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
メルカリの写真検索を支えるバックエンド CCSE 2019 version
Search
Hirofumi Nakagawa/中河 宏文
July 13, 2019
Programming
0
260
メルカリの写真検索を支えるバックエンド CCSE 2019 version
過去発表分との差分としてEdge関連のデモが追加されています。
デモ動画:
https://youtu.be/UsNMDuZyaJU
Hirofumi Nakagawa/中河 宏文
July 13, 2019
Tweet
Share
More Decks by Hirofumi Nakagawa/中河 宏文
See All by Hirofumi Nakagawa/中河 宏文
IoTデバイスでMLモデルを動かす技術
hnakagawa
0
140
Kanazawa_AI.pdf
hnakagawa
0
160
メルカリ写真検索における Amazon EKS の活用事例と プロダクトにおけるEdgeAI technologyの展望
hnakagawa
5
8.7k
メルカリ写真検索における Amazon EKS の活用事例
hnakagawa
6
29k
メルカリの写真検索を支えるバックエンド
hnakagawa
1
1.1k
Mercari ML Platform
hnakagawa
1
17k
mlct.pdf
hnakagawa
2
2k
機械学習によるマーケット健全化施策を支える技術
hnakagawa
0
210
メルカリのマーケット健全化施策を支えるML基盤
hnakagawa
10
8.9k
Other Decks in Programming
See All in Programming
飲食業界向けマルチプロダクトを実現させる開発体制とリアルな現状
hiroya0601
1
350
GCCのプラグインを作る / I Made a GCC Plugin
shouth
1
140
知られざるNaNの世界
hole
3
1.2k
qmuntal/stateless のススメ
sgash708
0
100
Kaigi on Rails 2024 - Rails APIモードのためのシンプルで効果的なCSRF対策 / kaigionrails-2024-csrf
corocn
4
2.3k
2万ページのSSG運用における工夫と注意点 / Vue Fes Japan 2024
chinen
3
1.2k
Folding Cheat Sheet #8
philipschwarz
PRO
0
160
組織に自動テストを書く文化を根付かせる戦略(2024秋版) / Building Automated Test Culture 2024 Autumn Edition
twada
PRO
9
4.3k
Vue SFCのtemplateでTypeScriptの型を活用しよう
tsukkee
3
1.4k
Jakarta Concurrencyによる並行処理プログラミングの始め方 (JJUG CCC 2024 Fall)
tnagao7
0
180
PagerDuty を軸にした On-Call 構築と運用課題の解決 / PagerDuty Japan Community Meetup 4
horimislime
1
100
watsonx.ai Dojo #3 プロンプトエンジニアリング入門
oniak3ibm
PRO
0
480
Featured
See All Featured
Rebuilding a faster, lazier Slack
samanthasiow
79
8.6k
RailsConf 2023
tenderlove
29
870
Code Reviewing Like a Champion
maltzj
519
39k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
131
33k
Designing Experiences People Love
moore
138
23k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
167
49k
A Tale of Four Properties
chriscoyier
156
23k
Keith and Marios Guide to Fast Websites
keithpitt
408
22k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
5
140
Designing the Hi-DPI Web
ddemaree
280
34k
Put a Button on it: Removing Barriers to Going Fast.
kastner
58
3.5k
What's new in Ruby 2.0
geeforr
342
31k
Transcript
Confidential - Do Not Share 1 ϝϧΧϦͷࣸਅݕࡧΛࢧ͑ΔόοΫΤϯυ גࣜձࣾϝϧΧϦ தՏ จ
Confidential - Do Not Share 2 • 20177݄ೖࣾ • ॴଐSRE→AI/MLνʔϜ
• σόΠευϥΠό։ൃ͔ΒϑϩϯτΤ ϯυ։ൃ·ͰΔԿͰ Twitter: hnakagawa14 GitHub: hnakagawa தՏ จ (Hirofumi Nakagawa) ࣗݾհ 2
Confidential - Do Not Share 3 Introduction
Confidential - Do Not Share 4 What is ࣸਅݕࡧ •
ࣸਅݕࡧͱɺ͍ΘΏΔը૾ ݕࡧػೳ • ΞϓϦ͔ΒࣸਅΛݩʹΛ ݕࡧ͢Δ • ໊ΛΒͳͯ͘ը૾͔ ΒΛݕࡧͰ͖Δ ಈըϦϯΫ: https://youtu.be/kTni8EvOCgI
Confidential - Do Not Share 5 جຊతͳࣸਅݕࡧͷΈ Deep Neural Networks
(DNN)Λ༻ͯ͠ը૾ ͔ΒಛϕΫτϧΛऔಘ औಘͨ͠ಛϕΫτϧΛ Approximate Nearest Neighbor Index(ANN Index) ʹՃͯ͠ը૾indexΛߏங ݕࡧ࣌ʹಉ͘͡ը૾͔Β DNNΛհͯ͠ಛϕΫτϧΛऔ ಘ͠ɺANN Index͔Βݕࡧ 2 3 1
Confidential - Do Not Share 6 What is Kubernetes •
KubernetesʢҎԼk8sʣͱ Φʔϓϯιʔεͷίϯςφɾ ΦʔέετϨʔγϣϯγες Ϝ • k8sʹCustom Resource DefinitionͱݺΕΔಠࣗͷ ϦιʔεΛఆٛͰ͖Δػೳ͕ ͋Γɺ։ൃऀͦͷػೳΛհ ͯ͠k8sͷػೳΛ֦ுͰ͖Δ
Confidential - Do Not Share 7 ML Platform Lykeion •
Training/Serving CRD & ΧελϜ ίϯτϩʔϥ • ίϯςφϕʔεɾύΠϓϥϯ • Training/Serving ίϯςφΠϝʔ δɾϏϧμʔ • ϞσϧɾϨϙδτϦ ࣸਅݕࡧLykeionͱݺΕΔͷ ML Platform্ʹߏங͞Ε͓ͯΓɺԼ هͷػೳPlatformଆͷػೳΛ༻͠ ͍ͯΔ
Confidential - Do Not Share 8 Architectureɹ
Confidential - Do Not Share 9 Architecture֓ཁਤ
Confidential - Do Not Share 10 1.TrainingɾϦιʔεͷ࡞
Confidential - Do Not Share 11 TrainingɾϦιʔεͷ࡞ • Training custom
resourceΛ CronJob͕࡞ • ΧελϜɾίϯτϩʔϥ͕ CRDɾϦιʔεͰઃఆ͞Εͨ ίϯςφϕʔεɾύΠϓϥΠ ϯΛ࣮ߦ • ࣮ߦ͢Δόον୯Ґͱͯ͠ Hourly, Daily, Monthly͕ଘࡏ
Confidential - Do Not Share 12 • ֤ఔΛݸผͷίϯςφɾΠϝʔδͰ࣮ߦ • ϥΠϒϥϦͷґଘؔͳͲڥφΠʔϒͳMLύΠϓϥΠϯͷΛղܾ
• ύΠϓϥΠϯDAGYAMLͰهड़ ֤ఔͷೖग़ྗPersistent VolumeʢҎ ԼPVʣΛհ͢ ίϯςφϕʔεɾύΠϓϥΠϯ
Confidential - Do Not Share 13 TrainingɾϦιʔεͷ࡞ • શͯͷόον࣮ߦใ͕ CRDɾϦιʔεͱͯ͠k8s্ʹ
Δ • ಉ͡ॲཧΛ࠶࣮ߦग़དྷΔͨ Ίɺόονͷ࠶࣮ߦΛ͏ো ෮چ࡞ۀ͕༰қ
Confidential - Do Not Share 14 2.ը૾ͷμϯϩʔυ
Confidential - Do Not Share 15 • S3্ʹଘࡏ͢ΔϝϧΧϦɾΠϝʔδετΞ͔Βը૾Λμϯϩʔυ • ύΠϓϥΠϯ্ͬͱ͕͔͔࣌ؒΔఔʢը૾͕େͳͨΊ)
• ͦͷͨΊPVʹҰఆظؒΩϟογϡ͢ΔࣄʹΑͬͯ࠶ΠϯσοΫε͕ඞཁ ͳ࣌ʹૉૣ͘ύΠϓϥΠϯΛճͤΔΑ͏ʹ͍ͯ͠Δ ը૾ͷμϯϩʔυ
Confidential - Do Not Share 16 3. ΞηοτͷΞοϓϩʔυ
Confidential - Do Not Share 17 • ύΠϓϥΠϯͷՌͰ͋ΔಛϕΫτϧͱANN IndexΛϞσϧɾϨϙδτ Ϧʹอଘ
• શͯͷՌόʔδϣϯཧ͞Εͨঢ়ଶͰอଘ͞ΕΔ • ϞσϧɾϨϙδτϦGCS্ʹߏங ΞηοτͷΞοϓϩʔυ
Confidential - Do Not Share 18 4.ServingΠϝʔδͷϏϧυ
Confidential - Do Not Share 19 1. ϞσϧɾϨϙδτϦΛImage BuilderͱݺΕΔdaemon͕ࢹ 2.
৽͍͠Serving͖͢Ϧιʔε͕Ճ͞ΕΔͱࣗಈͰServingίϯςφɾΠϝ ʔδΛϏϧυ 3. ίϯςφɾΠϝʔδશͯͷANN IndexͷαʔϏϯάʹඞཁͳϦιʔεΛ શؚͯΜͰ͍Δ 4. Ϗϧυ͞ΕͨίϯςφɾΠϝʔδΛίϯςφɾϨδετϦʹϓογϡ ServingΠϝʔδͷϏϧυ
Confidential - Do Not Share 20 5.ServingϦιʔεͷ࡞
Confidential - Do Not Share 21 ServingɾϦιʔεͷ࡞ • Image BuilderίϯςφɾΠϝʔ
δΛϏϧυͨ͋͠ͱɺServingΧε λϜɾϦιʔεΛ࡞ • ServingΧελϜɾίϯτϩʔϥ CRDɾϦιʔεͷઃఆΛݩʹඞཁ ͳDeploymentɺServiceΛ࡞ • ຊγεςϜͰߏங͞ΕͨANN IndexΛݸผͷIndexαʔϏεͱ͠ ͯσϓϩΠ
Confidential - Do Not Share 22 6.ServiceσΟεΧόϦ
Confidential - Do Not Share 23 αʔϏεɾσΟεΧόϦ • Ϋϥελ্ʹଘࡏ͢ΔIndexαʔϏ εΛk8sΛհͯࣗ͠ಈతʹऔಘ͢
Δ • ͳΔ͘େ͖ͳཻͷIndexΛ ༻͢ΔΑ͏ɺҟͳΔظؒɾཻͷ IndexαʔϏε(Hourly, Daily, Monthly) ΛࣗಈతʹΈ߹ΘͤΔ • REST <-> IndexαʔϏεؒͷϓϩ τίϧgRPCΛ༻
Confidential - Do Not Share 24 7.֓ཁਤৼΓฦΓ
Confidential - Do Not Share 25 Conclusionɹ
Confidential - Do Not Share 26 1. ίϯςφɾϕʔεͷ࠶ݱੑͷߴ͍γεςϜ 2. k8sͷCRD/ΧελϜɾίϯτϩʔϥαʔϏεɾσΟεΧόϦͷػೳΛ׆༻
3. Batch Execution as Custom ResourceɺML PlatformͰ࣮ݱ͞Ε͍ͯΔػ ೳΛ༻͠ɺϩόετͳγεςϜΛߏங 4. ΫϥυɾΠϯϑϥΛk8sͰநԽ͢ΔࣄʹΑͬͯɺ֤Ϋϥυɾϕϯμͷྑ ͍ͱ͜औΓΛ͍ͯ͠Δ ࣸਅݕࡧͷόοΫΤϯυɾΠϯϑϥ
Confidential - Do Not Share 27 Next Futureɹ
Confidential - Do Not Share 28 Realtime image search •
EdgeଆͰobject detection & feature extractionΛߦ͏ • feature vectorΛΫΤϦʹANN Index service͔ΒྨࣅΛऔಘ • Graph RuntimeTF Lite + custom operatorΛ༻
Confidential - Do Not Share 29 Realtime image search demo
• ݕࡧʹඞཁͳਪॲཧͷେ෦ΛEdgeଆͰߦ ͍ͬͯΔ • ϦΞϧλΠϜͳΠϯλϥΫγϣϯΛ࣮ݱ • UX্େ͖ͳϝϦοτ͕༗Δ
Confidential - Do Not Share 30 Thank you all for
coming todayɹ