Learn ML by building Computer Vision Application with Amazon Rekognition and SageMaker

Agenda
- Build Image Analysis System with Amazon Rekognition
- Machine Learning Basic Concepts
- Build a Visual Search Application with Amazon SageMaker
- Amazon SageMaker Studio Notebooks
- Amazon SageMaker Training Job
- Amazon SageMaker Endpoints

Transcript

1. © 2021, Amazon Web Services, Inc. or its Affiliates. Sungmin Kim Solutions Architect, AWS Computer Vision Applications을 만들면서 배우는 Machine Learning powered by Amazon Rekognition and SageMaker
2. Agenda • Amazon Rekognition • Machine Learning Basic Concepts • Amazon SageMaker • Amazon SageMaker Studio Notebooks • Amazon SageMaker Training Job • Amazon SageMaker Endpoints
3. AnyCompany Dream is
4. Which Advertisement Is Better?
5. (B) may be Better, isn’t It?
6. Why (B) is Better? Climbing sunglasses Climbing shoes How about climbing gloves?
7. How to Choose the Most Relevant Advertisement? • may be easy to find, if a image has correct tags. • If so, how to tag millions of images in fast, cost-efficient way? • Machine Learning may save your life
8. Automatic Image Tagging Automatic Image Recognition
9. Amazon SageMaker Label data Aggregate & prepare data Store & share features Auto ML Spark/R Detect bias Visualize in notebooks Pick algorithm Train models Tune parameters Debug & profile Deploy in production Manage & monitor CI/CD Human review Ground Truth Data Wrangler Feature store Autopilot Processing Clarify Studio Notebooks Built-in or Bring-your-own Experiments Spot Training Distributed Training Automatic Model Tuning Debugger Model Hosting Multi-model Endpoints Model Monitor Pipelines Augmented AI AMAZON SAGEMAKER EDGE MANAGER SAGEMAKER STUDIO IDE AMAZON SAGEMAKER JUMPSTART VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD CONTACT CENTERS Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Trainium Inferentia FPGA AI SERVICES ML SERVICES FRAMEWORKS & INFRASTRUCTURE DeepGraphLibrary Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Lex Amazon Personalize Amazon Forecast Amazon Comprehend +Medical Amazon Textract Amazon Kendra Amazon CodeGuru Amazon Fraud Detector Amazon Translate INDUSTRIAL AI CODE AND DEVOPS Amazon DevOps Guru Voice ID For Amazon Connect Contact Lens Amazon Monitron AWS Panorama + Appliance Amazon Lookout for Vision Amazon Lookout for Equipment Amazon HealthLake HEALTHCARE AI Amazon Lookout for Metrics ANOMOLY DETECTION Amazon Transcribe for Medical Amazon Comprehend for Medical 모든 개발자를 위한 다양한 인공 지능 도구 제공
10. Amazon SageMaker Label data Aggregate & prepare data Store & share features Auto ML Spark/R Detect bias Visualize in notebooks Pick algorithm Train models Tune parameters Debug & profile Deploy in production Manage & monitor CI/CD Human review Ground Truth Data Wrangler Feature store Autopilot Processing Clarify Studio Notebooks Built-in or Bring-your-own Experiments Spot Training Distributed Training Automatic Model Tuning Debugger Model Hosting Multi-model Endpoints Model Monitor Pipelines Augmented AI AMAZON SAGEMAKER EDGE MANAGER SAGEMAKER STUDIO IDE AMAZON SAGEMAKER JUMPSTART VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD CONTACT CENTERS Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Trainium Inferentia FPGA AI SERVICES ML SERVICES FRAMEWORKS & INFRASTRUCTURE DeepGraphLibrary Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Lex Amazon Personalize Amazon Forecast Amazon Comprehend +Medical Amazon Textract Amazon Kendra Amazon CodeGuru Amazon Fraud Detector Amazon Translate INDUSTRIAL AI CODE AND DEVOPS Amazon DevOps Guru Voice ID For Amazon Connect Contact Lens Amazon Monitron AWS Panorama + Appliance Amazon Lookout for Vision Amazon Lookout for Equipment Amazon HealthLake HEALTHCARE AI Amazon Lookout for Metrics ANOMOLY DETECTION Amazon Transcribe for Medical Amazon Comprehend for Medical 모든 개발자를 위한 다양한 인공 지능 도구 제공
11. Amazon Rekognition 기계 학습을 통한 이미지 및 비디오 분석 자동화
12. Amazon Rekognition Image and Video CELEBRITY RECOGNITION FACE COMPARE & SEARCH PATHING FACE DETECTION AND ANALYSIS LIVE STREAM VIDEO TEXT CONTENT MODERATION CUSTOM LABELS OBJECT, SCENE, AND ACTIVITY VIDEO SEGMENTS PPE DETECTION
13. Architecture: Automatic Image Tagging Amazon OpenSearch Service Amazon Kinesis Data Streams Amazon Rekognition Images AWS Lambda Amazon S3 bucket with images Amazon API Gateway https://github.com/aws-samples/aws-realtime-image-analysis Automatic Image Recognition
14. Demo: Automatic Image Tagging
15. AI Services 한 번에 정리하기 • Human-like • 보기(Vision) – Rekognition • 듣기 및 말하기(Speech) o Polly(Text-To-Speech) o Transcribe(Speech-To-Text) o Transcribe Medical • 읽기(Text) o Comprehend o Comprehend Medical o Textract • Common Applications • 예측 – Forecast • 추천 - Personalize • 검색 – Kendra • 채팅 – Lex • 고객 센터 – Contact Lens • 사기 탐지 – Fraud Detector • 개발자 도구 – Code Guru
16. 1 Year Later
17. Visual Search Similar results bonzai Provence lavender Cozy places Top 10 cozy apartments in Brooklyn
18. Building a Visual Search Application https://aws.amazon.com/blogs/machine-learning/building-a-visual-search-application-with- amazon-sagemaker-and-amazon-es/
19. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Basic Concepts
20. © 2020, Amazon Web Services, Inc. or its Affiliates. Marketing Offer On A New Product
21. © 2020, Amazon Web Services, Inc. or its Affiliates. Option 1- Build A Rule Engine Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Input Output Age Gender Purchase Date Items 30 M 3/1/2017 Toy …. …… ….. ….. Rule 1: 15 <age< 30 Rule 2: Bought Toy=Y, Last Purchase<30 days Rule 3: Gender = ‘M’, Bought Toy =‘Y’ Rule 4: …….. Rule 5: …….. Human Programmer
22. © 2020, Amazon Web Services, Inc. or its Affiliates. Model Output Historical Purchase Data (Training Data) Prediction Age Gender Items 35 F 39 M Toy Input - New Unseen Data Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Learning Algorithm Option 2 - Learn The Business Rules From Data
23. © 2020, Amazon Web Services, Inc. or its Affiliates. We Call This Approach Machine Learning Model Output Historical Purchase Data (Training Data) Prediction Age Gender Items 35 F 39 M Toy Input - New Unseen Data Age Gender Purchase Date Items 30 M 3/1/2017 Toy 40 M 1/3/2017 Books …. …… ….. ….. Rule 1: 15 <age< 30 Rule 2: Bought Toy=Y, Last Purchase<30 days Rule 3: Gender = ‘M’, Bought Toy =‘Y’ Rule 4: …….. Rule 5: …….. Human Programmer Learning Algorithm
24. © 2020, Amazon Web Services, Inc. or its Affiliates. What is Learning Algorithm? Input X (size of house) Output Y (price) f(x) = W*x + b xo xn 2 3 1
25. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Algorithm f(x) = W*x + b • W = ? • b = ? 모델 학습 대상 Size (X) 2104 1600 2400 1416 3000 1985 1534 1427 1380 1494 Price (y) 400 330 369 232 540 300 315 199 212 243 ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ Input X (size of house) Output Y (Price) 2 3 1 (1), (2), (3) 중 가장 적합한(fit) 것은? Dataset
26. © 2020, Amazon Web Services, Inc. or its Affiliates. Machine Learning Algorithm f(x) = W*x + b • W = ? • b = ? 모델 학습 대상 Size (X) 2104 1600 2400 1416 3000 1985 1534 1427 1380 1494 Price (y) 400 330 369 232 540 300 315 199 212 243 (1), (2), (3) 중 가장 적합한(fit) 것은? Dataset • 입력 데이터는 모두 숫자이다. • ML의 모델은 수학적 모형(수식) 이다. • ML의 결과물은 수식의 매개변수 이다.
27. © 2020, Amazon Web Services, Inc. or its Affiliates. 모델 평가 Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1 , w2 , …, wn , b} f(x) = w1 *x1 + w2 *x2 + … + wn *xn + b = W*x + b ML 알고리즘은 Numeric data로 f(x)라는 식(모델)의 매개변수(w1 , w2 , …, b)를 추정 하는 방법 ✗ ✗ ✗ ✗ ✗ ✗ ✗ ✗ Input X (size of house) Output Y (Price) 2 3 1 Q) (1), (2), (3) 중 가장 적합한(fit) 것은?
28. © 2020, Amazon Web Services, Inc. or its Affiliates. Input X (size of house) Loss Function (Objective Function) Output Y (Price) f(x) = W*x + b Error (f(Xj ) – Yj ) Loss(W, b) = ∑(f(xj ) – yj )2 1 n j=1 n xo xn Mean Square Error(MSE) Function Guessing Value Actual Value
29. © 2020, Amazon Web Services, Inc. or its Affiliates. Loss Function (Objective Function) 선형 회귀 문제 선형 회귀를 위한 목적 함수 • 𝑓! (𝐱" )는 예측함수의 출력, yi 는 예측함수가 맞추어야 하는 목표 값 • 𝑓! (𝐱" ) - yi 는 오차 = 평균제곱오차MSE(mean squared error)
30. © 2020, Amazon Web Services, Inc. or its Affiliates. Loss Function (Objective Function) 선형 회귀 문제 선형 회귀를 위한 목적 함수 • 𝑓! (𝐱" )는 예측함수의 출력, yi 는 예측함수가 맞추어야 하는 목표 값 • 𝑓! (𝐱" ) - yi 는 오차 = 평균제곱오차MSE(mean squared error) 처음에는 최적 매개변수 값을 알 수 없으므로 임의 값으로 Θ! = 𝑤! , 𝑏! 설정 à Θ" = 𝑤" , 𝑏" 로 개선 à Θ# = 𝑤#, 𝑏# 로 개선 à Θ# 는 최적해 & Θ • 이때 𝐽 Θ# > 𝐽 Θ$ > 𝐽 Θ%
31. © 2020, Amazon Web Services, Inc. or its Affiliates. Plotting Loss Function (Single Variable) W Loss (W) Minimum loss
32. © 2020, Amazon Web Services, Inc. or its Affiliates. Optimization - Minimize Loss Function W Minimum loss 현 지점의 기울기 (Partial Derivative) Loss를 낮추는 방향(Descent) WJ WJ+1 Gradient Descent Wj+1 = Wj 𝛼 Loss(Wj) ∂ ∂Wj Random initial value Loss (W) 𝛼 한 발자국 크기 (Learning Rate)
33. © 2020, Amazon Web Services, Inc. or its Affiliates. Gradient Decent: 최적화 문제 해결법 Learning Step weight의 업데이트 = 에러 낮추는 방향 x 한 발자국 크기 x 현 지점의 기울기 (decent) (learning rate) (gradient) Loss function의 현재 가중치에서 기울기(gradient)를 구해서 Loss를 줄이는 방향으로 가중치를 업데이트해 나간다 Learning Rate
34. © 2020, Amazon Web Services, Inc. or its Affiliates. Hyper Parameter Learning Rate(학습률)는 어떻게 설정 해야할까? Data Model ML Algorithm 숫자 0, 1, 2,.. 0.01, 0.02,.. 001, 010, 011, .. model {w1 , w2 , …, wn , b} f(x) = w1 *x1 + w2 *x2 + … + wn *xn + b = W*x + b Gradient Descent 알고 싶은 값 (Parameter) 모델 학습을 위해서 미리 알아야 하는 값 (Hyperparameter)
35. © 2020, Amazon Web Services, Inc. or its Affiliates. small learning rate right learning rate large learning rate Hyper Parameter Tuning (HPO) (학습이) 너무 느리다 답을 찾지 못한다
36. © 2020, Amazon Web Services, Inc. or its Affiliates. Weight 초기값, Learning Rate 등을 적절하게 선택해야한다. Gradient Descent pitfalls Weight 초기값1 Weight 초기값2
37. © 2020, Amazon Web Services, Inc. or its Affiliates. 최적화를 이용한 기계 학습의 문제 풀이 과정 f(x) = W*x + b House Price Prediction Guessing Value Actual Value Real-World Problem 최적화 Objective Function ML Model Gradient Descent
38. © 2020, Amazon Web Services, Inc. or its Affiliates. 모든 입력 데이터는 숫자(Number) Feature: 숫자로 변환된 ML 알고리즘의 입력 데이터
39. © 2020, Amazon Web Services, Inc. or its Affiliates. 학습(Training)의 최종 목표 한번도 본적이 없는 문제를 잘 푸는 것 학습 모의 평가 최종 평가
40. © 2020, Amazon Web Services, Inc. or its Affiliates. 데이터 나누기 전체 데이터 Training Test Training Validation 한번도 본적 없는 문제를 잘 풀 수 있도록 훈련 시키기 위해서 데이터를 나눈다 “훈련은 실전처럼, 실전은 훈련처럼”
41. © 2020, Amazon Web Services, Inc. or its Affiliates. Wrap-up: Machine Learning • Machine Learning ▪ 현실 문제 → 수학 모형(모델) → 모수 (Parameter, 가중치) 추정 • Feature Engineering: 입력 데이터 → 숫자 변환 (Feature), One-Hot Encoding • 수학 모형의 모수(Parameter) 추정 방법 ▪ Loss Function (Objective, Cost Function) = Error(Guessing value – Actual value) 함수 ▪ Error를 최소화 시키는 모수 (Parameter, 가중치) 찾기 ▪ Gradient Descent method (경사하강법) • Train/Validation/Test Set으로 데이터 분리 – 일반화
42. Typical Machine Learning Process Collect, prepare and label training data Choose and optimize ML algorithm Train and tune ML models Set up and manage environments for training Deploy models in production Scale and manage the production environment 1 2 3
43. Set up and track experiment Choose model Debug, compare, and evaluate experiments Monitor quality, detect drift, and retrain Share, review, and collaborate Machine Learning is iterative
44. Amazon SageMaker Label data Aggregate & prepare data Store & share features Auto ML Spark/R Detect bias Visualize in notebooks Pick algorithm Train models Tune parameters Debug & profile Deploy in production Manage & monitor CI/CD Human review Ground Truth Data Wrangler Feature store Autopilot Processing Clarify Studio Notebooks Built-in or Bring-your-own Experiments Spot Training Distributed Training Automatic Model Tuning Debugger Model Hosting Multi-model Endpoints Model Monitor Pipelines Augmented AI AMAZON SAGEMAKER EDGE MANAGER SAGEMAKER STUDIO IDE AMAZON SAGEMAKER JUMPSTART VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD CONTACT CENTERS Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Trainium Inferentia FPGA AI SERVICES ML SERVICES FRAMEWORKS & INFRASTRUCTURE DeepGraphLibrary Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Lex Amazon Personalize Amazon Forecast Amazon Comprehend +Medical Amazon Textract Amazon Kendra Amazon CodeGuru Amazon Fraud Detector Amazon Translate INDUSTRIAL AI CODE AND DEVOPS Amazon DevOps Guru Voice ID For Amazon Connect Contact Lens Amazon Monitron AWS Panorama + Appliance Amazon Lookout for Vision Amazon Lookout for Equipment Amazon HealthLake HEALTHCARE AI Amazon Lookout for Metrics ANOMOLY DETECTION Amazon Transcribe for Medical Amazon Comprehend for Medical 모든 개발자를 위한 다양한 인공 지능 도구 제공
45. Amazon SageMaker Label data Aggregate & prepare data Store & share features Auto ML Spark/R Detect bias Visualize in notebooks Pick algorithm Train models Tune parameters Debug & profile Deploy in production Manage & monitor CI/CD Human review Ground Truth Data Wrangler Feature store Autopilot Processing Clarify Studio Notebooks Built-in or Bring-your-own Experiments Spot Training Distributed Training Automatic Model Tuning Debugger Model Hosting Multi-model Endpoints Model Monitor Pipelines Augmented AI AMAZON SAGEMAKER EDGE MANAGER SAGEMAKER STUDIO IDE AMAZON SAGEMAKER JUMPSTART VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD CONTACT CENTERS Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Trainium Inferentia FPGA AI SERVICES ML SERVICES FRAMEWORKS & INFRASTRUCTURE DeepGraphLibrary Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Lex Amazon Personalize Amazon Forecast Amazon Comprehend +Medical Amazon Textract Amazon Kendra Amazon CodeGuru Amazon Fraud Detector Amazon Translate INDUSTRIAL AI CODE AND DEVOPS Amazon DevOps Guru Voice ID For Amazon Connect Contact Lens Amazon Monitron AWS Panorama + Appliance Amazon Lookout for Vision Amazon Lookout for Equipment Amazon HealthLake HEALTHCARE AI Amazon Lookout for Metrics ANOMOLY DETECTION Amazon Transcribe for Medical Amazon Comprehend for Medical 모든 개발자를 위한 다양한 인공 지능 도구 제공
46. End-to-End Machine Learning Platform Zero setup Flexible Model Training Pay by the second $ Amazon SageMaker 손쉬운 기계 학습 모델 생성, 훈련 및 서비스 배포 완전 관리 서비스
48. Amazon SageMaker Studio 기계 학습 모델 개발 및 배포를 위한 최초의 완전 통합 개발 환경 (IDE) Collaboration at scale 코드 의존성 추적 없이 확장 가능한 노트북 공유 Easy experiment management 수천 개의 모델 실험을 구성, 추적 및 비교 Automatic model generation 코드 작성 없이 데이터를 가지고 자동 모델 생성 Higher quality ML models 오류 자동 디버깅 및 실시간 오류 경보 모델 모니터링 및 고품질 유지 Increased productivity 완전 자동화된 머신 러닝 워크플로 구축
49. Amazon SageMaker Studio 기계 학습 모델 개발 및 배포를 위한 최초의 완전 통합 개발 환경 (IDE)
50. Amazon SageMaker Studio 시작 화면
51. • Jupyter notebooks • Support for Jupyter Lab • Multiple built-in kernels • Install external libraries and kernels • Integrate with Git • Sample notebooks • VPC Integration for integrated security
53. 한번의 클릭으로 노트북 공유 가능
54. Notebook Model Models bucket SageMaker Endpoint Train Amazon SageMaker End to End Training and Deployment
55. From Amazon SageMaker Notebooks training
56. Amazon SageMaker Training Specify Training Infrastructure
57. Amazon SageMaker Training Use Algorithm and Start training Execution Role SageMaker Estimator
58. Amazon SageMaker Training How does training happen XGBoost validation(optional) test(optional ECR S3 ML Instance ml.m4.xlarge xgboost linear-learner PCA DeepAR BlazingText Image classification … Object Detection Images S3 SageMaker Notebook SageMaker Training Job train Model
59. Launch container for training Job
60. Model Deployment training
61. Model artifacts Amazon SageMaker Deployment Hosting Services Inference Image Training Image Training Data Endpoint Amazon SageMaker Amazon S3 Amazon ECR
62. Model artifacts Amazon SageMaker Deployment Hosting Services Inference Image Training Image Training Data Endpoint Amazon SageMaker Amazon S3 Amazon ECR Model artifacts Inference Image
63. Amazon SageMaker Deployment SageMaker Endpoints (Private API) Auto Scaling group Availability Zone 1 Availability Zone 2 Availability Zone 3 Elastic Load Balancing Model Endpoint Client Deployment / Hosting Amazon SageMaker ML Compute Instances Input Data (Request) Prediction (Response)
64. Amazon SageMaker Deployment SageMaker Endpoints (Public API) Auto Scaling group Availability Zone 1 Availability Zone 2 Availability Zone 3 Elastic Load Balancing Model Endpoint Amazon API Gateway Client Deployment / Hosting Amazon SageMaker ML Compute Instances Input Data (Request) Prediction (Response)
65. Define Estimator Object created deploy() predict() Object created fit() Amazon SageMaker End to End Training and Deployment
66. Classification • Linear Learner • XGBoost • KNN Working with Text • BlazingText • Supervised • Unsupervised* Recommendation • Factorization Machines Forecasting • DeepAR Topic Modeling • LDA • NTM Amazon SageMaker에서 제공하는 Built-in Algorithms Sequence Translation • Seq2Seq* Clustering • KMeans Feature Reduction • PCA • Object2Vec Anomaly Detection • Random Cut Forests • IP Insights Computer Vision • Image Classification • Object Detection • Semantic Segmentation Regression • Linear Learner • XGBoost • KNN https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html
67. Model Deployment: Built-in Algorithms xgboost linear-learner PCA DeepAR BlazingText Image classification … Object Detection Built-in Algorithm Images Elastic Container Registry
68. Model Deployment: Bring Your Own Model
69. BYOM Deployment: Model Artifacts (model.tar.gz) model.tar.gz/ |- model.pth |- code/ |- inference.py |- requirements.txt model.tar.gz/ |- model | |- [model_version_number] | |- variables | |- saved_model.pb |- code |- inference.py |- requirements.txt TensorFlow (>= 1.11) PyTorch (>=1.2.0)
70. def model_fn(model_dir): # Loads a model for inference model = Your_Model() return model def input_fn(input_data, content_type): # Deserializes the input data return decoder.decode(input_data, content_type) def predict_fn(input_data, model): # Calls a model on data deseralized by input_fn return model(input_data) def output_fn(prediction, content_type): # Serializes predictions from predict_fn return encoder.encode(prediction, content_type) https://github.com/aws/sagemaker-inference-toolkit BYOM Deployment: Inference Handler Script https://github.com/tensorflow/serving def input_handler(data, context): # Pre-process request input before it is sent to TensorFlow Serving REST API if context.request_content_type == 'application/json': pass if context.request_content_type == 'text/csv': pass def output_handler(response, context): # Post-process TensorFlow Serving output before it is returned to the client response_content_type = context.accept_header prediction = response.content return prediction, response_content_type
71. A fully managed service that enables data scientists and developers to quickly and easily build machine-learning based models into production smart applications. Amazon SageMaker
72. Amazon SageMaker Studio 기계 학습 모델 개발 및 배포를 위한 최초의 완전 통합 개발 환경 (IDE) 학습 모델 구축 및 협업 SageMaker Notebooks SageMaker Pipelines 완전 자동화된 머신 러닝 워크플로 구축 학습 모델 훈련 및 검증 SageMaker Training Job One-click 배포 , 모델 모니터링 및 고품질 유지 SageMaker Endpoints 학습 모델 최적화 및 다중 알고리즘 튜닝 SageMaker HPO
73. Let’s build a Machine Learning powered Application
74. Visual Search Similar results bonzai Provence lavender Cozy places Top 10 cozy apartments in Brooklyn
75. Building a Visual Search Application https://aws.amazon.com/blogs/machine-learning/building-a-visual-search-application-with- amazon-sagemaker-and-amazon-es/
76. As-Is: Automatic Image Tagging Amazon Kinesis Data Streams Client AWS Lambda Amazon S3 bucket with images Amazon API Gateway Amazon OpenSearch Service Amazon Rekognition
77. To-Be: Visual Search Amazon Kinesis Data Streams Client AWS Lambda Amazon S3 bucket with images Amazon API Gateway Amazon OpenSearch Service
78. Visual Search Amazon Kinesis Data Streams Client AWS Lambda Amazon S3 bucket with images Amazon API Gateway Amazon SageMaker Amazon OpenSearch Service Notebook Model Models bucket SageMaker Endpoint Train
79. Demo: Visual Search Application https://tinyurl.com/53yubfzw
80. Demo: Visual Search Application https://tinyurl.com/53yubfzw
81. Demo: Visual Search Application https://tinyurl.com/53yubfzw
82. Demo: Visual Search Application https://tinyurl.com/53yubfzw
83. Your Dream Comes True
84. 문제 해결에 가장 적합한 AI 서비스 선택 문제 해결을 위한 ML 모델 개발 ML 모델 배포 및 모니터링 서비스 개발 문제 정의 AI 서비스 활용 Business Problem – ML problem framing SageMaker 활용 서비스 출시 How to choose the most relevant advertisement? How to tag millions of images in fast, cost-efficient way? How to build our own ML model? How to build Visual Search Application? Wrap-up Our Business Problem
85. AI/ML Stack을 활용한 비즈니스 문제 해결 과정 문제 해결에 가장 적합한 AI 서비스 선택 문제 해결을 위한 ML 모델 개발 ML 모델 배포 및 모니터링 서비스 개발 문제 정의 AI 서비스 활용 Business Problem – ML problem framing SageMaker 활용 서비스 출시
86. Put machine learning in the hands of every developer Our mission at
87. Amazon SageMaker Label data Aggregate & prepare data Store & share features Auto ML Spark/R Detect bias Visualize in notebooks Pick algorithm Train models Tune parameters Debug & profile Deploy in production Manage & monitor CI/CD Human review Ground Truth Data Wrangler Feature store Autopilot Processing Clarify Studio Notebooks Built-in or Bring-your-own Experiments Spot Training Distributed Training Automatic Model Tuning Debugger Model Hosting Multi-model Endpoints Model Monitor Pipelines Augmented AI AMAZON SAGEMAKER EDGE MANAGER SAGEMAKER STUDIO IDE AMAZON SAGEMAKER JUMPSTART VISION SPEECH TEXT SEARCH CHATBOTS PERSONALIZATION FORECASTING FRAUD CONTACT CENTERS Deep Learning AMIs & Containers GPUs & CPUs Elastic Inference Trainium Inferentia FPGA AI SERVICES ML SERVICES FRAMEWORKS & INFRASTRUCTURE DeepGraphLibrary Amazon Rekognition Amazon Polly Amazon Transcribe +Medical Amazon Lex Amazon Personalize Amazon Forecast Amazon Comprehend +Medical Amazon Textract Amazon Kendra Amazon CodeGuru Amazon Fraud Detector Amazon Translate INDUSTRIAL AI CODE AND DEVOPS Amazon DevOps Guru Voice ID For Amazon Connect Contact Lens Amazon Monitron AWS Panorama + Appliance Amazon Lookout for Vision Amazon Lookout for Equipment Amazon HealthLake HEALTHCARE AI Amazon Lookout for Metrics ANOMOLY DETECTION Amazon Transcribe for Medical Amazon Comprehend for Medical 모든 개발자를 위한 다양한 인공 지능 도구 제공
88. References • Image Insights - Automatic Image Tagging & Analysis System: https://tinyurl.com/kxydd2wn • Visual Image Search with Amazon SageMaker and Amazon ES: https://tinyurl.com/53yubfzw • Amazon Rekognition으로 나만의 컴퓨터 비전 모델 만들기: https://youtu.be/tioJru6b_4M • SageMaker Immersion Day Workshop ✯✯✯ : https://sagemaker-immersionday.workshop.aws/ • SageMaker Examples (100+) ✯✯✯ : https://sagemaker-examples.readthedocs.io/ • Advanced SageMaker Workshop: https://sagemaker-workshop.com/ • Amazon SageMaker 데모 (2020-03-25) ✯✯✯ : https://youtu.be/miIVGlq6OUk • How Startups Deploy Pretrained Models on Amazon SageMaker: https://tinyurl.com/4nwy9bd5 • Deploy trained Keras or TensorFlow models using Amazon SageMaker: https://tinyurl.com/nf2rwrw9 • Host multiple TensorFlow computer vision models using Amazon SageMaker multi-model endpoints: https://tinyurl.com/6w8f4862