SlideShare ist ein Scribd-Unternehmen logo
1 von 43
Downloaden Sie, um offline zu lesen
Curating Online Content with
Google ML APIs
Andres L. Martinez a.k.a almo
Google Developer Relations Manager
@davilagrau
Resources
Twitter: @davilagrau
GitHub: https://github.com/almo
Linkedin:
https://www.linkedin.com/in/aleonar
Unstructured data accounts for
90% of enterprise data*
Cloud Machine Learning APIs
help you make sense of it
*Source: IDC
The Machine Learning Spectrum
TensorFlow Cloud Machine Learning Machine Learning APIs
BYOML skills
(Friendly Machine Learning)
Pre-packaged ML
Voice Kit
Confidential & ProprietaryGoogle Cloud Platform 8
So…. Why APIs?
{ Google Cloud Platform }
1. We want to offer businesses the tools to differentiate by offering a powerful set of APIs
that enable apps to see, hear and understand the world
2. Reduce your Time to Market (TMM) when launching your next-generation app
3. Provide you easy access to machine learning technology to give any developer the
freedom to work in the language and tools they want
4. Provide virtually limitless scalability to your application without needing to manage
back-end servers running deep learning
Pre-Trained Machine Learning Models
Fully trained ML models from Google Cloud that allow a general developer to
take advantage of rich machine learning capabilities with simple REST based
services.
Introducing
Cloud Natural Language API
Sentiment analysis and entity
recognition for text
Confidential & ProprietaryGoogle Cloud Platform 11
Features
Extract sentence, identify parts of
speech and create dependency parse
trees for each sentence
Identify entities and label by types such
as person, organization, location, events,
products and media
Understand the overall sentiment of a
block of text
Access via REST API. Text can be
uploaded in the request or integrated
with Google Cloud Storage
Syntax Analysis Entity Recognition
Sentiment Analysis Integrated REST API
Cloud Vision API
Insight from images with our powerful
Cloud Vision API
Confidential & ProprietaryGoogle Cloud Platform 13
Faces: Faces, facial landmarks,
emotions
OCR: Read and extract text, with
support for > 10 languages
Photo credit Getty Images
Label: Detect entities from furniture to
transportation
Logos: Identify product logos
Landmarks & Image Properties
Detect landmarks & dominant
color of image
Safe Search: Detect explicit content -
adult, violent, medical and spoof
Cloud Vision API
Call API from anywhere, with support for embeddable images, and Google Cloud Storage
Let’s Party
Party planning
● Finding people @Twitter
● Cloud Vision API
● Custom classifier
(k-means)
Google Cloud Console
We need to have access so we can
add hash tag to intro slide
Google Cloud
Console
Show Me
the code!
Main shellplus_contacts = get_plus_contacts()
print "Processing %d contacts" % len(plus_contacts)
for plus_id in plus_contacts:
plus_profile = get_plus_profile(plus_id)
image_uri = plus_profile['image']['url'].replace("?sz=50","?sz=250")
image_data = analyze_img(image_uri)
if image_data is not None:
print(image_uri)
if 'labelAnnotations' in image_data['responses'][0]:
for label in image_data['responses'][0]['labelAnnotations']:
print label['description']; label['score']; image_uri
get_plus_contacts: oAuth
storage = Storage('/home/almo/dev/keys/ex1/oAuth_credentials.dat')
credentials = storage.get()
if credentials is None or credentials.invalid:
PEOPLE_API='https://www.googleapis.com/auth/contacts.readonly'
flow = flow_from_clientsecrets('/home/almo/dev/keys/ex1/oAuth_key.json',
scope=[PEOPLE_API])
credentials = run_flow(flow, storage)
http = credentials.authorize(httplib2.Http())
service = build('people','v1',http=http)
request = service.people().connections().list(resourceName='people/me',
pageSize=500)
analyze_image
api_key = json.load(open('/home/almo/dev/keys/ex1/api_key.json'))['api_key']
service = discovery.build('vision','v1',developerKey=api_key)
service_request = service.images().annotate(body={
'requests': [{
'image': {
'content': image_content.decode('UTF-8')
},
'features': [{
'type': 'LABEL_DETECTION',
'maxResults': 3
}]
}]
}
Data
face; 0,92830354; https://lh3.googleusercontent.com/-c3M1gn6ougg/AAAAAAAAAAI/AAAAAAAAAds/cTIrpGhktfw/photo.jpg?sz=250
text; 0,93046468; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250
font; 0,85384184; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250
line; 0,70535356; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250
eyebrow; 0,98022038; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250
hair; 0,96653992; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250
face; 0,95101357; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250
person; 0,92170084; https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250
news; 0,63342041; https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250
professional; 0,61274487;
https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250
drawer; 0,80023241; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250
furniture; 0,79278195; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250
product; 0,76023591; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250
eyewear; 0,97702742; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250
hair; 0,96766639; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250
sunglasses; 0,96445274; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250
person; 0,92747426; https://lh4.googleusercontent.com/--_BxhkQPYfA/AAAAAAAAAAI/AAAAAAAAACA/1pN6-Chy8EI/photo.jpg?sz=250
person; 0,96007371; https://lh3.googleusercontent.com/-sX8l_lv_-7w/AAAAAAAAAAI/AAAAAAAAAPU/ApQpBMPbcdc/photo.jpg?sz=250
face; 0,95332307; https://lh3.googleusercontent.com/-sX8l_lv_-7w/AAAAAAAAAAI/AAAAAAAAAPU/ApQpBMPbcdc/photo.jpg?sz=250
Raw Data
160 different labels
Max Freq.: 200
Min Freq. : 1
person 200 0,9320951099
hair 140 0,9609928544
face 139 0,9489352931
font 136 0,7606724908
text 130 0,925080287
blue 114 0,9112923658
facial hair 36 0,8802876539
nose 34 0,8859786603
profession 30 0,569073382
hairstyle 25 0,7532089968
cartoon 23 0,8588066957
professional 23 0,6149233535
glasses 20 0,8234816515
facial expression 14 0,9502550086
eyebrow 12 0,9559630675
black and white 11 0,9199305709
eyewear 11 0,9767648145
logo 11 0,7749610755
head 9 0,7432496333
clothing 7 0,9151270214
[{}]
Planning our next
Party
"hair", 0.9559916, "person", 0.94347906, "face", 0.92830354
"text", 0.9304647, "font", 0.85384184, "line", 0.70535356
"eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135
"person", 0.92170084, "news", 0.63342035, "professional", 0.61274487
"drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235
"eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274
"person", 0.92747426,
"https://lh4.googleusercontent.com/--_BxhkQPYfA/AAAAAAAAAAI/AAAAAAAAACA/1pN6-Chy8EI/photo.jpg
?sz=250"
"green", 0.9307698, "text", 0.92834556, "font", 0.8631033
"hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355
"face", 0.9523797, "person", 0.94760686, "hair", 0.94507515
"hair", 0.9731342, "face", 0.94925183, "person", 0.9371813
"hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.7414854
"person", 0.925232, "people", 0.9086431, "male", 0.83032143
"person", 0.95530343, "face", 0.94757956, "nose", 0.86752254
"face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414
"face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636
"phenomenon", 0.94444287, "celestial event", 0.53744316, "aurora", 0.52995497
"face", 0.9625666, "hair", 0.9514838, "facial expression", 0.94977105
"product", 0.80306137, "font", 0.77923214, "logo", 0.69078964
"black and white", 0.9267871, "person", 0.8998944, "photography", 0.8296365
Training
mode!
“invited”, "hair", 0.9559916, "person", 0.94347906, "face", 0.92830354
“excluded”, "text", 0.9304647, "font", 0.85384184, "line", 0.70535356
“excluded”, "eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135
“invited”, "person", 0.92170084, "news", 0.63342035, "professional",
0.61274487
“excluded”, "drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235
“excluded”, "eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274
“excluded”, "green", 0.9307698, "text", 0.92834556, "font", 0.8631033
“excluded”, "hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355
“invited”, "face", 0.9523797, "person", 0.94760686, "hair", 0.94507515
“invited”, "hair", 0.9731342, "face", 0.94925183, "person", 0.9371813
“invited”, "hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.7414854
“invited”, "person", 0.925232, "people", 0.9086431, "male", 0.83032143
“invited”, "person", 0.95530343, "face", 0.94757956, "nose", 0.86752254
“excluded”, "face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414
“excluded”, "face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636
Prediction
Mode!
"hair", 0.9559916, "person", 0.94347906, "face", 0.92830354 “invited”
"text", 0.9304647, "font", 0.85384184, "line", 0.70535356 “excluded”
"eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135 “excluded”
"person", 0.92170084, "news", 0.63342035, "professional", 0.61274487 “invited”
"drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235 “excluded”
"eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274 “excluded”
"green", 0.9307698, "text", 0.92834556, "font", 0.8631033 “excluded”
"hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355 “excluded”
"face", 0.9523797, "person", 0.94760686, "hair", 0.94507515 “invited”
"hair", 0.9731342, "face", 0.94925183, "person", 0.9371813 “invited”
"hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.741485 4 “invited”
"person", 0.925232, "people", 0.9086431, "male", 0.83032143 “invited”
"person", 0.95530343, "face", 0.94757956, "nose", 0.86752254 “invited”
"face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414 “excluded”
"face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636 “excluded”
Curating Online Content with
Google ML APIs
Andres L. Martinez a.k.a almo
Google Developer Relations Manager
@davilagrau
Curating online content with Google ML API

Weitere ähnliche Inhalte

Ähnlich wie Curating online content with Google ML API

Ähnlich wie Curating online content with Google ML API (20)

MongoDB World 2019: Gaining ML Insight with Google Vision API and MongoDB
MongoDB World 2019: Gaining ML Insight with Google Vision API and MongoDBMongoDB World 2019: Gaining ML Insight with Google Vision API and MongoDB
MongoDB World 2019: Gaining ML Insight with Google Vision API and MongoDB
 
Microsoft Azure User Group - Lessons Learned
Microsoft Azure User Group - Lessons Learned Microsoft Azure User Group - Lessons Learned
Microsoft Azure User Group - Lessons Learned
 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
 
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB World 2018: Building Intelligent Apps with MongoDB & Google Cloud
 
Building a Data Cloud to enable Analytics & AI-Driven Innovation - Lak Lakshm...
Building a Data Cloud to enable Analytics & AI-Driven Innovation - Lak Lakshm...Building a Data Cloud to enable Analytics & AI-Driven Innovation - Lak Lakshm...
Building a Data Cloud to enable Analytics & AI-Driven Innovation - Lak Lakshm...
 
Microsoft Azure and Microsoft 365 - How Will They Help You
Microsoft Azure and Microsoft 365 - How Will They Help YouMicrosoft Azure and Microsoft 365 - How Will They Help You
Microsoft Azure and Microsoft 365 - How Will They Help You
 
Easy path to machine learning (2023-2024)
Easy path to machine learning (2023-2024)Easy path to machine learning (2023-2024)
Easy path to machine learning (2023-2024)
 
2020-05-28 Microsoft 365 Virtual Marathon - Mobility with Microsoft 365 from ...
2020-05-28 Microsoft 365 Virtual Marathon - Mobility with Microsoft 365 from ...2020-05-28 Microsoft 365 Virtual Marathon - Mobility with Microsoft 365 from ...
2020-05-28 Microsoft 365 Virtual Marathon - Mobility with Microsoft 365 from ...
 
Summit Australia 2019 - Supercharge PowerPlatform with AI - Dipankar Bhattach...
Summit Australia 2019 - Supercharge PowerPlatform with AI - Dipankar Bhattach...Summit Australia 2019 - Supercharge PowerPlatform with AI - Dipankar Bhattach...
Summit Australia 2019 - Supercharge PowerPlatform with AI - Dipankar Bhattach...
 
Understanding ML kit offerings in android
Understanding ML kit offerings in androidUnderstanding ML kit offerings in android
Understanding ML kit offerings in android
 
Windays14 - How to (remote) control Office 365 with Azure
Windays14 - How to (remote) control Office 365 with AzureWindays14 - How to (remote) control Office 365 with Azure
Windays14 - How to (remote) control Office 365 with Azure
 
Azure IoT - A Practical Entry to New Retail
Azure IoT - A Practical Entry to New RetailAzure IoT - A Practical Entry to New Retail
Azure IoT - A Practical Entry to New Retail
 
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local DC 2018: Building Intelligent Apps with MongoDB & Google Cloud
 
Teams lifecycle management with office 365 tools only - Microsoft 365 Virtual...
Teams lifecycle management with office 365 tools only - Microsoft 365 Virtual...Teams lifecycle management with office 365 tools only - Microsoft 365 Virtual...
Teams lifecycle management with office 365 tools only - Microsoft 365 Virtual...
 
Global ai night sept 2019 - Milwaukee
Global ai night sept 2019 - MilwaukeeGlobal ai night sept 2019 - Milwaukee
Global ai night sept 2019 - Milwaukee
 
Are API Services Taking Over All the Interesting Data Science Problems?
Are API Services Taking Over All the Interesting Data Science Problems?Are API Services Taking Over All the Interesting Data Science Problems?
Are API Services Taking Over All the Interesting Data Science Problems?
 
AI pitch SSideri
 AI pitch SSideri  AI pitch SSideri
AI pitch SSideri
 
Worst Practices in Artificial Intelligence
Worst Practices in Artificial IntelligenceWorst Practices in Artificial Intelligence
Worst Practices in Artificial Intelligence
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
 
How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...
 

Mehr von Andrés Leonardo Martinez Ortiz

Mehr von Andrés Leonardo Martinez Ortiz (20)

How to plan work for your team
How to plan work for your teamHow to plan work for your team
How to plan work for your team
 
Tensorflow 2.0 and Coral Edge TPU
Tensorflow 2.0 and Coral Edge TPU Tensorflow 2.0 and Coral Edge TPU
Tensorflow 2.0 and Coral Edge TPU
 
Developer journey with classroom
Developer journey with classroomDeveloper journey with classroom
Developer journey with classroom
 
Better code, faster with kubernetes in google cloud
Better code, faster with kubernetes in google cloudBetter code, faster with kubernetes in google cloud
Better code, faster with kubernetes in google cloud
 
Fostering Google Software Technologies in Open Digital Ecosystems
Fostering Google Software Technologies in Open Digital EcosystemsFostering Google Software Technologies in Open Digital Ecosystems
Fostering Google Software Technologies in Open Digital Ecosystems
 
Engineering Machine Learning technologies
Engineering Machine Learning technologiesEngineering Machine Learning technologies
Engineering Machine Learning technologies
 
Google Cloud Online training resources and certification
Google Cloud Online training resources and certificationGoogle Cloud Online training resources and certification
Google Cloud Online training resources and certification
 
The future of conversation ui
The future of conversation uiThe future of conversation ui
The future of conversation ui
 
Clustering tensor flow con kubernetes y raspberry pi
Clustering tensor flow con kubernetes y raspberry piClustering tensor flow con kubernetes y raspberry pi
Clustering tensor flow con kubernetes y raspberry pi
 
Understanding the apps developer environment
Understanding the apps developer environmentUnderstanding the apps developer environment
Understanding the apps developer environment
 
Collaboration! Ramping up the future!
Collaboration! Ramping up the future!Collaboration! Ramping up the future!
Collaboration! Ramping up the future!
 
Firefox OS Innovating Mobile Platforms
Firefox OS Innovating Mobile PlatformsFirefox OS Innovating Mobile Platforms
Firefox OS Innovating Mobile Platforms
 
Wellsprings of innovation
Wellsprings of innovationWellsprings of innovation
Wellsprings of innovation
 
App Circus Developers Economic 2012
App Circus Developers Economic 2012App Circus Developers Economic 2012
App Circus Developers Economic 2012
 
Blue Via Plataforma De Pagos MóViles Y Ap Is De Red
Blue Via   Plataforma De Pagos MóViles Y Ap Is De RedBlue Via   Plataforma De Pagos MóViles Y Ap Is De Red
Blue Via Plataforma De Pagos MóViles Y Ap Is De Red
 
BlueVia 2012
BlueVia 2012BlueVia 2012
BlueVia 2012
 
BlueVia Developer Economics 2011
BlueVia Developer Economics 2011BlueVia Developer Economics 2011
BlueVia Developer Economics 2011
 
Economic Impact For Sm Es Of Cloud Technologies
Economic Impact For Sm Es Of Cloud TechnologiesEconomic Impact For Sm Es Of Cloud Technologies
Economic Impact For Sm Es Of Cloud Technologies
 
Economic Impact For Sm Es Of Oss Spanish Legal Framework
Economic Impact For Sm Es Of Oss Spanish Legal FrameworkEconomic Impact For Sm Es Of Oss Spanish Legal Framework
Economic Impact For Sm Es Of Oss Spanish Legal Framework
 
Collaborative Tools For Free Software Development
Collaborative Tools For Free Software DevelopmentCollaborative Tools For Free Software Development
Collaborative Tools For Free Software Development
 

Kürzlich hochgeladen

notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
MsecMca
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Kürzlich hochgeladen (20)

University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdfONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
 
Unit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdfUnit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdf
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
 
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
 
NFPA 5000 2024 standard .
NFPA 5000 2024 standard                                  .NFPA 5000 2024 standard                                  .
NFPA 5000 2024 standard .
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
Intze Overhead Water Tank Design by Working Stress - IS Method.pdf
Intze Overhead Water Tank  Design by Working Stress - IS Method.pdfIntze Overhead Water Tank  Design by Working Stress - IS Method.pdf
Intze Overhead Water Tank Design by Working Stress - IS Method.pdf
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
 

Curating online content with Google ML API

  • 1. Curating Online Content with Google ML APIs Andres L. Martinez a.k.a almo Google Developer Relations Manager @davilagrau
  • 3. Unstructured data accounts for 90% of enterprise data* Cloud Machine Learning APIs help you make sense of it *Source: IDC
  • 4. The Machine Learning Spectrum TensorFlow Cloud Machine Learning Machine Learning APIs BYOML skills (Friendly Machine Learning) Pre-packaged ML
  • 5.
  • 6.
  • 8. Confidential & ProprietaryGoogle Cloud Platform 8 So…. Why APIs? { Google Cloud Platform } 1. We want to offer businesses the tools to differentiate by offering a powerful set of APIs that enable apps to see, hear and understand the world 2. Reduce your Time to Market (TMM) when launching your next-generation app 3. Provide you easy access to machine learning technology to give any developer the freedom to work in the language and tools they want 4. Provide virtually limitless scalability to your application without needing to manage back-end servers running deep learning
  • 9. Pre-Trained Machine Learning Models Fully trained ML models from Google Cloud that allow a general developer to take advantage of rich machine learning capabilities with simple REST based services.
  • 10. Introducing Cloud Natural Language API Sentiment analysis and entity recognition for text
  • 11. Confidential & ProprietaryGoogle Cloud Platform 11 Features Extract sentence, identify parts of speech and create dependency parse trees for each sentence Identify entities and label by types such as person, organization, location, events, products and media Understand the overall sentiment of a block of text Access via REST API. Text can be uploaded in the request or integrated with Google Cloud Storage Syntax Analysis Entity Recognition Sentiment Analysis Integrated REST API
  • 12. Cloud Vision API Insight from images with our powerful Cloud Vision API
  • 13. Confidential & ProprietaryGoogle Cloud Platform 13 Faces: Faces, facial landmarks, emotions OCR: Read and extract text, with support for > 10 languages Photo credit Getty Images Label: Detect entities from furniture to transportation Logos: Identify product logos Landmarks & Image Properties Detect landmarks & dominant color of image Safe Search: Detect explicit content - adult, violent, medical and spoof Cloud Vision API Call API from anywhere, with support for embeddable images, and Google Cloud Storage
  • 15.
  • 16.
  • 17. Party planning ● Finding people @Twitter ● Cloud Vision API ● Custom classifier (k-means)
  • 18.
  • 19. Google Cloud Console We need to have access so we can add hash tag to intro slide
  • 21.
  • 23. Main shellplus_contacts = get_plus_contacts() print "Processing %d contacts" % len(plus_contacts) for plus_id in plus_contacts: plus_profile = get_plus_profile(plus_id) image_uri = plus_profile['image']['url'].replace("?sz=50","?sz=250") image_data = analyze_img(image_uri) if image_data is not None: print(image_uri) if 'labelAnnotations' in image_data['responses'][0]: for label in image_data['responses'][0]['labelAnnotations']: print label['description']; label['score']; image_uri
  • 24. get_plus_contacts: oAuth storage = Storage('/home/almo/dev/keys/ex1/oAuth_credentials.dat') credentials = storage.get() if credentials is None or credentials.invalid: PEOPLE_API='https://www.googleapis.com/auth/contacts.readonly' flow = flow_from_clientsecrets('/home/almo/dev/keys/ex1/oAuth_key.json', scope=[PEOPLE_API]) credentials = run_flow(flow, storage) http = credentials.authorize(httplib2.Http()) service = build('people','v1',http=http) request = service.people().connections().list(resourceName='people/me', pageSize=500)
  • 25. analyze_image api_key = json.load(open('/home/almo/dev/keys/ex1/api_key.json'))['api_key'] service = discovery.build('vision','v1',developerKey=api_key) service_request = service.images().annotate(body={ 'requests': [{ 'image': { 'content': image_content.decode('UTF-8') }, 'features': [{ 'type': 'LABEL_DETECTION', 'maxResults': 3 }] }] }
  • 26. Data
  • 27. face; 0,92830354; https://lh3.googleusercontent.com/-c3M1gn6ougg/AAAAAAAAAAI/AAAAAAAAAds/cTIrpGhktfw/photo.jpg?sz=250 text; 0,93046468; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250 font; 0,85384184; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250 line; 0,70535356; https://lh4.googleusercontent.com/-GFVyrVlgMy4/AAAAAAAAAAI/AAAAAAAAABE/u3xVd9eJgf8/photo.jpg?sz=250 eyebrow; 0,98022038; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250 hair; 0,96653992; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250 face; 0,95101357; https://lh5.googleusercontent.com/-5c9gdP9nX9M/AAAAAAAAAAI/AAAAAAAAGt4/FoZEEVA8F68/photo.jpg?sz=250 person; 0,92170084; https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250 news; 0,63342041; https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250 professional; 0,61274487; https://lh4.googleusercontent.com/-yVWpXcqQfXU/AAAAAAAAAAI/AAAAAAAAB5w/rqxRrJHgk_0/photo.jpg?sz=250 drawer; 0,80023241; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250 furniture; 0,79278195; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250 product; 0,76023591; https://lh6.googleusercontent.com/-Qf9SSsIUktA/AAAAAAAAAAI/AAAAAAAAABg/u6zPUNXCYFs/photo.jpg?sz=250 eyewear; 0,97702742; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250 hair; 0,96766639; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250 sunglasses; 0,96445274; https://lh3.googleusercontent.com/-ihQNk3ewmzQ/AAAAAAAAAAI/AAAAAAAAAMk/EEEylEyriNE/photo.jpg?sz=250 person; 0,92747426; https://lh4.googleusercontent.com/--_BxhkQPYfA/AAAAAAAAAAI/AAAAAAAAACA/1pN6-Chy8EI/photo.jpg?sz=250 person; 0,96007371; https://lh3.googleusercontent.com/-sX8l_lv_-7w/AAAAAAAAAAI/AAAAAAAAAPU/ApQpBMPbcdc/photo.jpg?sz=250 face; 0,95332307; https://lh3.googleusercontent.com/-sX8l_lv_-7w/AAAAAAAAAAI/AAAAAAAAAPU/ApQpBMPbcdc/photo.jpg?sz=250 Raw Data
  • 28. 160 different labels Max Freq.: 200 Min Freq. : 1
  • 29. person 200 0,9320951099 hair 140 0,9609928544 face 139 0,9489352931 font 136 0,7606724908 text 130 0,925080287 blue 114 0,9112923658 facial hair 36 0,8802876539 nose 34 0,8859786603 profession 30 0,569073382 hairstyle 25 0,7532089968
  • 30. cartoon 23 0,8588066957 professional 23 0,6149233535 glasses 20 0,8234816515 facial expression 14 0,9502550086 eyebrow 12 0,9559630675 black and white 11 0,9199305709 eyewear 11 0,9767648145 logo 11 0,7749610755 head 9 0,7432496333 clothing 7 0,9151270214
  • 31.
  • 32. [{}]
  • 33.
  • 35. "hair", 0.9559916, "person", 0.94347906, "face", 0.92830354 "text", 0.9304647, "font", 0.85384184, "line", 0.70535356 "eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135 "person", 0.92170084, "news", 0.63342035, "professional", 0.61274487 "drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235 "eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274 "person", 0.92747426, "https://lh4.googleusercontent.com/--_BxhkQPYfA/AAAAAAAAAAI/AAAAAAAAACA/1pN6-Chy8EI/photo.jpg ?sz=250" "green", 0.9307698, "text", 0.92834556, "font", 0.8631033 "hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355 "face", 0.9523797, "person", 0.94760686, "hair", 0.94507515 "hair", 0.9731342, "face", 0.94925183, "person", 0.9371813 "hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.7414854 "person", 0.925232, "people", 0.9086431, "male", 0.83032143 "person", 0.95530343, "face", 0.94757956, "nose", 0.86752254 "face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414 "face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636 "phenomenon", 0.94444287, "celestial event", 0.53744316, "aurora", 0.52995497 "face", 0.9625666, "hair", 0.9514838, "facial expression", 0.94977105 "product", 0.80306137, "font", 0.77923214, "logo", 0.69078964 "black and white", 0.9267871, "person", 0.8998944, "photography", 0.8296365
  • 37. “invited”, "hair", 0.9559916, "person", 0.94347906, "face", 0.92830354 “excluded”, "text", 0.9304647, "font", 0.85384184, "line", 0.70535356 “excluded”, "eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135 “invited”, "person", 0.92170084, "news", 0.63342035, "professional", 0.61274487 “excluded”, "drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235 “excluded”, "eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274 “excluded”, "green", 0.9307698, "text", 0.92834556, "font", 0.8631033 “excluded”, "hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355 “invited”, "face", 0.9523797, "person", 0.94760686, "hair", 0.94507515 “invited”, "hair", 0.9731342, "face", 0.94925183, "person", 0.9371813 “invited”, "hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.7414854 “invited”, "person", 0.925232, "people", 0.9086431, "male", 0.83032143 “invited”, "person", 0.95530343, "face", 0.94757956, "nose", 0.86752254 “excluded”, "face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414 “excluded”, "face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636
  • 39. "hair", 0.9559916, "person", 0.94347906, "face", 0.92830354 “invited” "text", 0.9304647, "font", 0.85384184, "line", 0.70535356 “excluded” "eyebrow", 0.9802204, "hair", 0.9665399, "face", 0.9510135 “excluded” "person", 0.92170084, "news", 0.63342035, "professional", 0.61274487 “invited” "drawer", 0.8002325, "furniture", 0.792782, "product", 0.760235 “excluded” "eyewear", 0.9770274, "hair", 0.9676664, "sunglasses", 0.96445274 “excluded” "green", 0.9307698, "text", 0.92834556, "font", 0.8631033 “excluded” "hair", 0.98155975, "face", 0.95545304, "eyebrow", 0.93590355 “excluded” "face", 0.9523797, "person", 0.94760686, "hair", 0.94507515 “invited” "hair", 0.9731342, "face", 0.94925183, "person", 0.9371813 “invited” "hair", 0.94741917, "person", 0.9436425, "hairstyle", 0.741485 4 “invited” "person", 0.925232, "people", 0.9086431, "male", 0.83032143 “invited” "person", 0.95530343, "face", 0.94757956, "nose", 0.86752254 “invited” "face", 0.96074444, "hair", 0.9606222, "eyebrow", 0.9451414 “excluded” "face", 0.9664352, "hair", 0.9561741, "nose", 0.9222636 “excluded”
  • 40.
  • 41.
  • 42. Curating Online Content with Google ML APIs Andres L. Martinez a.k.a almo Google Developer Relations Manager @davilagrau