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
機械学習によるマーケット健全化施策を支える技術
Search
Hirofumi Nakagawa/中河 宏文
May 23, 2018
Programming
0
220
機械学習によるマーケット健全化施策を支える技術
Hirofumi Nakagawa/中河 宏文
May 23, 2018
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
メルカリの写真検索を支えるバックエンド CCSE 2019 version
hnakagawa
0
270
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
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
【re:Growth 2024】 Aurora DSQL をちゃんと話します!
maroon1st
0
770
CSC305 Lecture 26
javiergs
PRO
0
140
range over funcの使い道と非同期N+1リゾルバーの夢 / about a range over func
mackee
0
110
rails statsで大解剖 🔍 “B/43流” のRailsの育て方を歴史とともに振り返ります
shoheimitani
2
930
ドメインイベント増えすぎ問題
h0r15h0
2
300
php-conference-japan-2024
tasuku43
0
270
LLM Supervised Fine-tuningの理論と実践
datanalyticslabo
5
1.2k
Security_for_introducing_eBPF
kentatada
0
110
生成AIでGitHubソースコード取得して仕様書を作成
shukob
0
360
Monixと常駐プログラムの勘どころ / Scalaわいわい勉強会 #4
stoneream
0
280
Effective Signals in Angular 19+: Rules and Helpers
manfredsteyer
PRO
0
100
HTTP compression in PHP and Symfony apps
dunglas
2
1.7k
Featured
See All Featured
Bash Introduction
62gerente
608
210k
4 Signs Your Business is Dying
shpigford
181
21k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
132
33k
We Have a Design System, Now What?
morganepeng
51
7.3k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
247
1.3M
Building Adaptive Systems
keathley
38
2.3k
For a Future-Friendly Web
brad_frost
175
9.4k
It's Worth the Effort
3n
183
28k
Being A Developer After 40
akosma
87
590k
How GitHub (no longer) Works
holman
311
140k
Six Lessons from altMBA
skipperchong
27
3.5k
Facilitating Awesome Meetings
lara
50
6.1k
Transcript
ػցֶशʹΑΔϚʔέοτ ݈શԽࢪࡦΛࢧ͑Δٕज़ Mercari Server Side Tech Talk Vol.2 ʙCREφΠτʙ
hnakagawa
ࣗݾհ • Hirofumi Nakagawa (hnakagawa) • 20177݄ೖࣾ • ॴଐSRE •
σόΠευϥΠό։ൃ͔Βϑϩϯ τΤϯυ։ൃ·ͰΔԿͰ • NOT MLΤϯδχΞ • https://github.com/hnakagawa
͓ࣄ • ML Platform։ൃ • MLΤϯδχΞͱSREͷεΩϧΪϟοϓΛຒΊ Δ • ML Reliability,
SysML?, MLOps? • SREͷཱ͔ΒCREνʔϜΛॿ͚Δ
ML Platform • ͷML Platform • kubernetesϕʔε • ϩʔΧϧڥͱΫϥελڥͷ ࠩΛநԽ͢Δ
• ศརAPI܈ • طଘͷML FrameworkΛ༻͠ ؆୯ʹTraining/ServingΛߦ͏ ڥΛఏڙ
ͦͷ͏ͪOSSͰެ։༧ఆ(ଟ
ࠓͷAgenda ϦΞϧλΠϜࢹγεςϜ
ϦΞϧλΠϜࢹγεςϜ • ௨শ Lovemachine • ML Platform্ʹ࣮͞Ε͍ͯΔ .-1MBUGPSN USBJOJOHDMVTUFS -PWFNBDIJOF
($4 GKE PubSub .-1MBUGPSN TFSWJOHDMVTUFS -PWFNBDIJOF
ML ModelͷServing….?
Model Serving APIͷߏྫ 5FOTPS'MPX 4FSWJOH 5' .PEFM 5' .PEFM 'MBTL
4, .PEFM 4, .PEFM 4, .PEFM gRPC .FSDBSJ"1* REST FlaskͰલॲཧΛߦ͍ ཪͷTensorFlow Servingʹ͍͛ͯΔ
Model Serving API Streaming ver ͷߏྫ 5FOTPS'MPX 4FSWJOH 5' .PEFM
5' .PEFM .-1MBUGPSN 'SBNFXPSL PS "QBDIF#FBN 4, .PEFM 4, .PEFM 4, .PEFM gRPC PubSub
TensorFlow Serving • TensorFlow project͕ఏڙͯ͠ ͍ΔServingڥ • PythonॲཧܥΛհͣ͞ʹTFͷ modelΛservingͰ͖Δ •
ඪ४ͷ࣮ͰgRPCͰAPIΛ ఏڙ
ModelͱίϯςφɾΠϝʔδ • ڊେͳML ModelΛίϯςφɾΠϝʔδʹؚΊ Δ͔൱͔ • ؚΊͳ͍ͷͰ͋ΕԿॲʹஔ͢Δ͔ • ϙʔλϏϦςΟੑͱϩʔυ࣌ؒͷτϨʔυΦϑ •
ྑ͍ΞΠσΟΞ͕͋Εڭ͑ͯԼ͍͞…
௨ৗͷAPIͱҧ͏ • ѻ͏ϦιʔεɺModelαΠζ͕େ͖͘ͳΔ ߹͕ଟ͍(ඦMBʙGB) • CPUɾϝϞϦϦιʔεͷফඅ͕ܹ͍͠ • ߹ʹΑͬͯGPU͏
ϝϞϦফඅ • LovemachineͷPython࣮෦࣮ߦ࣌ʹ 2GBϝϞϦΛফඅ͢Δˠࠓޙ͞Βʹ૿͑Δ༧ ఆ͋Δ • Scikit-learnͰهड़͞ΕͨTF-IDFͷલॲཧ෦ ͕େ͖͘ͳΔࣄ͕ଟ͍
Pythonͱฒྻੑ • વThread͕͑ͳ͍(GILͷͨΊ) • ϓϩηεຖʹModelΛϩʔυ͢Δͱඞཁͳϝ ϞϦαΠζ͕େ͖͘ͳΔˠ Blue-Green DeployͷোʹͳΔ
ਖ਼PythonͰͷServing Πϯϑϥతʹਏ͍ࣄ͕ଟ͍…
ϝϞϦΛݡ͘͏ • fork͢ΔલʹmodelΛϩʔυ͠Copy on Write Λޮ͔͢ • k8sͷone process per
containerηΦϦ͋ ͑ͯഁ͍ͬͯΔ
Copy On Writeͷ෮श ϝϞϦ ϓϩηε ࢠϓϩηε 2.fork 1BHF" 1.allocation ಉ͡ྖҬΛࢀর
ϓϩηε͕ϝϞϦͷ༰Λ ॻ͖͑Δͱ… ϝϞϦ ϓϩηε ࢠϓϩηε 1BHF" 1BHF# OS͕ผͷྖҬΛAllocationͯ͠ݩσʔλΛίϐʔ͢Δ ผͷྖҬΛࢀর
Current Issues • Mercari APIͱͷͭͳ͗ࠐΈʹۤ࿑ ˠ Ұ௨Γ࡞Εޙ࠶ར༻Ͱ͖Δͣ • ਓؒͷߦಈΛ૬खʹ͍ͯ͠Δҝɺσʔλͷ͕ม ΘΓ͔ͬͨ͢Γɺ༧֎ͷ͕ൃੜͨ͠Γͯ͠ɺ
ରԠ͠ଓ͚Δඞཁ͕͋Δ ˠ ML Model࡞ऀʹෛ୲ֻ͕͔Γଓ͚Δ ˠ SREͱͯࣗ͠ಈԽΛؚΜͩΈͰղܾ͍ͨ͠
Future Plans • ࣾͷσʔλ͔ΒಛྔΛநग़͢Δͯ͠ Embedding͢Δ൚༻ͷΈ ˠదͳྨثͱΈ߹ΘͤΕɺ୭Ͱͦͦ͜ ͜ͷྨϞσϧΛ࡞Ͱ͖Δ? →FBLearner Flowతͳͭ? •
ࣾͷղܾʹಛԽͨ͠ઐ༻ͷAutoMLతͳԿ ͔?
·ͱΊ • ML ModelͷServingʹɺগ͠௨ৗͱҧ͏Πϯϑ ϥ͕ඞཁʹͳΔ →·ͩϕετɾϓϥΫςΟε͔Βͳ͍ • ਓͷߦಈΛ૬खʹ͢Δͷେม • ͦͦMLͳػೳΛຊ֨ӡ༻͠Α͏ͱ͢Δͱɺେ
෯ͳࣗಈԽɾΈԽΛਐΊͳ͍ͱ্ख͘ߦ͔ͳ ͍
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠!!
We are Hiring!!
SRE ML Reliability • SysML? MLOps? ৽͍͠Job description • SREεΩϧ+MLͷجૅࣝ
• MLΠϯϑϥͷࣗಈԽɾΈԽΛਪ͠ਐΊͯ ͘ΕΔਓࡐ • ͪΖΜଞͷ৬छઈࢍืूத!!
ৄࡉͪ͜Β https://careers.mercari.com/