Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Image classification in real world : Car rental...
Search
Mathieu Hausherr
September 21, 2018
Technology
0
52
Image classification in real world : Car rental damage report
Mathieu Hausherr
September 21, 2018
Tweet
Share
More Decks by Mathieu Hausherr
See All by Mathieu Hausherr
Mobilis In Mobile 2024 - iOS, Android et la voiture - État des lieux
mhausherr
0
44
FrenchKit - Contact Tracing & Exposure Notification
mhausherr
0
130
FRAUG StopCovid19 : Le point sur les applications de tracing Bluetooth
mhausherr
1
240
Swift Lille - CoreML / CreateML
mhausherr
0
65
Mode offline Cocoaheads
mhausherr
0
34
Les surcouches constructeur sur Android
mhausherr
1
790
Mode offline : Notre application Android fonctionne au niveau -5 d’un parking
mhausherr
0
1.2k
Mode offline : Notre application mobile fonctionne au niveau -5 d’un parking
mhausherr
1
120
CocoaHeads : Apple Pay
mhausherr
0
56
Other Decks in Technology
See All in Technology
virtme-ng
ennael
PRO
0
260
C# 13 / .NET 9 の新機能 (RC 1 時点)
nenonaninu
0
1.1k
エムスリーマネジメントチーム紹介資料 / Introduction of M3 Management Team
m3_engineering
0
240
仮想化って何だろう
shkoga
0
130
REST API Design Pitfalls
victorrentea
1
500
Oracle Cloud Infrastructure:2024年9月度サービス・アップデート
oracle4engineer
PRO
0
250
FastAPIでのasync defとdefの使い分け
takashi1029
6
1.7k
【shownet.conf_】ShowNet伝送改めShowNet APN 2024
shownet
PRO
0
290
【shownet.conf_】ShowNet x 宇宙ネットワーク
shownet
PRO
0
270
生成AIアプリのアップデートと配布の課題をCDK Pipelinesで解決してみた
sonoda_mj
0
180
Efficient zero-copy networking using io_uring
ennael
PRO
0
230
k6を活用した再現性・拡張性の高い負荷試験基盤の構築
biwashi
11
2.7k
Featured
See All Featured
The Illustrated Children's Guide to Kubernetes
chrisshort
47
48k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
90
16k
Git: the NoSQL Database
bkeepers
PRO
425
64k
How STYLIGHT went responsive
nonsquared
93
5.1k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
30
2.6k
How to Ace a Technical Interview
jacobian
274
23k
Fireside Chat
paigeccino
31
2.9k
Automating Front-end Workflow
addyosmani
1365
200k
Large-scale JavaScript Application Architecture
addyosmani
509
110k
Principles of Awesome APIs and How to Build Them.
keavy
125
17k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
5
170
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
26
4k
Transcript
Image classification in real world Car rental damage report
None
None
None
TOP 7 Amazing Tips About Machine Learning for Dummies (aka
iPhone developers)
None
Image classification Folders train Unkown image Classes
#1 ML is not only for data-scientists
None
None
My Dataset 41 269 pictures 62,63 Go Same cars Same
set of colors Same luminosity (no light) Already classified by users
None
None
#2 You already have a dataset or you should
UX proposition Is it a Front alloy wheel ? Yes
sure ! No it’s not
Create ML Top 1 - From 1 34 %
Wheel Tire Fender Gas trap
Create ML Top 1 - From 1 34 % Top
1 - From 5 91 %
UX proposition v2 Something else
Wheel Roof Fender Gas trap
Create ML Top 1 - From 1 34 % Top
1 - From 5 91 % Top n - From n 78 %
#3 Don’t trust results Use it as a hint
None
None
None
Base Merge Classes Top 1 - From 1 34 %
37 % Top 1 - From 5 91 % 93 % Top n - From n 78 % 81 %
#4 Merge classes If you can’t see it, ML can’t
see it
Partner app
Base Partner data Top 1 - From 1 37 %
34 % Top 1 - From 5 93 % 89 % Top n - From n 81 % 75 %
Base Partner data Partner corrected data Top 1 - From
1 37 % 34 % 41 % Top 1 - From 5 93 % 89 % 94 % Top n - From n 81 % 75 % 84 %
#5 Clean your data Size of dataset don’t always matter
None
Inception v3 - MobileNet Inception v3 MobileNet Create ML Top
1 - From 5 91 % 90 % 91 % Top n - From n 79 % 18 % 78 % Size 87 Mo 2.2 Mo 1.5 Mo Training time 2h41 2h38 1h50
#6 Use Create ML It’s really cool
#1 ML is for mobile developer too #2 You already
have a dataset #3 Don’t trust the result #4 If you can’t see it, ML can’t see it #5 Clean your data #6 Use Create ML #7 Drive safe
#1 ML is for mobile developer too #2 You already
have a dataset #3 Don’t trust the result #4 If you can’t see it, ML can’t see it #5 Clean your data #6 Use Create ML #7 Drive safe
Mathieu Hausherr @mhausherr