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

Amazon SageMakerの最新アップデートの紹介

tandfy
December 16, 2019
Programming
1
860

Amazon SageMakerの最新アップデートの紹介

re:Growth 2019 Osakaでの発表内容です。

tandfy

December 16, 2019
Tweet

More Decks by tandfy

See All by tandfy
アプリから集まるイベントデータのリアルタイム処理入門
tandfy
0
1.4k
Amazon Personalizeではじめるレコメンドサービス
tandfy
0
1k
DeepRacerで学ぶ機械学習 1.1
tandfy
0
940
DeepRacerで始める機械学習
tandfy
1
1.6k
DeepRacerでまなぶ強化学習
tandfy
1
1.3k
Amazon SageMakerではじめる物体検出
tandfy
1
990

Other Decks in Programming

See All in Programming
エンジニアとして関わる要件と仕様(公開用)
murabayashi
0
300
flutterkaigi_2024.pdf
kyoheig3
0
150
どうして僕の作ったクラスが手続き型と言われなきゃいけないんですか
akikogoto
1
120
[Do iOS '24] Ship your app on a Friday...and enjoy your weekend!
polpielladev
0
110
3rd party scriptでもReactを使いたい！ Preact + Reactのハイブリッド開発
righttouch
PRO
1
610
Enabling DevOps and Team Topologies Through Architecture: Architecting for Fast Flow
cer
PRO
0
340
OSSで起業してもうすぐ10年 / Open Source Conference 2024 Shimane
furukawayasuto
0
110
ふかぼれ！CSSセレクターモジュール / Fukabore! CSS Selectors Module
petamoriken
0
150
카카오페이는 어떻게 수천만 결제를 처리할까? 우아한 결제 분산락 노하우
kakao
PRO
0
110
ActiveSupport::Notifications supporting instrumentation of Rails apps with OpenTelemetry
ymtdzzz
1
250
LLM生成文章の精度評価自動化とプロンプトチューニングの効率化について
layerx
PRO
2
190
TypeScript Graph でコードレビューの心理的障壁を乗り越える
ysk8hori
2
1.1k

Featured

See All Featured
Building Applications with DynamoDB
mza
90
6.1k
A Philosophy of Restraint
colly
203
16k
Unsuck your backbone
ammeep
668
57k
Product Roadmaps are Hard
iamctodd
PRO
49
11k
Why You Should Never Use an ORM
jnunemaker
PRO
54
9.1k
RailsConf 2023
tenderlove
29
900
Raft: Consensus for Rubyists
vanstee
136
6.6k
Docker and Python
trallard
40
3.1k
Automating Front-end Workflow
addyosmani
1366
200k
How to Think Like a Performance Engineer
csswizardry
20
1.1k
ピンチをチャンスに：未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
109
49k
We Have a Design System, Now What?
morganepeng
50
7.2k

Transcript

  1. "NB[PO4BHF.BLFS࠷৽Ξοϓσʔτ  େᖒ༐ే SF(SPXUI04","

  2. ࣗݾ঺հ  େᖒ༐ే σʔλΞφϦςΟΫεࣄۀຊ෦ΠϯςάϨʔγϣϯ෦ ػցֶशνʔϜΤϯδχΞ!େࡕ w 4BHF.BLFSؔ࿈ϒϩάຊ d  w

    SF*OWFOUࢀՃճ໨

  3. εϥΠυ͸ޙͰೖख͢Δ͜ͱ͕ग़དྷ·͢ͷͰ ൃදதͷ಺༰ΛϝϞ͢Δඞཁ͸͋Γ·ͤΜɻ ࣸਅࡱӨΛ͢Δ৔߹͸ ϑϥογϡɾγϟολʔԻ͕ग़ͳ͍Α͏ʹ͝഑ྀ͍ͩ͘͞ Attention

  4.  SF*OWFOU ػցֶशؔ࿈ͷΞοϓσʔτ͕৭ʑ͋Γ·ͨ͠

  5. ػցֶशؔ࿈Ξοϓσʔτ  w "84%FFQ$PNQPTFS ϓϨϏϡʔ  w $POUBDU-FOTGPS"NB[PO $POOFDU ϓϨϏϡʔ

     w "NB[PO'SBVE%FUFDUPS ϓϨϏϡʔ  w "NB[PO,FOESB ϓϨϏϡʔ  w "NB[PO$PEF(VSV ϓϨϏϡʔ  w "NB[PO"VHNFOUFE"* ϓϨϏϡʔ w"NB[PO4BHF.BLFS4UVEJP w"NB[PO4BHF.BLFS/PUFCPPLT ϓϨϏϡʔ  w"NB[PO4BHF.BLFS%FCVHHFS w"NB[PO4BHF.BLFS&YQFSJNFOUT w"NB[PO4BHF.BLFS"VUPQJMPU w"NB[PO4BHF.BLFS1SPDFTTJOH w"NB[PO4BHF.BLFS.PEFM.POJUPS w"NB[PO4BHF.BLFSͷ%FFQ(SBQI-JCSBSZର Ԡ w"NB[PO4BHF.BLFS0QFSBUPSTGPS ,VCFSOFUFT

  6. ػցֶशؔ࿈Ξοϓσʔτ  w "84%FFQ$PNQPTFS ϓϨϏϡʔ  w $POUBDU-FOTGPS"NB[PO$POOFDU ϓϨϏϡʔ 

    w "NB[PO'SBVE%FUFDUPS ϓϨϏϡʔ  w "NB[PO,FOESB ϓϨϏϡʔ  w "NB[PO$PEF(VSV ϓϨϏϡʔ  w "NB[PO"VHNFOUFE"* ϓϨϏϡʔ w"NB[PO4BHF.BLFS4UVEJP w"NB[PO4BHF.BLFS/PUFCPPLT ϓϨϏϡʔ  w"NB[PO4BHF.BLFS%FCVHHFS w"NB[PO4BHF.BLFS&YQFSJNFOUT w"NB[PO4BHF.BLFS"VUPQJMPU w"NB[PO4BHF.BLFS1SPDFTTJOH w"NB[PO4BHF.BLFS.PEFM.POJUPS w"NB[PO4BHF.BLFSͷ%FFQ(SBQI-JCSBSZ ରԠ w"NB[PO4BHF.BLFS0QFSBUPSTGPS ,VCFSOFUFT

  7. ࠓ೔࿩͢಺༰  w"NB[PO4BHF.BLFS4UVEJP w"NB[PO4BHF.BLFS/PUFCPPLT w"NB[PO4BHF.BLFS%FCVHHFS w"NB[PO4BHF.BLFS &YQFSJNFOUT w"NB[PO4BHF.BLFS"VUPQJMPU w"NB[PO4BHF.BLFS1SPDFTTJOH w"NB[PO4BHF.BLFS.PEFM.POJUPS

    w"NB[PO4BHF.BLFSͷ%FFQ(SBQI-JCSBSZରԠ w"NB[PO4BHF.BLFS0QFSBUPSTGPS,VCFSOFUFT wػցֶशʹ͓͚ΔϫʔΫϑϩʔ w"NB[PO4BHF.BLFS֓ཁ w"NB[PO4BHF.BLFSͷ֤छΞοϓσʔτ಺༰

  8.  ػցֶशͷϫʔΫϑϩʔ

  9. ػցֶशͷϫʔΫϑϩʔ 

  10. ػցֶशͷϫʔΫϑϩʔ  ࣮ݧΛ܁Γฦ͢

  11. ػցֶशͷϫʔΫϑϩʔ  ͻͨ͢Β܁Γฦ͢

  12.  "NB[PO4BHF.BLFS

  13. ͜Ε·Ͱͷ "NB[PO4BHF.BLFS  Πϯϑϥ؅ཧෆཁͰ&%"͔ΒϞσϧͷӡ༻·ͰՄೳͳ ػցֶशͷϑϧϚωʔδυαʔϏε w+VQZUFSͷϗεςΟϯά wػցֶशϞσϧͷֶशͱϋΠύʔύϥϝʔλνϡʔχϯά wػցֶशϞσϧͷϗεςΟϯάͱόονਪ࿦ w֤छ૊ΈࠐΈΞϧΰϦζϜͷ༻ҙ֤छϑϨʔϜϫʔΫʹ΋ରԠ w"NB[PO4BHF.BLFS(SPVOE5SVUIϥϕϧ͚ͮ

    Ξϊςʔγϣϯ δϣϒͷ࡞੒ͱ؅ཧ w"NB[PO4BHF.BLFS/FPϞσϧͷίϯύΠϧ w"NB[PO4BHF.BLFS4FBSDIֶशδϣϒͷݕࡧͱൺֱ

  14.  "NB[PO4BHF.BLFS ֤छΞοϓσʔτ಺༰

  15.  "NB[PO4BHF.BLFS4UVEJP

  16. "NB[PO4BHF.BLFS4UVEJP  ػցֶशͷͨΊͷ౷߹։ൃ؀ڥ *%&  w+VQZUFS-BCϕʔε w"NB[PO4BHF.BLFSͷ֤ػೳͱ࿈ܞ wίʔυϕʔεͰͷ&%"͔Β࣮ݧɺӡ༻·ͰՄೳ w440ͰͷϢʔβ؅ཧɾΞΫηε͕Մೳ wΦϋΠΦϦʔδϣϯͰར༻Մೳ

  17. "NB[PO4BHF.BLFS4UVEJP  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  18.  "NB[PO4BHF.BLFS/PUFCPPLT ϓϨϏϡʔ

  19. "NB[PO4BHF.BLFS/PUFCPPLT ϓϨϏϡʔ  +VQZUFSϊʔτϒοΫͷར༻ͱڞ༗͕؆୯ʹ w+VQZUFS+VQZUFS-BC͕਺ඵͰ࢖͑Δ wΠϯϑϥ؅ཧ͸ෆཁ wϊʔτϒοΫͷڞ༗͕؆୯ʹͰ͖Δ wܭࢉϦιʔεͷ੾Γସ͑΋؆୯

  20. ϊʔτϒοΫͷڞ༗  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  21.  "NB[PO4BHF.BLFS &YQFSJNFOUT

  22. "NB[PO4BHF.BLFS&YQFSJNFOUT 

  23. "NB[PO4BHF.BLFS&YQFSJNFOUT  ػցֶशδϣϒ΍࣮ݧͷ؅ཧɾൺֱΛΑΓ؆୯ʹ w࣮ݧ໊ͱτϥΠΞϧ໊Ͱ֤छδϣϒΛ؅ཧ w࣮ݧ͸τϥΠΞϧͷू߹ɺτϥΠΞϧ͸τϥΠΞϧίϯϙʔωϯτͰߏ੒ w"NB[PO4BHF.BLFS4UVEJPͱ࿈ܞ͢Δ͜ͱͰɺ(6*Ͱͷ ؅ཧͱൺֱ͕Մೳ

  24. ֶश࣌ʹ͓͚ΔϩεͷมԽΛൺֱ  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  25.  "NB[PO4BHF.BLFS%FCVHHFS

  26. "NB[PO4BHF.BLFS%FCVHHFS 

  27. "NB[PO4BHF.BLFS%FCVHHFS  ϞσϧͷֶशΛޮ཰Խ wֶशதʹࢦఆͨ͠σʔλΛऩू wֶशঢ়ଶͷϧʔϧϕʔεͷϞχλϦϯά w$MPVE8BUDIͱ࿈ܞͨ͠ϧʔϧϕʔεͷϦΞϧλΠϜΞΫ γϣϯ w5FOTPS'MPXɺ1Z5PSDIɺ.9/FUɺ9(#PPTUʹαϙʔτ

  28. ؂ࢹϧʔϧͷఆٛɺϧʔϧҧ൓ݕग़ɺϩεΧʔϒ  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  29.  "NB[PO4BHF.BLFS 1SPDFTTJOH

  30. "NB[PO4BHF.BLFS1SPDFTTJOH 

  31. "NB[PO4BHF.BLFS1SPDFTTJOH  લޙॲཧͱධՁॲཧͷϚωʔδυαʔϏε wεΫϦϓτͱ࣮ߦ؀ڥɺೖग़ྗ৘ใ͚ͩͰ࣮ߦՄೳ w"NB[PO4BHF.BLFSʹֶशҎ֎ͷॲཧΛΦϑϩʔυͰ͖Δ wಠࣗίϯςφͷར༻΋Մೳ

  32. εΫϦϓτྫ  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-processin-fully-managed-data-processing-and-model-evaluation/?nc1=b_rp

  33.  "NB[PO4BHF.BLFS.PEFM .POJUPS

  34. "NB[PO4BHF.BLFS.PEFM.POJUPS 

  35. "NB[PO4BHF.BLFS.PEFM.POJUPS  Ϟσϧӡ༻࣌ͷҟৗΛݕग़ wσϓϩΠͨ͠Ϟσϧͷೖग़ྗσʔλΛه࿥ɾ෼ੳ wϞχλϦϯάδϣϒͷఆظ࣮ߦ wϧʔϧϕʔεͰͷҟৗνΣοΫ w$MPVE8BUDIͱͷ࿈ܞ

  36. ͋Δಛ௃ྔͷ߹ܭ஋ͷൺֱ ج४σʔλͱϞχλϦϯάσʔλ  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  37.  "NB[PO4BHF.BLFS"VUPQJMPU

  38. "NB[PO4BHF.BLFS"VUPQJMPU 

  39. "NB[PO4BHF.BLFS"VUPQJMPU  "VUP.- w&%"͔ΒલॲཧɺΞϧΰϦζϜͷબ୒ɺֶशɺνϡʔχϯά ·ͰࣗಈͰ࣮ߦ wߦͬͨલॲཧ΍ֶशΛ࠶ݱՄೳͳϊʔτϒοΫͷࣗಈ࡞੒

  40. "VUPQJMPUʹΑΔτϥΠΞϧҰཡ  https://aws.amazon.com/jp/blogs/news/amazon-sagemaker-studio-the-first-fully-integrated-development-environment-for-machine-learning/

  41.  "NB[PO4BHF.BLFSͷ%FFQ (SBQI-JCSBSZରԠ

  42. "NB[PO4BHF.BLFSͷ%FFQ(SBQI-JCSBSZରԠ  "NB[PO4BHF.BLFSͰάϥϑσʔλͷֶश͕ΑΓ؆ ୯ʹ w%FFQ(SBQI-JCSBSZ͸άϥϑߏ଄Λ࣋ͬͨσʔλͷͨΊͷ 044ͷਂ૚ֶशϑϨʔϜϫʔΫ wόοΫΤϯυ͸1Z5PSDIͱ.9/FUʹରԠ wίϯςφΠϝʔδ͕༻ҙ͞Ε͍ͯΔͨΊɺεΫϦϓτͱύϥ ϝʔλɺσʔλ͚ͩͰֶशՄೳ

  43. εΫϦϓτྫ  https://aws.amazon.com/jp/blogs/news/now-available-on-amazon-sagemaker-the-deep-graph-library/?nc1=b_rp

  44.  "NB[PO4BHF.BLFS0QFSBUPS GPS,VCFSOFUFT

  45. "NB[PO4BHF.BLFS0QFSBUPSGPS,VCFSOFUFT  ,VCFSOFUFTΛհͨ͠4BHF.BLFSͷར༻͕Մೳʹ wϞσϧͷֶश͚ͩͰͳ͘ɺνϡʔχϯά΍ϗεςΟϯά΋Մ ೳ w,VCFSOFUFT"1*΍LVCFDUM͔Β4BHF.BLFSͰͷδϣϒ͕࡞ ੒Մೳ

  46. ֶशδϣϒΛΧελϜϦιʔεͱͯ͠ఆٛ͠ɺ࣮ߦ  https://aws.amazon.com/jp/blogs/news/introducing-amazon-sagemaker-operators-for-kubernetes/?nc1=b_rp

  47.  ·ͱΊ

  48. "NB[PO4BHF.BLFS͕ύϫʔΞοϓʂ  %FFQ(SBQI-JCSBSZʹ΋ରԠʂ,VCFSOFUFT͔Β΋࢖͑Δʂ