Upgrade to Pro — share decks privately, control downloads, hide ads and more …
Sign up for free

Build Image Classification service with Amazon ...

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
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
370
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
22k
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
470

Other Decks in Programming

See All in Programming
Vue Fes Japan の “作る側”に関わってみて
Avatar for Naoki Haba naokihaba
0
160
3回つくってわかった、
定期実行ジョブ基盤の本質情報
Avatar for Naoto Takai takai
0
530
[2026-10-14](C)Re:ゼロから始める異世界生活〜始まりの終わりと終わりの始まり〜
Avatar for tosite tosite
0
110
Kotlinの15年とServer-Side Kotlin
Avatar for Takehata Naoto n_takehata
1
160
個人開発者よ、Honoを使え（おじさんver）
Avatar for tanahiro2010 tanahiro2010
2
270
dotNET_vulnclicker_intro.pdf
Avatar for Tomohiko Morita deka_morita
0
150
[JA] Domain Modeling with Vanilla Rails: 「操作」から再考するRailsの設計論
Avatar for Yuichi Goto yasaichi
3
480
當我們開始不讀 Code - AI Agent 時代，Code Review 與 Clean Code 還剩下什麼？
Avatar for James Wang jame2408
1
270
TechTown - Creating Composable Callables in Contemporary C++
Avatar for Björn Fahller rollbear
0
130
月間100万人のサービス刷新で、 技術選定をHonoに振り切った話
Avatar for bara yutobara
8
6.7k
re:Inventに行く前に知っておきたい現地参加のノウハウ
Avatar for nokomoro3 nokomoro3
0
440
コードで差別化できない時代の ソフトウェアエンジニアリング / Software Engineering in an Era Where Code Doesn’t Differentiate
Avatar for Naoki Kishida kishida
2
180

Featured

See All Featured
Context Engineering - Making Every Token Count
Avatar for Addy Osmani addyosmani
9
1.2k
Optimising Largest Contentful Paint
Avatar for Harry Roberts csswizardry
37
4k
A Modern Web Designer's Workflow
Avatar for Chris Coyier chriscoyier
699
190k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
Avatar for Morgane Peng morganepeng
133
20k
A brief & incomplete history of 
UX Design for the World Wide Web: 1989–2019
Avatar for Jason CranfordTeague jct
2
540
Understanding Cognitive Biases in Performance Measurement
Avatar for Philip Tellis bluesmoon
32
3.1k
BBQ
Avatar for Matthew Crist matthewcrist
90
10k
Marketing to machines
Avatar for Jono Alderson jonoalderson
1
5.9k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
Avatar for Mfonobong Umondia mfonobong
2
590
The Cult of Friendly URLs
Avatar for Andy Hume andyhume
79
7k
Building AI with AI
Avatar for Ines Montani inesmontani
PRO
1
1.3k
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
Avatar for Katarina Dahlin katarinadahlin
PRO
3
3.9k

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