Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Build Image Classification service with Amazon ...

Sponsored · Your Podcast. Everywhere. Effortlessly. Share. Educate. Inspire. Entertain. You do you. We'll handle the rest. →
Avatar for Yuichiro Someya Yuichiro Someya
November 22, 2016
Programming
2.9k
4

Build Image Classification service with Amazon ECS and GPU instances

Avatar for Yuichiro Someya

Yuichiro Someya

November 22, 2016

More Decks by Yuichiro Someya

See All by Yuichiro Someya
にんげんがさき 基盤はあと / Developers over ML platform
Avatar for Yuichiro Someya ayemos
0
15k
機械学習をスモールスタートさせる方法 / small machine learning
Avatar for Yuichiro Someya ayemos
3
2.1k
アットホームな分析基盤の作り方 / Homemade Machine Learning Toolkits
Avatar for Yuichiro Someya ayemos
1
1k
サービス開発、機械学習、クラウド / the trinity of machine learning
Avatar for Yuichiro Someya ayemos
0
3.7k
成長を止めない機械学習のやり方 / Don't stop 'til you get enough (data).
Avatar for Yuichiro Someya ayemos
15
5.3k
AWS で加速する機械学習 / Accelerate Machine Learning with AWS
Avatar for Yuichiro Someya ayemos
1
360
クックパッドの機械学習基盤 2018 / Machine Learning Platform at Cookpad ~ 2018 ~
Avatar for Yuichiro Someya ayemos
15
21k
PyTorchとCaffe2とONNXと深層学習モデルのデプロイについて
Avatar for Yuichiro Someya ayemos
1
3.1k
クックパッドにおけるAWS GPUインスタンスの利用事例 / Powering by AWS GPU Instances in Cookpad Inc
Avatar for Yuichiro Someya ayemos
0
460

Other Decks in Programming

See All in Programming
Hatena Engineer Seminar #37「言語モデルの活用に関する研究」
Avatar for SlashNephy slashnephy
0
470
決定論的オーケストレーションの設計と実装 / Design and Implementation of Deterministic Orchestration
Avatar for nrs nrslib
4
1.6k
そのテスト、説明できますか？~LWテスト戦略FW~のご紹介
Avatar for Kei Nakahara nakahara
0
190
正しくソフトウェアを作る、前提を疑うための認知の視点 / doubt-premise
Avatar for MinoDriven minodriven
21
7.2k
LLM本来の能力を解き放つサンドボックス技術とAI民主化への適用
Avatar for Yuku Kotani yukukotani
3
4.8k
AI がコードを書く時代における新卒エンジニアの仕事風景 (2026) / New Graduate Engineers in the Era of AI Coding (2026)
Avatar for sushichan044 sushichan044
0
200
Semantic Version 単位で戦略を柔軟に変えて、パッケージアップデートを自動化する
Avatar for daitasu daitasu
1
340
アルゴリズムは何を圧縮しているのか ─ Haskell から育った「圧縮代数」というメンタルモデル
Avatar for Naoya Ito naoya
11
1.9k
スマートグラスで並列バイブコーディング
Avatar for Hayami Shuhei hyshu
0
280
Strategic Design in the Frontend: Moduliths & Micro Frontends @DDDEurope
Avatar for Manfred Steyer manfredsteyer
PRO
0
140
霧の中の代数的エフェクト
Avatar for funnycat funnyycat
1
150
分散システム、なんですぐ死んでしまうん？耐障害性を高めたいあなたのためのレジリエンスパターン入門
Avatar for Mitsuhiro Shibuya mshibuya
7
2.8k

Featured

See All Featured
AI: The stuff that nobody shows you
Avatar for John Nunemaker jnunemaker
PRO
8
770
Done Done
Avatar for chrislema chrislema
186
16k
Intergalactic Javascript Robots from Outer Space
Avatar for Vicent Martí tanoku
273
27k
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
Avatar for Aleyda Solis aleyda
1
1.3k
Leveraging Curiosity to Care for An Aging Population
Avatar for Cassini Nazir cassininazir
1
310
Learning to Love Humans: Emotional Interface Design
Avatar for Aarron Walter aarron
275
41k
Color Theory Basics | Prateek | Gurzu
Avatar for Gurzu gurzu
0
380
YesSQL, Process and Tooling at Scale
Avatar for Rocio Delgado rocio
174
15k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
Avatar for soudai sone soudai
PRO
201
75k
Save Time (by Creating Custom Rails Generators)
Avatar for Garrett Dimon garrettdimon
PRO
32
3.6k
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
Avatar for Aleyda Solis aleyda
2
11k
Music & Morning Musume
Avatar for Bryan Veloso bryan
47
7.3k

Transcript

  1. Build Image Classification service with AWS ECS and GPU instances

    Yuichiro Someya @ Cookpad

  2. • છ୩ ༔Ұ࿠ [Yuichiro Someya] • ౦޻େେֶӃ ܭࢉ޻ֶઐ߈ म࢜ •

    '16 ৽ଔ @ ΫοΫύου • github.com/ayemos • twitter.com/kumasan_com echo `whoami`

  3. • ྉཧࣸਅͷࣗಈऩूαʔϏεΛ • CaffeNet[1]Λݩʹ࡞ͬͨྉཧը૾ೝࣝϞσϧͱ • Amazon SQS/S3 Ͱߏங͞Εͨσʔλϑϩʔͱ • Amazon

    ECS (GPU instance) Λར༻ͯ͠ӡ༻͍ͯ͠Δ࿩ <>IUUQTHJUIVCDPN#7-$DB⒎F Agenda

  4. • ྉཧࣸਅͷࣗಈऩूαʔϏεΛ • CaffeNet[1]Λݩʹ࡞ͬͨྉཧը૾ೝࣝϞσϧͱ • Amazon SQS/S3 Ͱߏங͞Εͨσʔλϑϩʔͱ • Amazon

    ECS (GPU instance) Λར༻ͯ͠ӡ༻͍ͯ͠Δ࿩ <>IUUQTHJUIVCDPN#7-$DB⒎F Agenda

  5. ΫοΫύου • Ϩγϐ਺ɿ 250ສ඼Ҏ্ • ݄࣍ؒར༻ऀ਺ɿ 6,000ສਓҎ্

  6. • εϚϗ಺ͷࣸਅ͔Βྉཧ͚ͩΛࣗಈతʹऩू • Ұ෦ͷϢʔβʔ޲͚ʹݶఆతʹެ։த ྉཧ͖Ζ͘

  7. • CaffeNetΛ ྉཧʗඇྉཧ ൑ఆ޲͚ʹFine Tuningͨ͠Ϟσϧ • Caffe[1]Ͱֶश͞ΕͨϞσϧΛChainerͷCaffe emulatorͰಡΉ
 ref: http://docs.chainer.org/en/stable/reference/caffe.html

    • ෼ྨΧςΰϦΛ ྉཧʗඇྉཧ ʹมߋ͠ɺΫοΫύου্ͷ
 ྉཧࣸਅΛ࢖ֶͬͯश <>IUUQDB⒎FCFSLFMFZWJTJPOPSH CookpadNet

  8. • CookpadNet͸Ͳ͜Ͱ൑ఆΛߦ͍ɺͦͷ݁Ռ͸Ͳ͜ʹͲ͏఻͑Δ ͷ͔ʁ • ൑ఆϞσϧΛΫϥΠΞϯτʹஔ͍ͯ൑ఆ • ϞσϧαΠζ͕େ͖͍(100MB~)ͷͰɺݱ࣮తͰͳ͍ • (αΠζͷখ͍͞ϞσϧΛݚڀத) •

    ൑ఆΛߦ͏ίϯϙʔωϯτΛ֎෦ʹஔ͘ • HTTP Serverʁ σʔλϑϩʔʗϫʔΫϑϩʔ

  9. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO4FSWFS QZUIPO DIBJOFS

  10. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO DIBJOFS

  11. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO 1045DMBTTJGZ\QIPUPCJOBSZ^ DIBJOFS

  12. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO 1045DMBTTJGZ\QIPUPCJOBSZ^ SFTVMU\JT@GPPECPPM^

    DIBJOFS

  13. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO 1045DMBTTJGZ\QIPUPCJOBSZ^ SFTVMU\JT@GPPECPPM^

    DIBJOFS SFTVMU\JT@GPPECPPM^

  14. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO 1045DMBTTJGZ\QIPUPCJOBSZ^ SFTVMU\JT@GPPECPPM^

    DIBJOFS ը૾ͷΞοϓϩʔυ ը૾ॲཧ ൑ఆ SFTVMU\JT@GPPECPPM^

  15. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ 1045DMBTTJGZ\QIPUPCJOBSZ^ $MBTTJpDBUJPO4FSWFS QZUIPO 1045DMBTTJGZ\QIPUPCJOBSZ^ SFTVMU\JT@GPPECPPM^

    DIBJOFS ը૾ͷΞοϓϩʔυ ը૾ॲཧ ൑ఆ SFTVMU\JT@GPPECPPM^ >>> 300~500 ms <<<

  16. • ը૾ॲཧͱϞσϧʹinferenceʹֻ͕͔ͦͦ࣌ؒ͜͜Δ
 (300~500ms) • APIαʔόʔ͔Βಉظతʹୟ͚ͳ͍
 (Unicorn ͷ worker͕ਚ͖ͯ͠·͏) • Amazon

    S3, SQSΛར༻ͨ͠ඇಉظͳ൑ఆॲཧϫʔΫϑϩʔ σʔλϑϩʔʗϫʔΫϑϩʔ

  17. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    "NB[PO424 2VFVF %#

  18. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> "NB[PO424 2VFVF %#

  19. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ %#

  20. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ %#

  21. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ <%PXOMPBE*NBHF> %#

  22. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ 1045SFTVMU
 \LFZ@PO@TTUSJOH SFTVMU\JT@GPPE <%PXOMPBE*NBHF> %#

  23. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS "NB[PO4 4UPSBHF

    <6QMPBEQIPUPUPDMBTTJGZ> 1045JT@QIPUP\LFZ@PO@TTUSJOH^ "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ 1045SFTVMU
 \LFZ@PO@TTUSJOH SFTVMU\JT@GPPE <%PXOMPBE*NBHF> %#

  24. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS SFTVMU\JT@GPPECPPM^ "NB[PO4

    4UPSBHF <6QMPBEQIPUPUPDMBTTJGZ> 1045JT@QIPUP\LFZ@PO@TTUSJOH^ "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ 1045SFTVMU
 \LFZ@PO@TTUSJOH SFTVMU\JT@GPPE <%PXOMPBE*NBHF> %#

  25. $MJFOU "OESPJE J04 "1*4FSWFS SVCZ $MBTTJpDBUJPO8PSLFS QZUIPO DIBJOFS SFTVMU\JT@GPPECPPM^ "NB[PO4

    4UPSBHF <6QMPBEQIPUPUPDMBTTJGZ> 1045JT@QIPUP\LFZ@PO@TTUSJOH^ "NB[PO424 2VFVF FORVFVF
 \LFZ@PO@TTUSJOH^ EFRVFVF
 \LFZ@PO@TTUSJOH^ 1045SFTVMU
 \LFZ@PO@TTUSJOH SFTVMU\JT@GPPECPPM^^ <%PXOMPBE*NBHF> ඇಉظʹ൑ఆॲཧ

  26. • ྉཧࣸਅͷࣗಈऩूαʔϏεΛ • CaffeNet[1]Λݩʹ࡞ͬͨྉཧը૾ೝࣝϞσϧͱ • Amazon SQS/S3 Ͱߏங͞Εͨσʔλϑϩʔͱ • Amazon

    ECS Λར༻ͯ͠ӡ༻͍ͯ͠Δ࿩ <>IUUQTHJUIVCDPN#7-$DB⒎F Agenda

  27. • ECS: Amazon EC2 Container Service • Docker ContainerΛEC2Ͱߏ੒͞ΕͨΫϥελʹ഑ஔ(Task) •

    github.com/eagletmt/hako • ECSͷߏ੒ΛyamlϑΝΠϧͰ؅ཧ ECSͱGPUͱDockerͱ…

  28. "8471$ # cookpadnet-worker.yml scheduler: type: ecs region: ap-northeast-1 cluster: hako-production-g2

    desired_count: 1 app: image: cookpadnet-worker-gpu cpu: 128 memory: 3072 memory_reservation: 2048 env: AWS_REGION: ap-northeast-1 COOKPADNET_ENV: production ... %PDLFS3FHJTUSZ ։ൃऀ EPDLFSQVTI IBLPEFQMPZ &$4 EPDLFSQVMM 5BTL DPPLQBEOFUXPSLFS

  29. "8471$ # cookpadnet-worker.yml scheduler: type: ecs region: ap-northeast-1 cluster: hako-production-g2

    desired_count: 1 app: image: cookpadnet-worker-gpu cpu: 128 memory: 3072 memory_reservation: 2048 env: AWS_REGION: ap-northeast-1 COOKPADNET_ENV: production ... %PDLFS3FHJTUSZ ։ൃऀ EPDLFSQVTI IBLPEFQMPZ &$4 EPDLFSQVMM 5BTL DPPLQBEOFUXPSLFS DockerԽ͞ΕͨWorkerΛ
 hakoͰσϓϩΠ & ߏ੒؅ཧ

  30. w XPSLFSͰ͸(16Λ࢖༻ w ಉՁ֨ଳͷ$16Πϯελϯεͱൺ΂ͯ ഒͷੑೳࠩ w %PDLFS (16 GPU

  31. • Driver͕ඞཁ • nvidia-driverͷkernel module • ಉ͡όʔδϣϯͷuser-level drivers • Docker

    Container͔ΒGPU devicesΛૢ࡞͢Δҝ
 Containerʹద੾ͳLinux Capabilityͷઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ

  32. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT

  33. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT

  34. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT ESJWFSךQBUIכ04ח״׶殯ז׷

  35. NVIDIA Docker • Docker CLIͷബ͍ϥούʔ • `docker run` ࣌ʹඞཁͳvolumeΛࣗಈతʹmount
 ͯ͘͠ΕΔ

  36. NVIDIA Docker • Docker CLIͷബ͍ϥούʔ • `docker run` ࣌ʹඞཁͳvolumeΛࣗಈతʹmount
 ͯ͘͠ΕΔ

    "NB[PO&$4דכ劢؟ه٦ز

  37. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT

  38. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT (ಉҰόʔδϣϯ)

  39. ubuntu EPDLFSDPOUBJOFS ཧ૝ OWJEJB(16 VTFSMFWFMESJWFS LFSOFMNPEVMFT 㣐⡤鍑寸 (ಉҰόʔδϣϯ)

  40. • Driver͕ඞཁ • nvidia-driverͷkernel module • ಉ͡όʔδϣϯͷuser-level drivers • Docker

    Container͔ΒGPU devicesΛૢ࡞͢Δҝ
 Containerʹద੾ͳLinux Capabilityͷઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ

  41. • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOa EFWJDFEFWOWJEJBEFWOWJEJBa EFWJDFEFWOWJEJBVWNEFWOWJEJBVWNa

    HQVXPSLFS

  42. • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOa EFWJDFEFWOWJEJBEFWOWJEJBa EFWJDFEFWOWJEJBVWNEFWOWJEJBVWNa

    HQVXPSLFS &$4ͷ5BTLఆٛʹ͓͍ͯEFWJDFΦϓγϣϯ͸ະαϙʔτ

  43. • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOa EFWJDFEFWOWJEJBEFWOWJEJBa EFWJDFEFWOWJEJBVWNEFWOWJEJBVWNa

    HQVXPSLFS &$4ͷ5BTLఆٛʹ͓͍ͯEFWJDFΦϓγϣϯ͸ະαϙʔτ

  44. • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOQSJWJMFHFEHQVXPSLFS

  45. Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOQSJWJMFHFEHQVXPSLFS • capability શ։์ • rootͰ࣮ߦ͞Ε͍ͯΔdockerd্ͷcontainerͷதͰrootΛ औ͍ͬͯΔͷͰ৭ʑग़དྷΔ

    EPDLFSSVOQSJWJMFHFEBMQJOFMBUFTUEBUFT • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ

  46. • GPUσόΠε͸ಛघͳϑΝΠϧͱͯ͠ଘࡏ • ΞΫηε͢ΔͨΊʹಛఆͷCapabilityઃఆ͕ඞཁ Ծ૝Խ v.s. Χʔωϧ EPDLFSSVOQSJWJMFHFEHQVXPSLFS • rootҎ֎ͷϢʔβʔͰ࣮ߦ͢Δ͜ͱʹ͢Δ

    • DockerFile಺Ͱ `USER runner`

  47. • ྉཧࣸਅͷࣗಈऩूαʔϏεΛ • CaffeNet[1]Λݩʹ࡞ͬͨྉཧը૾ೝࣝϞσϧͱ • Amazon SQS/S3 Ͱߏங͞Εͨσʔλϑϩʔͱ • Amazon

    ECS (GPU instance) Λར༻ͯ͠ӡ༻͍ͯ͠Δ࿩ <>IUUQTHJUIVCDPN#7-$DB⒎F Agenda