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
280
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
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
Rubyでつくるパケットキャプチャツール
ydah
0
420
Vue.jsでiOSアプリを作る方法
hal_spidernight
0
120
知られざるDMMデータエンジニアの生態 〜かつてツチノコと呼ばれし者〜
takaha4k
3
980
自分ひとりから始められる生産性向上の取り組み #でぃーぷらすオオサカ
irof
8
2.1k
2025.01.17_Sansan × DMM.swift
riofujimon
2
640
自動で //nolint を挿入する取り組み / Gopher's Gathering
utgwkk
1
150
[JAWS-UG横浜 #80] うわっ…今年のServerless アップデート、少なすぎ…?
maroon1st
0
140
DevinとCursorから学ぶAIエージェントメモリーの設計とMoatの考え方
itarutomy
1
470
AHC041解説
terryu16
0
520
振り返れば奴(Cline)がいる
keiyagi
0
110
Fixstars高速化コンテスト2024準優勝解法
eijirou
0
200
“あなた” の開発を支援する AI エージェント Bedrock Engineer / introducing-bedrock-engineer
gawa
9
1.2k
Featured
See All Featured
YesSQL, Process and Tooling at Scale
rocio
170
14k
Thoughts on Productivity
jonyablonski
68
4.4k
Building an army of robots
kneath
302
45k
Typedesign – Prime Four
hannesfritz
40
2.5k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
192
16k
Making Projects Easy
brettharned
116
6k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
Adopting Sorbet at Scale
ufuk
74
9.2k
Making the Leap to Tech Lead
cromwellryan
133
9k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
11
900
Facilitating Awesome Meetings
lara
51
6.2k
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