SlideShare a Scribd company logo

【14-C-7】コンピュータビジョンを支える深層学習技術の新潮流

Developers Summit
Developers Summit
Developers SummitDevelopers Summit

Developers Summit 2019【14-C-7】鮫島様の講演資料です。

【14-C-7】コンピュータビジョンを支える深層学習技術の新潮流

1 of 44
Download to read offline
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Masaki Samejima
Machine Learning Solutions Architect, Amazon Web Services Japan.
2019.2.14
Developers Summit 2019
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Agenda
•
•
•
•
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
•
•
Demographic Data
Facial Landmarks
Sentiment Expressed
Image Quality
General Attributes
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
2012
SuperVision[1]
ILSVRC2012
[1] A. Krizhevsky, et al., Imagenet classification with deep convolutional neural networks, NIPS 2012.
[2] R Girshick, et al., Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014.
[3] I.J. Goodfellow, et al., Generative Adversarial Nets, NIPS 2014.
[4] V. Badrinarayanan, et al, SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. PAMI 2017
2014
R-CNN[2] Pascal
VOC GAN[3] SegNet[4]
2015
© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
https://gluon-cv.mxnet.io/model_zoo/classification.html
senet_154
resnet_v1d
resnet_v1c
resnet_v1b
resnet_v1
densenet
darknet
VGG
resnet_v2
mobilenet
mobilenetv2
0.80
0.75
0.70
Accuracy
1000 2000 #sample/sec.3000 4000
• ImageNet 80%
• V100 GPU

Recommended

Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...
Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...
Building Content Recommendation Systems Using Apache MXNet and Gluon - MCL402...Amazon Web Services
 
NEW LAUNCH! Infinitely Scalable Machine Learning Algorithms with Amazon AI - ...
NEW LAUNCH! Infinitely Scalable Machine Learning Algorithms with Amazon AI - ...NEW LAUNCH! Infinitely Scalable Machine Learning Algorithms with Amazon AI - ...
NEW LAUNCH! Infinitely Scalable Machine Learning Algorithms with Amazon AI - ...Amazon Web Services
 
Building Content Recommendation Systems using MXNet Gluon
Building Content Recommendation Systems using MXNet GluonBuilding Content Recommendation Systems using MXNet Gluon
Building Content Recommendation Systems using MXNet GluonApache MXNet
 
MCL310_Building Deep Learning Applications with Apache MXNet and Gluon
MCL310_Building Deep Learning Applications with Apache MXNet and GluonMCL310_Building Deep Learning Applications with Apache MXNet and Gluon
MCL310_Building Deep Learning Applications with Apache MXNet and GluonAmazon Web Services
 
SageMaker Algorithms Infinitely Scalable Machine Learning
SageMaker Algorithms Infinitely Scalable Machine LearningSageMaker Algorithms Infinitely Scalable Machine Learning
SageMaker Algorithms Infinitely Scalable Machine LearningAmazon Web Services
 
Debugging and Performance tricks for MXNet Gluon
Debugging and Performance tricks for MXNet GluonDebugging and Performance tricks for MXNet Gluon
Debugging and Performance tricks for MXNet GluonApache MXNet
 
Build Deep Learning Applications Using Apache MXNet - Featuring Chick-fil-A (...
Build Deep Learning Applications Using Apache MXNet - Featuring Chick-fil-A (...Build Deep Learning Applications Using Apache MXNet - Featuring Chick-fil-A (...
Build Deep Learning Applications Using Apache MXNet - Featuring Chick-fil-A (...Amazon Web Services
 
Working with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model TrainingWorking with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model TrainingAmazon Web Services
 

More Related Content

Similar to 【14-C-7】コンピュータビジョンを支える深層学習技術の新潮流

Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...
Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...
Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...Amazon Web Services
 
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...Lisa Roth, PMP
 
Amazon SageMaker Algorithms: Machine Learning Week San Francisco
Amazon SageMaker Algorithms: Machine Learning Week San FranciscoAmazon SageMaker Algorithms: Machine Learning Week San Francisco
Amazon SageMaker Algorithms: Machine Learning Week San FranciscoAmazon Web Services
 
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...Amazon Web Services
 
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...Amazon Web Services
 
Time series modeling workd AMLD 2018 Lausanne
Time series modeling workd AMLD 2018 LausanneTime series modeling workd AMLD 2018 Lausanne
Time series modeling workd AMLD 2018 LausanneSunil Mallya
 
Real Time and Offline Applications with GraphQL
Real Time and Offline Applications with GraphQLReal Time and Offline Applications with GraphQL
Real Time and Offline Applications with GraphQLAmazon Web Services
 
Deep Learning at AWS: Embedding & Attention Models
Deep Learning at AWS: Embedding & Attention ModelsDeep Learning at AWS: Embedding & Attention Models
Deep Learning at AWS: Embedding & Attention ModelsAmazon Web Services
 
AMF305_Autonomous Driving Algorithm Development on Amazon AI
AMF305_Autonomous Driving Algorithm Development on Amazon AIAMF305_Autonomous Driving Algorithm Development on Amazon AI
AMF305_Autonomous Driving Algorithm Development on Amazon AIAmazon Web Services
 
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018Amazon Web Services Korea
 
Enhanced Media Workflows Using Amazon AI
Enhanced Media Workflows Using Amazon AIEnhanced Media Workflows Using Amazon AI
Enhanced Media Workflows Using Amazon AIAmazon Web Services
 
Working with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model TrainingWorking with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model TrainingAmazon Web Services
 
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...Amazon Web Services
 
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...Amazon Web Services
 
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...Amazon Web Services Korea
 
From notebook to production with Amazon Sagemaker
From notebook to production with Amazon SagemakerFrom notebook to production with Amazon Sagemaker
From notebook to production with Amazon SagemakerAmazon Web Services
 
Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)Amazon Web Services
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Amazon Web Services
 
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Amazon Web Services
 

Similar to 【14-C-7】コンピュータビジョンを支える深層学習技術の新潮流 (20)

Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...
Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...
Build Deep Learning Applications Using Apache MXNet, Featuring Workday (AIM40...
 
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...
MongoDB .local London 2019: Using AWS to Transform Customer Data in MongoDB i...
 
Amazon SageMaker Algorithms: Machine Learning Week San Francisco
Amazon SageMaker Algorithms: Machine Learning Week San FranciscoAmazon SageMaker Algorithms: Machine Learning Week San Francisco
Amazon SageMaker Algorithms: Machine Learning Week San Francisco
 
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
Build, train, and deploy machine learning models at scale - AWS Summit Cape T...
 
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...
[NEW LAUNCH!] Introducing Amazon Elastic Inference: Reduce Deep Learning Infe...
 
Time series modeling workd AMLD 2018 Lausanne
Time series modeling workd AMLD 2018 LausanneTime series modeling workd AMLD 2018 Lausanne
Time series modeling workd AMLD 2018 Lausanne
 
Real Time and Offline Applications with GraphQL
Real Time and Offline Applications with GraphQLReal Time and Offline Applications with GraphQL
Real Time and Offline Applications with GraphQL
 
Deep Learning at AWS: Embedding & Attention Models
Deep Learning at AWS: Embedding & Attention ModelsDeep Learning at AWS: Embedding & Attention Models
Deep Learning at AWS: Embedding & Attention Models
 
AMF305_Autonomous Driving Algorithm Development on Amazon AI
AMF305_Autonomous Driving Algorithm Development on Amazon AIAMF305_Autonomous Driving Algorithm Development on Amazon AI
AMF305_Autonomous Driving Algorithm Development on Amazon AI
 
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
엔터프라이즈를 위한 머신러닝 그리고 AWS (김일호 솔루션즈 아키텍트, AWS) :: AWS Techforum 2018
 
Amazon SageMaker
Amazon SageMakerAmazon SageMaker
Amazon SageMaker
 
Enhanced Media Workflows Using Amazon AI
Enhanced Media Workflows Using Amazon AIEnhanced Media Workflows Using Amazon AI
Enhanced Media Workflows Using Amazon AI
 
Working with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model TrainingWorking with Amazon SageMaker Algorithms for Faster Model Training
Working with Amazon SageMaker Algorithms for Faster Model Training
 
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
 
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...
Advanced Patterns in Microservices Implementation with Amazon ECS - CON402 - ...
 
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...
Amazon SageMaker 기반 고품질 데이터 생성 및 심화 기계학습 기법 - 김필호 솔루션즈 아키텍트, AWS / 강정희 솔루션즈 아...
 
From notebook to production with Amazon Sagemaker
From notebook to production with Amazon SagemakerFrom notebook to production with Amazon Sagemaker
From notebook to production with Amazon Sagemaker
 
Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)Amazon SageMaker 內建機器學習演算法 (Level 400)
Amazon SageMaker 內建機器學習演算法 (Level 400)
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
 
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...
 

More from Developers Summit

【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」
【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」
【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」Developers Summit
 
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~Developers Summit
 
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~Developers Summit
 
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみるDevelopers Summit
 
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。Developers Summit
 
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦Developers Summit
 
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツールDevelopers Summit
 
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツールDevelopers Summit
 
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)Developers Summit
 
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~Developers Summit
 
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えしますDevelopers Summit
 
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~Developers Summit
 
【15-A-1】ドラゴンクエストXを支える失敗事例
【15-A-1】ドラゴンクエストXを支える失敗事例【15-A-1】ドラゴンクエストXを支える失敗事例
【15-A-1】ドラゴンクエストXを支える失敗事例Developers Summit
 
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~Developers Summit
 
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜Developers Summit
 
【B-5】モダンな開発を実現するツールチェーンのご紹介
【B-5】モダンな開発を実現するツールチェーンのご紹介【B-5】モダンな開発を実現するツールチェーンのご紹介
【B-5】モダンな開発を実現するツールチェーンのご紹介Developers Summit
 
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習Developers Summit
 
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道Developers Summit
 
【B-2】AI時代におけるエンジニアの生存戦略
【B-2】AI時代におけるエンジニアの生存戦略【B-2】AI時代におけるエンジニアの生存戦略
【B-2】AI時代におけるエンジニアの生存戦略Developers Summit
 
【B-2】AI時代のエンジニア生存戦略
【B-2】AI時代のエンジニア生存戦略【B-2】AI時代のエンジニア生存戦略
【B-2】AI時代のエンジニア生存戦略Developers Summit
 

More from Developers Summit (20)

【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」
【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」
【18-A-2】ゲーミフィケーション・エバンジェリストが見る「あなたの技術力が“ワクワクするサービス”に変わる未来」
 
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・小林様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
 
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
【C-2・醍醐様】AIとAPIがITインフラにもたらす変化 ~プログラマブルなクラウド型Wi-Fi~
 
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる
【B-4】オープンソース開発で、フリー静的解析ツールを使ってみる
 
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。
【B-6】Androidスマホの生体認証の脆弱性、調べてみたらよくある話だった。
 
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦
【13-B-6】Hondaの生産技術屋さんがソフトウェア開発でアジャイルを初導入し組織変革に挑戦
 
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
 
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
【15-E-7】セキュアな環境でDevOpsを実現する厳選ツール
 
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)
【14-E-3】セキュリティ・テストの自動化によるDevSecOpsの実現 (デモ有)
 
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~
【15-D-2】デンソーのMaaS開発~アジャイル開発で顧客との協調・チームビルディング・実装概要~
 
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします
【14-C-8】みんなの暮らしを支えるAmazon S3の裏側、お伝えします
 
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~
【15-B-7】無意味なアラートからの脱却 ~ Datadogを使ってモダンなモニタリングを始めよう ~
 
【15-A-1】ドラゴンクエストXを支える失敗事例
【15-A-1】ドラゴンクエストXを支える失敗事例【15-A-1】ドラゴンクエストXを支える失敗事例
【15-A-1】ドラゴンクエストXを支える失敗事例
 
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~
【15-A-5】ゲーミフィケーションエバンジェリストが説く、アプリ開発で見落としがちな「おもてなし」とは~面白さを伝える × 面白く魅せる~
 
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜
【B-2】福岡発Node.jsで支える大規模システム!〜「誰ガ為のアルケミスト」と歩んだ三年〜
 
【B-5】モダンな開発を実現するツールチェーンのご紹介
【B-5】モダンな開発を実現するツールチェーンのご紹介【B-5】モダンな開発を実現するツールチェーンのご紹介
【B-5】モダンな開発を実現するツールチェーンのご紹介
 
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習
【C-2】メモリも、僕のキャパシティも溢れっぱなし。。2年目エンジニアが実現した機械学習
 
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道
【A-2】とあるマーケティング部隊とデータエンジニアのデータドリブンへの道
 
【B-2】AI時代におけるエンジニアの生存戦略
【B-2】AI時代におけるエンジニアの生存戦略【B-2】AI時代におけるエンジニアの生存戦略
【B-2】AI時代におけるエンジニアの生存戦略
 
【B-2】AI時代のエンジニア生存戦略
【B-2】AI時代のエンジニア生存戦略【B-2】AI時代のエンジニア生存戦略
【B-2】AI時代のエンジニア生存戦略
 

Recently uploaded

21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN
21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN
21ST CENTURY LITERACY FROM TRADITIONAL TO MODERNRonnelBaroc
 
Azure Migration Guide for IT Professionals
Azure Migration Guide for IT ProfessionalsAzure Migration Guide for IT Professionals
Azure Migration Guide for IT ProfessionalsChristine Shepherd
 
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdf
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdfQuinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdf
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdfDomotica daVinci
 
Manual Eurotronic Thermostatic Valve Comry Z-Wave
Manual Eurotronic Thermostatic Valve Comry Z-WaveManual Eurotronic Thermostatic Valve Comry Z-Wave
Manual Eurotronic Thermostatic Valve Comry Z-WaveDomotica daVinci
 
Enhancing SaaS Performance: A Hands-on Workshop for Partners
Enhancing SaaS Performance: A Hands-on Workshop for PartnersEnhancing SaaS Performance: A Hands-on Workshop for Partners
Enhancing SaaS Performance: A Hands-on Workshop for PartnersThousandEyes
 
Heltun_HE-RS01_User_Manual_B9AH.pdf
Heltun_HE-RS01_User_Manual_B9AH.pdfHeltun_HE-RS01_User_Manual_B9AH.pdf
Heltun_HE-RS01_User_Manual_B9AH.pdfMarielaL5
 
Semiconductor Review Magazine Feature.pdf
Semiconductor Review Magazine Feature.pdfSemiconductor Review Magazine Feature.pdf
Semiconductor Review Magazine Feature.pdfkeyaramicrochipusa
 
From eSIMs to iSIMs: It’s Inside the Manufacturing
From eSIMs to iSIMs: It’s Inside the ManufacturingFrom eSIMs to iSIMs: It’s Inside the Manufacturing
From eSIMs to iSIMs: It’s Inside the ManufacturingSoracom Global, Inc.
 
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMING
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMINGAUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMING
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMINGLiveplex
 
My self introduction to know others abut me
My self  introduction to know others abut meMy self  introduction to know others abut me
My self introduction to know others abut meManoj Prabakar B
 
Automate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellenceAutomate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellencePrecisely
 
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...Memory Fabric Forum
 
Tete thermostatique Zigbee MOES BRT-100 V2.pdf
Tete thermostatique Zigbee MOES BRT-100 V2.pdfTete thermostatique Zigbee MOES BRT-100 V2.pdf
Tete thermostatique Zigbee MOES BRT-100 V2.pdfDomotica daVinci
 
AWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user groupAWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user groupAWS Chicago
 
Q1 Memory Fabric Forum: XConn CXL Switches for AI
Q1 Memory Fabric Forum: XConn CXL Switches for AIQ1 Memory Fabric Forum: XConn CXL Switches for AI
Q1 Memory Fabric Forum: XConn CXL Switches for AIMemory Fabric Forum
 
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdf
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdfLLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdf
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdfThomas Poetter
 
Q1 Memory Fabric Forum: SMART CXL Product Lineup
Q1 Memory Fabric Forum: SMART CXL Product LineupQ1 Memory Fabric Forum: SMART CXL Product Lineup
Q1 Memory Fabric Forum: SMART CXL Product LineupMemory Fabric Forum
 
Importance of magazines in education ppt
Importance of magazines in education pptImportance of magazines in education ppt
Importance of magazines in education pptsafnarafeek2002
 

Recently uploaded (20)

5 Tech Trend to Notice in ESG Landscape- 47Billion
5 Tech Trend to Notice in ESG Landscape- 47Billion5 Tech Trend to Notice in ESG Landscape- 47Billion
5 Tech Trend to Notice in ESG Landscape- 47Billion
 
COE AI Lab Universities
COE AI Lab UniversitiesCOE AI Lab Universities
COE AI Lab Universities
 
21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN
21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN
21ST CENTURY LITERACY FROM TRADITIONAL TO MODERN
 
Azure Migration Guide for IT Professionals
Azure Migration Guide for IT ProfessionalsAzure Migration Guide for IT Professionals
Azure Migration Guide for IT Professionals
 
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdf
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdfQuinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdf
Quinto Z-Wave Heltun_HE-RS01_User_Manual_B9AH.pdf
 
Manual Eurotronic Thermostatic Valve Comry Z-Wave
Manual Eurotronic Thermostatic Valve Comry Z-WaveManual Eurotronic Thermostatic Valve Comry Z-Wave
Manual Eurotronic Thermostatic Valve Comry Z-Wave
 
Enhancing SaaS Performance: A Hands-on Workshop for Partners
Enhancing SaaS Performance: A Hands-on Workshop for PartnersEnhancing SaaS Performance: A Hands-on Workshop for Partners
Enhancing SaaS Performance: A Hands-on Workshop for Partners
 
Heltun_HE-RS01_User_Manual_B9AH.pdf
Heltun_HE-RS01_User_Manual_B9AH.pdfHeltun_HE-RS01_User_Manual_B9AH.pdf
Heltun_HE-RS01_User_Manual_B9AH.pdf
 
Semiconductor Review Magazine Feature.pdf
Semiconductor Review Magazine Feature.pdfSemiconductor Review Magazine Feature.pdf
Semiconductor Review Magazine Feature.pdf
 
From eSIMs to iSIMs: It’s Inside the Manufacturing
From eSIMs to iSIMs: It’s Inside the ManufacturingFrom eSIMs to iSIMs: It’s Inside the Manufacturing
From eSIMs to iSIMs: It’s Inside the Manufacturing
 
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMING
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMINGAUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMING
AUGMENTED REALITY (AR) IN DAILY LIFE: EXPANDING BEYOND GAMING
 
My self introduction to know others abut me
My self  introduction to know others abut meMy self  introduction to know others abut me
My self introduction to know others abut me
 
Automate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellenceAutomate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center Excellence
 
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...
Q1 Memory Fabric Forum: Advantages of Optical CXL​ for Disaggregated Compute ...
 
Tete thermostatique Zigbee MOES BRT-100 V2.pdf
Tete thermostatique Zigbee MOES BRT-100 V2.pdfTete thermostatique Zigbee MOES BRT-100 V2.pdf
Tete thermostatique Zigbee MOES BRT-100 V2.pdf
 
AWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user groupAWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user group
 
Q1 Memory Fabric Forum: XConn CXL Switches for AI
Q1 Memory Fabric Forum: XConn CXL Switches for AIQ1 Memory Fabric Forum: XConn CXL Switches for AI
Q1 Memory Fabric Forum: XConn CXL Switches for AI
 
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdf
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdfLLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdf
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI.pdf
 
Q1 Memory Fabric Forum: SMART CXL Product Lineup
Q1 Memory Fabric Forum: SMART CXL Product LineupQ1 Memory Fabric Forum: SMART CXL Product Lineup
Q1 Memory Fabric Forum: SMART CXL Product Lineup
 
Importance of magazines in education ppt
Importance of magazines in education pptImportance of magazines in education ppt
Importance of magazines in education ppt
 

【14-C-7】コンピュータビジョンを支える深層学習技術の新潮流

  • 1. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Masaki Samejima Machine Learning Solutions Architect, Amazon Web Services Japan. 2019.2.14 Developers Summit 2019
  • 2. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Agenda • • • •
  • 3. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 4. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • Demographic Data Facial Landmarks Sentiment Expressed Image Quality General Attributes
  • 5. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. 2012 SuperVision[1] ILSVRC2012 [1] A. Krizhevsky, et al., Imagenet classification with deep convolutional neural networks, NIPS 2012. [2] R Girshick, et al., Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014. [3] I.J. Goodfellow, et al., Generative Adversarial Nets, NIPS 2014. [4] V. Badrinarayanan, et al, SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. PAMI 2017 2014 R-CNN[2] Pascal VOC GAN[3] SegNet[4] 2015
  • 6. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. https://gluon-cv.mxnet.io/model_zoo/classification.html senet_154 resnet_v1d resnet_v1c resnet_v1b resnet_v1 densenet darknet VGG resnet_v2 mobilenet mobilenetv2 0.80 0.75 0.70 Accuracy 1000 2000 #sample/sec.3000 4000 • ImageNet 80% • V100 GPU
  • 7. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. https://gluon-cv.mxnet.io/model_zoo/detection.html mAP 10 100 #sample/sec. 40 35 30 yolo3 faster_rcnn ssd • (IoU ) mAP 30-40% •
  • 8. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. https://gluon-cv.mxnet.io/model_zoo/segmentation.html 0 10 20 30 40 50 60 70 80 90 100 fcn_resnet101 psp_resnet101 deeplab_resnet101 fcn_resnet101 psp_resnet101 deeplab_resnet101 deeplab_resnet152 COCO VOC IoU
  • 9. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. 3 [1] [1] B. Tekin, et al., Real-Time Seamless Single Shot 6D Object Pose Prediction, CVPR 2018. [2] R. Girdhar, et al., Detect-and-Track: Efficient Pose Estimation in Videos, CVPR 2018. [3] L. Chen, et al., MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features, CVPR 2018. [2] [3]
  • 10. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. GANNoise Text-to-image [3] (and Image-to-text)[1] [2] [1] P. Isola, et al., Image-to-Image Translation with Conditional Adversarial Nets, CVPR 2017. [2] C. Ledig, et al., Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, CVPR 2017. [3] S. Reed, et al., Generative Adversarial Text to Image Synthesis, ICML 2016.
  • 11. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Saliency ( ) [1] [1] N. Liu, et al., PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection, CVPR 2018. [2] Z. Li, et al., MegaDepth: Learning Single-View Depth Prediction from Internet Photos, CVPR 2018. [2]
  • 12. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. 0 2 4 6 8 10 12 14 16 18 20 1 2 3 4 5 6 7 8 9 1011121314151617181920 ID [1] O. Vinyals, et al., Matching Networks for One Shot Learning, arXiv:1606.04080 • • [1]
  • 13. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • Deep Learning • X. Yuan, et al., Adversarial Examples: Attacks and Defenses for Deep Learning, IEEE Trans Neural Netw Learn Syst. 2019.
  • 14. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 15. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • • • ONNX AutoML Define-by-run
  • 16. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • TensorFlow models TF slim GluonCV ChainerCV PyTorchCV
  • 17. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. ResNet (Gluon vs MXNet) num_unit = len(units) assert(num_unit == num_stages) data = mx.sym.Variable(name='data') if dtype == 'float32': data = mx.sym.identity(data=data, name='id') else: if dtype == 'float16': data = mx.sym.Cast(data=data, dtype=np.float16) data = mx.sym.BatchNorm(data=data, fix_gamma=True, eps=2e-5, momentum=bn_mom, name='bn_data') (nchannel, height, width) = image_shape if height <= 32: # such as cifar10 body = mx.sym.Convolution(data=data, num_filter=filter_list[0], kernel=(3, 3), stride=(1,1), pad=(1, 1), no_bias=True, name="conv0", workspace=workspace) else: # often expected to be 224 such as imagenet body = mx.sym.Convolution(data=data, num_filter=filter_list[0], kernel=(7, 7), stride=(2,2), pad=(3, 3), no_bias=True, name="conv0", workspace=workspace) body = mx.sym.BatchNorm(data=body, fix_gamma=False, eps=2e-5, momentum=bn_mom, name='bn0') body = mx.sym.Activation(data=body, act_type='relu', name='relu0') body = mx.sym.Pooling(data=body, kernel=(3, 3), stride=(2,2), pad=(1,1), pool_type='max') for i in range(num_stages): body = residual_unit(body, filter_list[i+1], (1 if i==0 else 2, 1 if i==0 else 2), False, name='stage%d_unit%d' % (i + 1, 1), bottle_neck=bottle_neck, workspace=workspace, memonger=memonger) for j in range(units[i]-1): body = residual_unit(body, filter_list[i+1], (1,1), True, name='stage%d_unit%d' % (i + 1, j + 2), bottle_neck=bottle_neck, workspace=workspace, memonger=memonger) bn1 = mx.sym.BatchNorm(data=body, fix_gamma=False, eps=2e-5, momentum=bn_mom, name='bn1') relu1 = mx.sym.Activation(data=bn1, act_type='relu', name='relu1') MXNet from mxnet.gluon.model_zoo import vision resnet18 = vision.resnet18_v1() Gluon
  • 18. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. ONNX (Open Neural Network Exchange) MXNet Caffe2 PyTorch TF CNTKCoreML Tensor RT NGraph SNPE • ONNX ONNX •
  • 19. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. ONNX Protocol Buffers • • • API Protocol Buffers Graph Operator Tensor, … Operator Definitions ONNX Python API
  • 20. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Define-and-run Define-by-run • Define-and-run • • TensorFlow, MXNet • Define-by-run • • Chainer PyTorch, TensorFlow, MXNet
  • 21. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Define-and-run Define-by-run Define-and-run Define-by-run def our_function(A, B): C = A + B return C A = Load_Data_A() B = Load_Data_B() result = our_function(A, B) A = placeholder() B = placeholder() C = A + B our_function = compile(inputs=[A, B], outputs =[C]) A = Load_Data_A() B = Load_Data_B() result = our_function(A, B) https://gluon.mxnet.io/chapter07_distributed-learning/hybridize.html Define Run Define, Run
  • 22. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Define-by-run Define-and-run Define-by-run def our_function(A, B): C = A + B return C A = Load_Data_A() B = Load_Data_B() result = our_function(A, B) A = placeholder() B = placeholder() C = A + B our_function = compile(inputs=[A, B], outputs =[C]) A = Load_Data_A() B = Load_Data_B() result = our_function(A, B)
  • 23. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. AutoML • • , etc. D. Bayor, et al., TFX: A TensorFlow-Based Production-Scale Machine Learning Platform, KDD 2017.
  • 24. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. AutoML • AutoML • ICML 2014 AutoML * • • • Meta-Learning, Learning to learn * https://sites.google.com/site/automlwsicml14/
  • 25. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. AutoML
  • 26. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. AutoML Amazon Forecast User CSV file 1. S3 2. Forecast 3. Forecast 4.
  • 27. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 28. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • Model Server Interpretable ML
  • 29. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Model Server • • Model Server • • REST/RPC Model Server Mobile client Deploy REST/RPC
  • 30. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. TensorFlow Serving [1] C. Olston, et al., TensorFlow-Serving: Flexible, High-Performance ML Serving, NIPS 2017. • Controller, Synchronizer Serving job • Router Serving job
  • 31. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. MXNet Model Server https://aws.amazon.com/jp/blogs/news/model-server-for-apache-mxnet-v1-0-released/ • REST API • MMS 1.0 1,000 MMS 1.0 MMS 0.4
  • 32. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • • • AWS, SageMaker Neo • Nvidia, TensorRT Raspberry Pi ResNet18 Mobilenet 11.5x 2.2x
  • 33. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. SageMaker Neo / TVM • Operator Fusion • Data Layout Transformation 4x4 4x4 • Tensor Expression and Schedule Space • Nested Parallelism with Cooperation • etc… T. Chen, et al., TVM: An Automated End-to-End Optimizing Compiler for Deep Learning, OSDI 2018.
  • 34. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. TensorRT • Layer & Tensor Fusion 1 • FP16 and INT8 Precision Calibration FP32 FP16 INT8 • Kernel Auto-Tuning • Dynamic Tensor Memory • Multi Stream Execution https://devblogs.nvidia.com/tensorrt-3-faster-tensorflow-inference/
  • 35. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Interpretable ML: : SVM GBT C. Molnar, Interpretable Machine Learning, https://christophm.github.io/interpretable-ml-book/ >900< 900 < 2000 km2 > 2000 km2
  • 36. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Interpretable ML for computer vision • • M.T. Ribeiro, et al., Anchors: High-Precision Model-Agnostic Explanations, AAAI 2018.
  • 37. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 38. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • • • 1 1 • • AWS Inferentia • Intel Nervana
  • 39. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Machine Learning on FPGA • FPGA • AWS F1 instance Amazon Machine Image • Loop tiling [1] [1] C. Zhang, et al., Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks, FPGA 2015.
  • 40. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • GPU
  • 41. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 42. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 43. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. • • AutoML AI •
  • 44. © 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. https://amzn.to/aws_dev