SlideShare una empresa de Scribd logo
1 de 38
Enhanced Media Workflows Using Amazon AI
Tobias Börjeson, Solutions Architect, AWS
December 7, 2017
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Media & Entertainment Cloud
Symposium | Stockholm
Artificial Intelligence at Amazon
Thousands Of Employees Across The Company Focused on AI
Discovery &
Search
Fulfilment &
Logistics
Enhance
Existing Products
Define New
Products
Bring Machine
Learning To All
Artificial Intelligence At Amazon
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Deep Learning for Media – Glass to Glass
Playout &
Distribution
Filtering & Quality
Control
Visual Effects &
Editing
Application & Filesystem
Texture & Asset Search
Analytics
Sentiment Analysis
Other Amazon AI
Services
(Lex, Polly)
DAM & Archive
Auto-categorization
Metadata Augmentation
Digital Supply
Chain
Tag on Ingest
Live and VOD Feature
Extraction
Celebrity Detection
Publishing
Value Add
API-based services
OTT
Filtering &
Quality Control
Acquisition
Pre-
processing &
optimization
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
So where should we start?
© NVIDIA
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
The 10,000ft Intro to Deep Learning
Raw Data Low Level Features Mid Level Features High Level Features
Result
Application
Components
Task
Identify a Face
Training
10-100M images
Network
~ 10 layers
1B parameters
Learning
~ 30 Exaflops
~ 30 GPU days
© 2016 NVIDIA
Input
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Confidence Labels
99.2%
Animal
Dog
Chihuahua
98.6%
Food
Dessert
Muffin
97.9% Collage
Dog or Muffin?
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
The Amazon AI Stack
Services
Platforms
Frameworks
Infrastructure
MXNet TorchCTKKerasGluonCaffe
TensorFlo
w
AWS Deep Learning AMI
Amazon
Sagemaker
Mechanical
Turk
AWS
DeepLens
Amazon ML Spark & EMR
Vision
Rekognition
Speech
Polly, Transcribe
Language
Lex, Translate, Comprehend
GPU / FPGA ServerlessCPU IoT Mobile
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Frameworks & Infrastructure
Services
Platforms
Frameworks
Infrastructure
MXNet TorchCTKKerasGluonCaffe
TensorFlo
w
AWS Deep Learning AMI
Amazon
Sagemaker
Mechanical
Turk
AWS
DeepLens
Amazon ML Spark & EMR
Vision Speech Language
GPU / FPGA ServerlessCPU IoT Mobile
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Deep Learning Compute
AWS Deep Learning AMI
MXNet
Torch
CTKKeras
TheanoCaffe
TensorFlow
Amazon EC2
AnacondaIntel MKL
CUDA+cuDNN Python 2+3
Caffe2
• One Click launch
• Machine Image or Stack-based
• Single node or distributed
• GPU, CPU (& FPGA)
• NVIDIA & Intel acceleration
• Anaconda Data Science Platform
• Python w/ AI/ML/DL libraries
Media-Centric Models & Datasets
CelebAPlaces CIFAR-10/100
Object, Network & Gateway
Storage Services
Frameworks, 3rd Party Enablement, & Industry Initiatives
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Choosing the right Instance Type for AI
Instance
Name
GPU
Count
vCPU
Count
Memory Network EBS
p3.xlarge 1 8 61 GiB ~10Gbps 1.5 Gbps
p3.8xlarge 4 32 244 GiB 10Gbps 7Gbps
p3.16xlarge 8 64 488 GiB 25Gbps 14Gbps
P2 & P3: Distributed Training &
Inference
Hyper-scale performance on NVIDIA V100s
G3: Multi-User Modeling
NVIDIA M60 GPUs, 16,384 cores
F1: High Speed Inference
Xilinx Ulstrascale Plus, 6,800 engines
X1: Specialized AI/ML/DL
128 vCPUs, 3,904 GiB RAM
P3 Instances Provide up to 1 Petaflop of mixed precision performance,
and 125 Teraflops of single precision floating point
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Why is this Important?
Amazon EC2 Compute & EBS block storage supports second-level billing.
Combined with EC2 SPOT Fleet, this provides a up to ~90% cost savings over on-demand.
Artificial Artificial Intelligence
Ground Truth Generation & Niche
Image Categorization at scale is time
consuming & untenable
• Crowdworking to the rescue
• Deep Learning for Unlabeled Data
• Amazon Mechanical Turk – build
machine learning datasets using HITs
(human intelligence tasks), Requesters &
Workers
• Human Inference can be as high as 100s
of HITs/min (2/s @ ~200ms)
Price Task Images Labels Time
Worker
s
$0.01
Label at least
one object in
the image
237 678 13.5 37
- ~50,000 AMT Workers
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Building A Deep Learning Pipeline in the Cloud
Training
Version Controlled
Datasets
Amazon
S3
Amazon
API Gateway
Amazon
EC2
Amazon
S3
AWS Lambda
Amazon
EFS
AWS
Batch
Amazon
ECS
Amazon
Glacier
AWS
Snowball
Data
Scientist
Amazon
Mechanical Turk
Amazon SageMaker
B u i l d , Tr a i n , a n d D e p l o y M a c h i n e L e a r n i n g M o d e l s a t S c a l e
• Zero setup with Managed Notebooks
• Built-in, High Performance Algorithms
• One-click Training
• Automatic Model Tuning
• Reduced model training time
• One-Click Deployment
• Pay by the second
One-click
training
Automatic, built-
in model tuning
Highly-
optimized ML
algorithms
Deployment
without
engineering
effort
Fully-managed
hosting at scale
Build
Managed
notebook
instancesDeploy
Train
Can Amazon Rekognition add value to my content?
‘What about using the same process to enhance my Media Workflows?’
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Ingest Store Analyze Deliver
PETABYTES OF IMAGES
AND VIDEO ASSETS
CENTRALIZED STORAGE
& GLOBAL REGISTRY
METADATA ENRICHMENT
THROUGH DEEP LEARNING
ENHANCED VALUE
AND SEARCH EXPERIENCE
Media Workflow Enrichment with Rekognition
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
FEEDBACK
LOOP
Amazon Rekognition Image
Deep learning-based image recognition service
Search, verify, and organize millions of images
Object & Scene
Detection
Facial
Analysis
Face
Comparison
Facial
Recognition
Celebrity
Recognition
Image
Moderation
Text
Detection
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Rekognition Video
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Workflow Considerations
Content
VOD, LIVE &
IMAGE-BASED
Processing
COMPLEXITY &
TENANCY
Quality
MEZZANINE
vs. UGC
Integration
AWS, INTERNAL
& PARTNER
FILE
FORMATS
STREAMING
PROTOCOLS
STORAGE
& NETWORK
IO
PROCESSING
VELOCITY
SIDECAR
DATA
CMS,
MAM & DAM
CONFORMANCE
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Maple
Villa
Bushes
Grass
Tree
House
Window
Sky
Mountain Range
Forest
Clouds
Object and scene detection makes it easy for you to add features
that search, filter, and curate large libraries.
Identify objects and scenes and provide confidence scores
DetectLabelsObject & Scene Detection
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Demographic Data
Facial Landmarks
Sentiment Expressed
Image Quality
Brightness: 23.6
Sharpness: 99.9
General Attributes
Facial Analysis DetectFaces
Analyze facial characteristics in multiple dimensions
Smiling
99.1%
Female
100%
Mouth Closed
99.5%
Age Range
26 – 43 years old
Crowd Mode
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Celebrity Recognition & Image Moderation
Detect explicit and suggestive contentRecognize thousands of famous individuals
RekognizeCelebrities
DetectModerationLabel
s
Safe
Appropriate
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
{
"FaceMatches": [
{"Face": {"BoundingB
"Height":
0.2683333456516266,
"Left":
0.5099999904632568,
"Top":
0.1783333271741867,
"Width":
0.17888888716697693},
"
{
"FaceMatches": [
{"Face": {"BoundingB
"Height":
0.2683333456516266,
"Left":
0.5099999904632568,
"Top":
0.1783333271741867,
"Width":
0.17888888716697693},
"
Rekognition APIs – Overview
CompareFaces
DetectFaces
DetectLabels
DetectModerationLabels
GetCelebrityInfo
RecognizeCelebrities
Non-storage API Operations
CreateCollection
DeleteCollection
DeleteFaces
IndexFaces
ListCollections
SearchFaces
SearchFacesByImage
Storage-based API Operations
ListFaces
Detect-Text
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Deterministic Response Time
~500ms Object & Scene Detection
<500ms Search for 1mil Face Collection
moderation level = safe
Building Rich Metadata Indexes using Rekognition
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Name: You?
Complementary Services Decoupling
Amazon
SQS
Amazon
SNS
Amazon
KinesisProcessing
Amazon API
Gateway
AWS Batch
Amazon
EC2 Amazon
ECS
Compute
Applications
AWS
Lambda
Storage
Amazon
EFSAmazon
S3
Persistence
Amazon
DynamoDB
Amazon
ElasticSearch
AWS
Elemental
MediaConvert AWS
Elemental
MediaLive
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
ASSET INGEST AMAZON S3 AWS LAMBDA
CLIENT APP AMAZON ELASTICSEARCH
AMAZON REKOGNITION
Mobile app uploads
the image to S3
A Lambda function is triggered
and calls Rekognition
Rekognition retrieves the image from S3 and
returns labels for the property and amenities
Other users can search properties by
landmarks, category, etc.
MEDIA ASSET
MANAGEMENT
S3TA or 3rd Party Asset
Ingest
Event-Based Processing
Via S3 Notifications
Lambda Triggers Rekognition
asynchronously
Return Object, Scene & Face
Data for Video
Inject Asset Tags via REST API
Into specific fields
Searchable Tags stored as bag of
words collections
Authenticated Users can
Search Assets via Custom/Web App
Metadata Enrichment using Amazon Rekognition
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Amazon Rekognition media use cases
• Automated metadata. Classification of videos and still images – objects,
scenes, activity, sentiment, demographics
• Real time demographic & sentiment tracking. Touchless capture of
audience demos and reactions to displayed content, synchronized to
timeline
• Dynamic display enrichment. OTT users seamlessly access details of
actors appearing on screen in real-time
• Content moderation. Identify suggestive and explicit content to improve
alignment with rating standards
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
• Built in 3 weeks
• Indexed against 99,000 people
• Index created in one day
• Saved ~9,000 hours a year in manual
curation costs
• Live video with frame sampling
Automating footage tagging with Amazon
Rekognition
Previously, only about half of all footage was indexed due to the
immense time requirements required by manual processes
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Solution Architecture
EncodersStills Extraction &
Feeds
Results
Cache
Bucket
R3
Amazon
Rekognition
Users
Stills
Frames
SQS
Trigger
1
2
3
4
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Key Takeaways
• AI-based technology provides unique opportunities to enhance
existing media delivery services
• Running Deep Learning Infrastructure is hard
• Managed services can be used to eliminate ‘undifferentiated
heavy lifting’, allowing for niche AI focus
• AI for media is a cross-functional tech undertaking
• Don’t overcomplicate the pipeline & infrastructure
• Many traditional ‘in the cloud’ paradigms map to deep learning
• When you have to, utilize compute diversification across GPU,
CPU & FPGA, combined with Object Storage & Fractional
Billing
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Thank You!

Más contenido relacionado

La actualidad más candente

GPSTEC326-GPS Industry 4.0 AI and the Future of Manufacturing
GPSTEC326-GPS Industry 4.0 AI and the Future of ManufacturingGPSTEC326-GPS Industry 4.0 AI and the Future of Manufacturing
GPSTEC326-GPS Industry 4.0 AI and the Future of ManufacturingAmazon Web Services
 
AWS Initiate Day Manchester 2019 – AWS Cost Optimisation
AWS Initiate Day Manchester 2019 – AWS Cost OptimisationAWS Initiate Day Manchester 2019 – AWS Cost Optimisation
AWS Initiate Day Manchester 2019 – AWS Cost OptimisationAmazon Web Services
 
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...Amazon Web Services
 
Build your case for the cloud and engage your business stakeholders
Build your case for the cloud and engage your business stakeholdersBuild your case for the cloud and engage your business stakeholders
Build your case for the cloud and engage your business stakeholdersAmazon Web Services
 
WIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS ServicesWIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS ServicesAmazon Web Services
 
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...Amazon Web Services
 
CON203_Driving Innovation with Containers
CON203_Driving Innovation with ContainersCON203_Driving Innovation with Containers
CON203_Driving Innovation with ContainersAmazon Web Services
 
SRV307_Operating Your Serverless API at Scale
SRV307_Operating Your Serverless API at ScaleSRV307_Operating Your Serverless API at Scale
SRV307_Operating Your Serverless API at ScaleAmazon Web Services
 
Building Chatbots with Amazon Lex
Building Chatbots with Amazon LexBuilding Chatbots with Amazon Lex
Building Chatbots with Amazon LexAmazon Web Services
 
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUs
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUsCMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUs
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUsAmazon Web Services
 
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...Amazon Web Services
 
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...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
 
DEV337_Deploy a Data Lake with AWS CloudFormation
DEV337_Deploy a Data Lake with AWS CloudFormationDEV337_Deploy a Data Lake with AWS CloudFormation
DEV337_Deploy a Data Lake with AWS CloudFormationAmazon Web Services
 
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...Amazon Web Services
 
GPSTEC305-Machine Learning in Capital Markets
GPSTEC305-Machine Learning in Capital MarketsGPSTEC305-Machine Learning in Capital Markets
GPSTEC305-Machine Learning in Capital MarketsAmazon Web Services
 
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...Amazon Web Services
 
MBL306_Mobile State of the Union
MBL306_Mobile State of the UnionMBL306_Mobile State of the Union
MBL306_Mobile State of the UnionAmazon Web Services
 
Comparing Compute Options for Microservices - AWS Summti Sydney 2018
Comparing Compute Options for Microservices - AWS Summti Sydney 2018Comparing Compute Options for Microservices - AWS Summti Sydney 2018
Comparing Compute Options for Microservices - AWS Summti Sydney 2018Amazon Web Services
 

La actualidad más candente (20)

GPSTEC326-GPS Industry 4.0 AI and the Future of Manufacturing
GPSTEC326-GPS Industry 4.0 AI and the Future of ManufacturingGPSTEC326-GPS Industry 4.0 AI and the Future of Manufacturing
GPSTEC326-GPS Industry 4.0 AI and the Future of Manufacturing
 
AWS Initiate Day Manchester 2019 – AWS Cost Optimisation
AWS Initiate Day Manchester 2019 – AWS Cost OptimisationAWS Initiate Day Manchester 2019 – AWS Cost Optimisation
AWS Initiate Day Manchester 2019 – AWS Cost Optimisation
 
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...
MSC202_Learn How Salesforce Used ADCs for App Load Balancing for an Internati...
 
Introducing Amazon EKS
Introducing Amazon EKSIntroducing Amazon EKS
Introducing Amazon EKS
 
Build your case for the cloud and engage your business stakeholders
Build your case for the cloud and engage your business stakeholdersBuild your case for the cloud and engage your business stakeholders
Build your case for the cloud and engage your business stakeholders
 
WIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS ServicesWIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS Services
 
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...
GPSTEC319-Build Once Deploy Many Architecting and Building Automated Reusable...
 
CON203_Driving Innovation with Containers
CON203_Driving Innovation with ContainersCON203_Driving Innovation with Containers
CON203_Driving Innovation with Containers
 
SRV307_Operating Your Serverless API at Scale
SRV307_Operating Your Serverless API at ScaleSRV307_Operating Your Serverless API at Scale
SRV307_Operating Your Serverless API at Scale
 
Building Chatbots with Amazon Lex
Building Chatbots with Amazon LexBuilding Chatbots with Amazon Lex
Building Chatbots with Amazon Lex
 
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUs
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUsCMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUs
CMP208_Unleash Your Graphics Solutions with the Flexibility of Elastic GPUs
 
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...
HLC302_Adopting Microservices in Healthcare Building a Compliant DevOps Pipel...
 
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...
Zero to Lightspeed: Building production apps easily with Amazon Lightsail - C...
 
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 - ...
 
DEV337_Deploy a Data Lake with AWS CloudFormation
DEV337_Deploy a Data Lake with AWS CloudFormationDEV337_Deploy a Data Lake with AWS CloudFormation
DEV337_Deploy a Data Lake with AWS CloudFormation
 
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...
GPSTEC322-GPS Creating Your Virtual Data Center VPC Fundamentals Connectivity...
 
GPSTEC305-Machine Learning in Capital Markets
GPSTEC305-Machine Learning in Capital MarketsGPSTEC305-Machine Learning in Capital Markets
GPSTEC305-Machine Learning in Capital Markets
 
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...
DEV328_DevOps Lessons from Courser a Site Performance, Reliability, and Devel...
 
MBL306_Mobile State of the Union
MBL306_Mobile State of the UnionMBL306_Mobile State of the Union
MBL306_Mobile State of the Union
 
Comparing Compute Options for Microservices - AWS Summti Sydney 2018
Comparing Compute Options for Microservices - AWS Summti Sydney 2018Comparing Compute Options for Microservices - AWS Summti Sydney 2018
Comparing Compute Options for Microservices - AWS Summti Sydney 2018
 

Similar a Enhanced Media Workflows Using Amazon AI

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
 
Artificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartArtificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartVladimir Simek
 
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
 
Artificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartArtificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartVladimir Simek
 
AI / ML Services - re:Invent Comes to London 2.0
AI / ML Services - re:Invent Comes to London 2.0AI / ML Services - re:Invent Comes to London 2.0
AI / ML Services - re:Invent Comes to London 2.0Amazon Web Services
 
Integrating Deep Learning Into Your Enterprise
Integrating Deep Learning Into Your EnterpriseIntegrating Deep Learning Into Your Enterprise
Integrating Deep Learning Into Your EnterpriseAmazon Web Services
 
Building Your Smart Applications with Amazon AI.pdf
Building Your Smart Applications with Amazon AI.pdfBuilding Your Smart Applications with Amazon AI.pdf
Building Your Smart Applications with Amazon AI.pdfAmazon Web Services
 
Supercharge your Machine Learning Solutions with Amazon SageMaker
Supercharge your Machine Learning Solutions with Amazon SageMakerSupercharge your Machine Learning Solutions with Amazon SageMaker
Supercharge your Machine Learning Solutions with Amazon SageMakerAmazon Web Services
 
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und Experten
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und ExpertenMaschinelles Lernen auf AWS für Entwickler, Data Scientists und Experten
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und ExpertenAWS Germany
 
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Amazon Web Services
 
Integrating Deep Learning In the Enterprise
Integrating Deep Learning In the EnterpriseIntegrating Deep Learning In the Enterprise
Integrating Deep Learning In the EnterpriseAmazon 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
 
MCL314_Unlocking Media Workflows Using Amazon Rekognition
MCL314_Unlocking Media Workflows Using Amazon RekognitionMCL314_Unlocking Media Workflows Using Amazon Rekognition
MCL314_Unlocking Media Workflows Using Amazon RekognitionAmazon Web Services
 
Integrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseIntegrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseAmazon Web Services
 
Integrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseIntegrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseAmazon Web Services
 
AWS Machine Learning Week SF: Integrating Deep Learning into Your Enterprise
AWS Machine Learning Week SF: Integrating Deep Learning into Your EnterpriseAWS Machine Learning Week SF: Integrating Deep Learning into Your Enterprise
AWS Machine Learning Week SF: Integrating Deep Learning into Your EnterpriseAmazon Web Services
 
New AI/ML services at AWS re:Invent 2017
New AI/ML services at AWS re:Invent 2017New AI/ML services at AWS re:Invent 2017
New AI/ML services at AWS re:Invent 2017Julien SIMON
 
Devoxx: Building AI-powered applications on AWS
Devoxx: Building AI-powered applications on AWSDevoxx: Building AI-powered applications on AWS
Devoxx: Building AI-powered applications on AWSAdrian Hornsby
 
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...Amazon Web Services
 
Supercharge Your Machine Learning Solutions with Amazon SageMaker
Supercharge Your Machine Learning Solutions with Amazon SageMakerSupercharge Your Machine Learning Solutions with Amazon SageMaker
Supercharge Your Machine Learning Solutions with Amazon SageMakerAmazon Web Services
 

Similar a Enhanced Media Workflows Using Amazon AI (20)

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...
 
Artificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartArtificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to Start
 
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
 
Artificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to StartArtificial Intelligence (Machine Learning) on AWS: How to Start
Artificial Intelligence (Machine Learning) on AWS: How to Start
 
AI / ML Services - re:Invent Comes to London 2.0
AI / ML Services - re:Invent Comes to London 2.0AI / ML Services - re:Invent Comes to London 2.0
AI / ML Services - re:Invent Comes to London 2.0
 
Integrating Deep Learning Into Your Enterprise
Integrating Deep Learning Into Your EnterpriseIntegrating Deep Learning Into Your Enterprise
Integrating Deep Learning Into Your Enterprise
 
Building Your Smart Applications with Amazon AI.pdf
Building Your Smart Applications with Amazon AI.pdfBuilding Your Smart Applications with Amazon AI.pdf
Building Your Smart Applications with Amazon AI.pdf
 
Supercharge your Machine Learning Solutions with Amazon SageMaker
Supercharge your Machine Learning Solutions with Amazon SageMakerSupercharge your Machine Learning Solutions with Amazon SageMaker
Supercharge your Machine Learning Solutions with Amazon SageMaker
 
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und Experten
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und ExpertenMaschinelles Lernen auf AWS für Entwickler, Data Scientists und Experten
Maschinelles Lernen auf AWS für Entwickler, Data Scientists und Experten
 
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
 
Integrating Deep Learning In the Enterprise
Integrating Deep Learning In the EnterpriseIntegrating Deep Learning In the Enterprise
Integrating Deep Learning In the Enterprise
 
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
 
MCL314_Unlocking Media Workflows Using Amazon Rekognition
MCL314_Unlocking Media Workflows Using Amazon RekognitionMCL314_Unlocking Media Workflows Using Amazon Rekognition
MCL314_Unlocking Media Workflows Using Amazon Rekognition
 
Integrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseIntegrating Deep Learning into your Enterprise
Integrating Deep Learning into your Enterprise
 
Integrating Deep Learning into your Enterprise
Integrating Deep Learning into your EnterpriseIntegrating Deep Learning into your Enterprise
Integrating Deep Learning into your Enterprise
 
AWS Machine Learning Week SF: Integrating Deep Learning into Your Enterprise
AWS Machine Learning Week SF: Integrating Deep Learning into Your EnterpriseAWS Machine Learning Week SF: Integrating Deep Learning into Your Enterprise
AWS Machine Learning Week SF: Integrating Deep Learning into Your Enterprise
 
New AI/ML services at AWS re:Invent 2017
New AI/ML services at AWS re:Invent 2017New AI/ML services at AWS re:Invent 2017
New AI/ML services at AWS re:Invent 2017
 
Devoxx: Building AI-powered applications on AWS
Devoxx: Building AI-powered applications on AWSDevoxx: Building AI-powered applications on AWS
Devoxx: Building AI-powered applications on AWS
 
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...
AWS Machine Learning Week SF: Build an Image-Based Automatic Alert System wit...
 
Supercharge Your Machine Learning Solutions with Amazon SageMaker
Supercharge Your Machine Learning Solutions with Amazon SageMakerSupercharge Your Machine Learning Solutions with Amazon SageMaker
Supercharge Your Machine Learning Solutions with Amazon SageMaker
 

Más de Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsAmazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareAmazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSAmazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAmazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareAmazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon Web Services
 

Más de Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Enhanced Media Workflows Using Amazon AI

  • 1. Enhanced Media Workflows Using Amazon AI Tobias Börjeson, Solutions Architect, AWS December 7, 2017 © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Media & Entertainment Cloud Symposium | Stockholm
  • 3.
  • 4.
  • 5.
  • 6. Thousands Of Employees Across The Company Focused on AI Discovery & Search Fulfilment & Logistics Enhance Existing Products Define New Products Bring Machine Learning To All Artificial Intelligence At Amazon © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 7. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 8. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Deep Learning for Media – Glass to Glass Playout & Distribution Filtering & Quality Control Visual Effects & Editing Application & Filesystem Texture & Asset Search Analytics Sentiment Analysis Other Amazon AI Services (Lex, Polly) DAM & Archive Auto-categorization Metadata Augmentation Digital Supply Chain Tag on Ingest Live and VOD Feature Extraction Celebrity Detection Publishing Value Add API-based services OTT Filtering & Quality Control Acquisition Pre- processing & optimization
  • 9. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. So where should we start?
  • 10. © NVIDIA © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. The 10,000ft Intro to Deep Learning Raw Data Low Level Features Mid Level Features High Level Features Result Application Components Task Identify a Face Training 10-100M images Network ~ 10 layers 1B parameters Learning ~ 30 Exaflops ~ 30 GPU days © 2016 NVIDIA Input
  • 11. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Confidence Labels 99.2% Animal Dog Chihuahua 98.6% Food Dessert Muffin 97.9% Collage Dog or Muffin?
  • 12. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. The Amazon AI Stack Services Platforms Frameworks Infrastructure MXNet TorchCTKKerasGluonCaffe TensorFlo w AWS Deep Learning AMI Amazon Sagemaker Mechanical Turk AWS DeepLens Amazon ML Spark & EMR Vision Rekognition Speech Polly, Transcribe Language Lex, Translate, Comprehend GPU / FPGA ServerlessCPU IoT Mobile
  • 13. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Frameworks & Infrastructure Services Platforms Frameworks Infrastructure MXNet TorchCTKKerasGluonCaffe TensorFlo w AWS Deep Learning AMI Amazon Sagemaker Mechanical Turk AWS DeepLens Amazon ML Spark & EMR Vision Speech Language GPU / FPGA ServerlessCPU IoT Mobile
  • 14. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Deep Learning Compute AWS Deep Learning AMI MXNet Torch CTKKeras TheanoCaffe TensorFlow Amazon EC2 AnacondaIntel MKL CUDA+cuDNN Python 2+3 Caffe2 • One Click launch • Machine Image or Stack-based • Single node or distributed • GPU, CPU (& FPGA) • NVIDIA & Intel acceleration • Anaconda Data Science Platform • Python w/ AI/ML/DL libraries
  • 15. Media-Centric Models & Datasets CelebAPlaces CIFAR-10/100 Object, Network & Gateway Storage Services Frameworks, 3rd Party Enablement, & Industry Initiatives © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 16. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Choosing the right Instance Type for AI Instance Name GPU Count vCPU Count Memory Network EBS p3.xlarge 1 8 61 GiB ~10Gbps 1.5 Gbps p3.8xlarge 4 32 244 GiB 10Gbps 7Gbps p3.16xlarge 8 64 488 GiB 25Gbps 14Gbps P2 & P3: Distributed Training & Inference Hyper-scale performance on NVIDIA V100s G3: Multi-User Modeling NVIDIA M60 GPUs, 16,384 cores F1: High Speed Inference Xilinx Ulstrascale Plus, 6,800 engines X1: Specialized AI/ML/DL 128 vCPUs, 3,904 GiB RAM P3 Instances Provide up to 1 Petaflop of mixed precision performance, and 125 Teraflops of single precision floating point
  • 17. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Why is this Important? Amazon EC2 Compute & EBS block storage supports second-level billing. Combined with EC2 SPOT Fleet, this provides a up to ~90% cost savings over on-demand.
  • 18. Artificial Artificial Intelligence Ground Truth Generation & Niche Image Categorization at scale is time consuming & untenable • Crowdworking to the rescue • Deep Learning for Unlabeled Data • Amazon Mechanical Turk – build machine learning datasets using HITs (human intelligence tasks), Requesters & Workers • Human Inference can be as high as 100s of HITs/min (2/s @ ~200ms) Price Task Images Labels Time Worker s $0.01 Label at least one object in the image 237 678 13.5 37 - ~50,000 AMT Workers © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 19. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Building A Deep Learning Pipeline in the Cloud Training Version Controlled Datasets Amazon S3 Amazon API Gateway Amazon EC2 Amazon S3 AWS Lambda Amazon EFS AWS Batch Amazon ECS Amazon Glacier AWS Snowball Data Scientist Amazon Mechanical Turk
  • 20. Amazon SageMaker B u i l d , Tr a i n , a n d D e p l o y M a c h i n e L e a r n i n g M o d e l s a t S c a l e • Zero setup with Managed Notebooks • Built-in, High Performance Algorithms • One-click Training • Automatic Model Tuning • Reduced model training time • One-Click Deployment • Pay by the second One-click training Automatic, built- in model tuning Highly- optimized ML algorithms Deployment without engineering effort Fully-managed hosting at scale Build Managed notebook instancesDeploy Train
  • 21. Can Amazon Rekognition add value to my content? ‘What about using the same process to enhance my Media Workflows?’ © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 22. Ingest Store Analyze Deliver PETABYTES OF IMAGES AND VIDEO ASSETS CENTRALIZED STORAGE & GLOBAL REGISTRY METADATA ENRICHMENT THROUGH DEEP LEARNING ENHANCED VALUE AND SEARCH EXPERIENCE Media Workflow Enrichment with Rekognition © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. FEEDBACK LOOP
  • 23. Amazon Rekognition Image Deep learning-based image recognition service Search, verify, and organize millions of images Object & Scene Detection Facial Analysis Face Comparison Facial Recognition Celebrity Recognition Image Moderation Text Detection © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 24. Amazon Rekognition Video © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 25. Workflow Considerations Content VOD, LIVE & IMAGE-BASED Processing COMPLEXITY & TENANCY Quality MEZZANINE vs. UGC Integration AWS, INTERNAL & PARTNER FILE FORMATS STREAMING PROTOCOLS STORAGE & NETWORK IO PROCESSING VELOCITY SIDECAR DATA CMS, MAM & DAM CONFORMANCE © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 26. Maple Villa Bushes Grass Tree House Window Sky Mountain Range Forest Clouds Object and scene detection makes it easy for you to add features that search, filter, and curate large libraries. Identify objects and scenes and provide confidence scores DetectLabelsObject & Scene Detection © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 27. Demographic Data Facial Landmarks Sentiment Expressed Image Quality Brightness: 23.6 Sharpness: 99.9 General Attributes Facial Analysis DetectFaces Analyze facial characteristics in multiple dimensions Smiling 99.1% Female 100% Mouth Closed 99.5% Age Range 26 – 43 years old Crowd Mode © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 28. Celebrity Recognition & Image Moderation Detect explicit and suggestive contentRecognize thousands of famous individuals RekognizeCelebrities DetectModerationLabel s Safe Appropriate © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 29. { "FaceMatches": [ {"Face": {"BoundingB "Height": 0.2683333456516266, "Left": 0.5099999904632568, "Top": 0.1783333271741867, "Width": 0.17888888716697693}, " { "FaceMatches": [ {"Face": {"BoundingB "Height": 0.2683333456516266, "Left": 0.5099999904632568, "Top": 0.1783333271741867, "Width": 0.17888888716697693}, " Rekognition APIs – Overview CompareFaces DetectFaces DetectLabels DetectModerationLabels GetCelebrityInfo RecognizeCelebrities Non-storage API Operations CreateCollection DeleteCollection DeleteFaces IndexFaces ListCollections SearchFaces SearchFacesByImage Storage-based API Operations ListFaces Detect-Text © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 30. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Deterministic Response Time ~500ms Object & Scene Detection <500ms Search for 1mil Face Collection
  • 31. moderation level = safe Building Rich Metadata Indexes using Rekognition © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Name: You?
  • 32. Complementary Services Decoupling Amazon SQS Amazon SNS Amazon KinesisProcessing Amazon API Gateway AWS Batch Amazon EC2 Amazon ECS Compute Applications AWS Lambda Storage Amazon EFSAmazon S3 Persistence Amazon DynamoDB Amazon ElasticSearch AWS Elemental MediaConvert AWS Elemental MediaLive © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 33. ASSET INGEST AMAZON S3 AWS LAMBDA CLIENT APP AMAZON ELASTICSEARCH AMAZON REKOGNITION Mobile app uploads the image to S3 A Lambda function is triggered and calls Rekognition Rekognition retrieves the image from S3 and returns labels for the property and amenities Other users can search properties by landmarks, category, etc. MEDIA ASSET MANAGEMENT S3TA or 3rd Party Asset Ingest Event-Based Processing Via S3 Notifications Lambda Triggers Rekognition asynchronously Return Object, Scene & Face Data for Video Inject Asset Tags via REST API Into specific fields Searchable Tags stored as bag of words collections Authenticated Users can Search Assets via Custom/Web App Metadata Enrichment using Amazon Rekognition © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 34. Amazon Rekognition media use cases • Automated metadata. Classification of videos and still images – objects, scenes, activity, sentiment, demographics • Real time demographic & sentiment tracking. Touchless capture of audience demos and reactions to displayed content, synchronized to timeline • Dynamic display enrichment. OTT users seamlessly access details of actors appearing on screen in real-time • Content moderation. Identify suggestive and explicit content to improve alignment with rating standards © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 35. • Built in 3 weeks • Indexed against 99,000 people • Index created in one day • Saved ~9,000 hours a year in manual curation costs • Live video with frame sampling Automating footage tagging with Amazon Rekognition Previously, only about half of all footage was indexed due to the immense time requirements required by manual processes © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
  • 36. Solution Architecture EncodersStills Extraction & Feeds Results Cache Bucket R3 Amazon Rekognition Users Stills Frames SQS Trigger 1 2 3 4
  • 37. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Key Takeaways • AI-based technology provides unique opportunities to enhance existing media delivery services • Running Deep Learning Infrastructure is hard • Managed services can be used to eliminate ‘undifferentiated heavy lifting’, allowing for niche AI focus • AI for media is a cross-functional tech undertaking • Don’t overcomplicate the pipeline & infrastructure • Many traditional ‘in the cloud’ paradigms map to deep learning • When you have to, utilize compute diversification across GPU, CPU & FPGA, combined with Object Storage & Fractional Billing
  • 38. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Thank You!