\par}
\vspace{1cm}
{by}
\vspace{1cm}
{\LARGE Andre Goncalves Henriques}\\
{\large URN: 6644818}\\[1cm]
{\normalsize A dissertation submitted in partial fulfilment of the}\\
{\normalsize requirements for the award of}\\[1cm]
{\Large BACHELOR OF SCIENCE IN COMPUTER SCIENCE}\\[1cm]
{\normalsize\mydate}\\
\begin{center}
\includegraphics[height=0.3\textheight]{uni_surrey}
\end{center}
{\normalsize Department of Computer Science}\\
{\normalsize University of Surrey}\\
{\normalsize Guildford GU2 7XH}\\[2cm]
{\normalsize Supervised by: Dr. Rizwan Asghar}
\end{center}
}\makeatother

61
report/start.tex Normal file
View File

@ -0,0 +1,61 @@
\pagenumbering{gobble}
\maketitle
\NewPage
\pagenumbering{arabic}
\pagestyle{simple}
\begin{center}
\vspace*{\fill}
\section*{Declaration of Originality}
I confirm that the submitted work is my own work and that I have clearly identified and fully
acknowledged all material that is entitled to be attributed to others (whether published or
unpublished) using the referencing system set out in the programme handbook. I agree that the
University may submit my work to means of checking this, such as the plagiarism detection service
Turnitin® UK. I confirm that I understand that assessed work that has been shown to have been
plagiarised will be penalised.\\
\vspace*{\fill}
Andre Goncalves Henriques\\
\mydate\\
University of Surrey\\
Guildford GU27XH\\
\vspace*{\fill}
\end{center}
\NewPage
\begin{center}
\vspace*{\fill}
\section*{Acknowledgements}
I would like to take this opportunity to thank my supervisor, Rizwan Asghar who helped me with this project from the start of the until the end.
His help with the report was incredibly useful.\\
I would like to thank my family and friends for their support and encouragement.\\
\vspace*{\fill}
Andre Goncalves Henriques\\
\mydate\\
University of Surrey\\
Guildford GU27XH\\
\vspace*{\fill}
\end{center}
\NewPage
\section*{Abstract}
There are many automatable tasks that are currently being done manually.
If those tasks can be done automatically, a lot of productivity could be gained by having the computers perform those tasks, allowing humans to perform tasks that only humans can do.
One of this set of tasks are image classification tasks.
Many image classification tasks are being performed by humans, when they could be performed by computers.\\
This project aims to develop an image classification platform where users can create image classification models with as few clicks as possible.
Allowing for users that do not have any knowledge about image classification to use this system.
Making it possible for more of the manually classified tasks to be done by machines, and not humans, increasing the productivity of possible users.\\
This dissertation evaluates the feasibility of such system, current similarly implemented systems, current techniques for image classification, and possible requirements, designs and implementations of such system.
The dissertation focuses mainly on the implemented software, and the implementation choices that were made to achieve this project.
The dissertation ends with a critical evaluation of the results of this project, to ensure that the goals set forth were achieved.
\NewPage
\tableofcontents
\newpage
\pagestyle{full}