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
290
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
8.8k
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
220
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
[Fin-JAWS 第38回 ~re:Invent 2024 金融re:Cap~]FaultInjectionServiceアップデート@pre:Invent2024
shintaro_fukatsu
0
400
2024年のWebフロントエンドのふりかえりと2025年
sakito
1
220
バックエンドのためのアプリ内課金入門 (サブスク編)
qnighy
8
1.7k
Open source software: how to live long and go far
gaelvaroquaux
0
610
密集、ドキュメントのコロケーション with AWS Lambda
satoshi256kbyte
0
120
Conform を推す - Advocating for Conform
mizoguchicoji
3
670
社内フレームワークとその依存性解決 / in-house framework and its dependency management
vvakame
1
550
自動で //nolint を挿入する取り組み / Gopher's Gathering
utgwkk
1
240
データの整合性を保つ非同期処理アーキテクチャパターン / Async Architecture Patterns
mokuo
38
13k
AWS Lambda functions with C# 用の Dev Container Template を作ってみた件
mappie_kochi
0
240
ペアーズでの、Langfuseを中心とした評価ドリブンなリリースサイクルのご紹介
fukubaka0825
2
290
Amazon ECS とマイクロサービスから考えるシステム構成
hiyanger
2
490
Featured
See All Featured
Unsuck your backbone
ammeep
669
57k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
3.7k
Done Done
chrislema
182
16k
How to Ace a Technical Interview
jacobian
276
23k
Agile that works and the tools we love
rasmusluckow
328
21k
Adopting Sorbet at Scale
ufuk
74
9.2k
Fireside Chat
paigeccino
34
3.2k
Why You Should Never Use an ORM
jnunemaker
PRO
55
9.2k
GitHub's CSS Performance
jonrohan
1030
460k
Why Our Code Smells
bkeepers
PRO
335
57k
Optimising Largest Contentful Paint
csswizardry
34
3.1k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
7
620
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