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
50
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
43
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
64
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
55
Other Decks in Technology
See All in Technology
チームビルディングは"感性"で向き合おう / Team Building with Awareness
kohzas
0
270
ネットワークだけ隔離されたコンテナ作成デモ / Kichijoji.pm36
tenforward
1
240
内製化を目指す事業会社が、システム開発会社と共に進める「開発生産性改善」の取り組み事例 #devsumi
yuwji
1
130
サプライチェーン攻撃に備える
ryunen344
0
360
20240911_New_Relicダッシュボード活用例
speakerdeckfk
0
110
スタッフエンジニアの道: The Staff Engineer’s Path
snoozer05
PRO
44
14k
言葉は感情の近似値である。その感情と言葉の誤差を最小化しよう ~コミュニケーションにおけるアナログ/デジタル変換の課題に立ち向かう~
nktamago
0
240
OR学会2024秋_短期収益と将来のオフ方策評価性能を考慮したクーポン割当方策混合比の決定
recruitengineers
PRO
4
480
『GRANBLUE FANTASY Relink』キャラクターの魅力を支えるリグ・シミュレーション制作事例
cygames
0
160
Tricentisにおけるテスト自動化へのAI活用ご紹介/20240910Shunsuke Katakura
shift_evolve
0
210
JEP 480: Structured Concurrency
aya_ebata
0
130
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
5
46k
Featured
See All Featured
We Have a Design System, Now What?
morganepeng
48
7.1k
Scaling GitHub
holman
458
140k
Web development in the modern age
philhawksworth
205
10k
Raft: Consensus for Rubyists
vanstee
136
6.5k
Art, The Web, and Tiny UX
lynnandtonic
294
20k
Speed Design
sergeychernyshev
22
430
The Art of Programming - Codeland 2020
erikaheidi
48
13k
Infographics Made Easy
chrislema
239
18k
What's new in Ruby 2.0
geeforr
340
31k
Fontdeck: Realign not Redesign
paulrobertlloyd
80
5.1k
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
Large-scale JavaScript Application Architecture
addyosmani
508
110k
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