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
870

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
1.1k
DeepRacerで学ぶ機械学習 1.1
tandfy
0
960
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
1k

Other Decks in Programming

See All in Programming
CSS Linter による Baseline サポートの仕組み
ryo_manba
1
110
定理証明プラットフォーム lapisla.net
abap34
1
1.8k
SpringBoot3.4の構造化ログ #kanjava
irof
2
1k
Unity Android XR入門
sakutama_11
0
160
Bedrock Agentsレスポンス解析によるAgentのOps
licux
3
840
Spring gRPC について / About Spring gRPC
mackey0225
0
220
Grafana Loki によるサーバログのコスト削減
mot_techtalk
1
130
Honoとフロントエンドの 型安全性について
yodaka
7
1.2k
SwiftUIで単方向アーキテクチャを導入して得られた成果
takuyaosawa
0
270
社内フレームワークとその依存性解決 / in-house framework and its dependency management
vvakame
1
560
動作確認やテストで漏れがちな観点3選
starfish719
6
1k
pylint custom ruleで始めるレビュー自動化
shogoujiie
0
120

Featured

See All Featured
Embracing the Ebb and Flow
colly
84
4.6k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
193
16k
[RailsConf 2023] Rails as a piece of cake
palkan
53
5.2k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
100
18k
Agile that works and the tools we love
rasmusluckow
328
21k
The Power of CSS Pseudo Elements
geoffreycrofte
75
5.5k
Into the Great Unknown - MozCon
thekraken
35
1.6k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.4k
Mobile First: as difficult as doing things right
swwweet
223
9.3k
KATA
mclloyd
29
14k
Designing on Purpose - Digital PM Summit 2013
jponch
117
7.1k

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