SlideShare a Scribd company logo
1 of 22
Download to read offline
INTRODUCTION TO
EINSTEIN VISION
1
INTRODUCTION
TO EINSTEIN
VISION
Einstein vision is a part of Einstein Platform services
technology which provides services in the form of
API to build AI powered apps.
Using Einstein Vision, you can
▸ Leverage pre-trained classifiers
▸ Train custom classifiers
▸ Bring the power of image recognition to CRM or
other third party applications
2
The Einstein
Vision APIs
3
Einstein Image
Classification API
● Enables developers to train deep
learning models for image
classification and recognition
Einstein Object Detection
(Pilot) API
● Enables developers to train models to
recognize and count multiple distinct
objects within an image
● Provide granular details like the size
and location of each object.
WHERE CAN
YOU USE IT?
Gain new insights of your customer and leverage it
for Sales, Service and Marketing of your products or
services.
4 1. Visual Search
Visual Filters to
Find Product
Search By Product Photo
WHERE CAN
YOU USE IT?
5
2. Brand Detection
Understand Customer
Preferences
Monitor User-Generated
Images
Evaluate Banner
Advertisement Exposure
WHERE CAN
YOU USE IT?
6
3. Product Identification
Early Product Issue
Identification
Streamline Inventory
Restocking
Optimize Product Selling
Priorities
How Einstein
Vision work?
7
HOW EINSTEIN
VISION WORK?
Einstein Vision is a concept from Deep Learning,
deep learning is a branch of Machine Learning.
Machine Learning allows computers to predict
more accurately without being explicitly
programmed.
8
EINSTEIN VISION
FUNDAMENTALS
9
EINSTEIN
VISION
FUNDAMENTALS
10 Dataset Label Training
Prediction Model
It defined set of the
similar data at one
place.
It is a set of data that
need to be pass to API
of the Einstein Vision
User need to train the
data by classifying
user's dataset.
Finally the Model will
return results where the
input matches in the
dataset.
Machine learning will
construct the unique Model
on providing correctly
trained dataset.
Build Your Own
Einstein Vision
Application
11
Have you
registered for
Einstein
Platform
Services?
12 Download Private Key
(einstein_platform.pem)
Register on
api.einstein.ai/signup
Upload key on
api.einstein.ai/token
Upload Private Key
(.pem file) in the org
(Files->Upload Files)
Get TokenAdd Remote Site
Settings -
api.einstein.ai
13
Steps:
▸ Create Examples
(following these
rules) from a zip file
▸ To Create a Dataset
we need to upload
the .zip file (from
Local or Cloud)
using cURL
▸ Upload a .zip file to
the location
https://api.einstein.
ai/v2/vision/dataset
s/upload
How do we
Create a
Dataset?
For Better
performance, it is
recommended that
to create a Dataset
and uploading a
.zip file.
Command to
Upload a .zip
file at Local
Machine
Request:
curl -X POST -H "Authorization: Bearer
358101028905754f22cf4e96ce8d9f6071ecc5a5" -H "Cache-Control:
no-cache" -H "Content-Type: multipart/form-data" -F "type=image" -F
"data=@D:/Projects/Salesforce Einstein/Electronics_SAC.zip"
https://api.einstein.ai/v2/vision/datasets/upload
Response:
{"id":1014352,"name":"Electronics_SAC","createdAt":"2017-09-27T05:54:
10.000+0000","updatedAt":"2017-09-27T05:54:10.000+0000","labelSummary
":{"labels":[]},"totalExamples":0,"available":false,"statusMsg":"UPLO
ADING","type":"image","object":"dataset"}
Get Status: Using Dataset id we get in response
curl -X GET -H "Authorization: Bearer
85c1d97ee86b43551ebdb28ed9414689a55f6e61" -H "Cache-Control:
no-cache" https://api.einstein.ai/v2/vision/datasets/1014352
14
Request:
curl -X POST -H "Authorization: Bearer
358101028905754f22cf4e96ce8d9f6071ecc5a5" -H "Cache-Control:
no-cache" -H "Content-Type: multipart/form-data" -F "type=image"
-F "path=http://einstein.ai/images/mountainvsbeach.zip"
https://api.einstein.ai/v2/vision/datasets/upload
Response we get and Status can be checked as similar to mentioned
in the previous slide
Command to
Upload a .zip
file in the
Cloud
15
Request:
curl -X POST -H "Authorization: Bearer
dbc706627fae59df668940d32c14d00170e45ac5" -H "Cache-Control:
no-cache" -H "Content-Type: multipart/form-data" -F "name=Animal
Model" -F "datasetId=1014363" https://api.einstein.ai/v2/vision/train
Response:
{"datasetId":1014363,"datasetVersionId":0,"name":"Animal
Model","status":"QUEUED","progress":0,"createdAt":"2017-09-27T08:35:1
9.000+0000","updatedAt":"2017-09-27T08:35:19.000+0000","learningRate"
:0.0,"epochs":0,"queuePosition":1,"object":"training","modelId":"TWJX
XO432WIVBNKMM7AVPGGTIA","trainParams":null,"trainStats":null,"modelTy
pe":"image"}
Get Training Status: Using Model id that we get in response
curl -X GET -H "Authorization: Bearer
dbc706627fae59df668940d32c14d00170e45ac5" -H "Cache-Control:
no-cache"
https://api.einstein.ai/v2/vision/train/TWJXXO432WIVBNKMM7AVPGGTIA
Train the
Dataset
**To Train the
dataset you need to
have 40 examples
16
Prediction
Using Image
File
Request:
curl -X POST -H "Authorization: Bearer
85c1d97ee86b43551ebdb28ed9414689a55f6e61" -H "Cache-Control:
no-cache" -H "Content-Type: multipart/form-data" -F
"sampleId=Photo Prediction" -F
"sampleContent=@/FileToPredict/camel.jpg" -F
"modelId=TWJXXO432WIVBNKMM7AVPGGTIA"
https://api.einstein.ai/v2/vision/predict
Response:
(Prediction:[label=Domestic Animal, probability=0.5282774],
Prediction:[label=Wild Animals, probability=0.47172257])
Application UI:
Download Code
17
What’s new
with
Einstein
Vision in
Winter’ 18?
18
Switch to the new API End point
Use Feedback API to Optimize Your
Model
Identify Multiple Objects with a Multi-Label
Model
Classify Images with two Prebuilt Models
Add Data to a Model with Global Datasets
Creating a Dataset Requires a Dataset
Type
Created By:
Jina Chetia (Founder)
Amar Kulkarni (Sr. Tech Lead)
Sukanya Banekar (Salesforce Developer)
Designed By:
Chetan More (Digital Marketer)
Nilesh Bhongale (Graphic Designer)
19
Advisory Services
Integrated Solution
Salesforce Automation
Lightning Development
Product Development
Salesforce Customization & Development
Introduction To Einstein Vision - Zen4orce
Introduction To Einstein Vision - Zen4orce

More Related Content

What's hot

User Experience as Competitive Advantage
User Experience as Competitive AdvantageUser Experience as Competitive Advantage
User Experience as Competitive AdvantageKalle Tiihonen
 
About experiture-product-brochure
About experiture-product-brochureAbout experiture-product-brochure
About experiture-product-brochureMukut Chakravarti
 
Optimized Online Marketing in Facebook (Smartly.io)
Optimized Online Marketing in Facebook (Smartly.io)Optimized Online Marketing in Facebook (Smartly.io)
Optimized Online Marketing in Facebook (Smartly.io)Markus Ojala
 
Empower Inside Sales With High Velocity Sales (Salesforce + AI)
Empower Inside Sales With High Velocity Sales (Salesforce + AI)Empower Inside Sales With High Velocity Sales (Salesforce + AI)
Empower Inside Sales With High Velocity Sales (Salesforce + AI)Harshala Shewale ☁
 
How to Market Your New App on the Atlassian Marketplace
How to Market Your New App on the Atlassian MarketplaceHow to Market Your New App on the Atlassian Marketplace
How to Market Your New App on the Atlassian MarketplaceAtlassian
 

What's hot (6)

User Experience as Competitive Advantage
User Experience as Competitive AdvantageUser Experience as Competitive Advantage
User Experience as Competitive Advantage
 
About experiture-product-brochure
About experiture-product-brochureAbout experiture-product-brochure
About experiture-product-brochure
 
Optimized Online Marketing in Facebook (Smartly.io)
Optimized Online Marketing in Facebook (Smartly.io)Optimized Online Marketing in Facebook (Smartly.io)
Optimized Online Marketing in Facebook (Smartly.io)
 
Empower Inside Sales With High Velocity Sales (Salesforce + AI)
Empower Inside Sales With High Velocity Sales (Salesforce + AI)Empower Inside Sales With High Velocity Sales (Salesforce + AI)
Empower Inside Sales With High Velocity Sales (Salesforce + AI)
 
How to Market Your New App on the Atlassian Marketplace
How to Market Your New App on the Atlassian MarketplaceHow to Market Your New App on the Atlassian Marketplace
How to Market Your New App on the Atlassian Marketplace
 
Brochure-v6
Brochure-v6Brochure-v6
Brochure-v6
 

Similar to Introduction To Einstein Vision - Zen4orce

Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingAdhesh Shrivastava
 
Google cloud platform
Google cloud platformGoogle cloud platform
Google cloud platformrajdeep
 
What Is Computer Vision as a Service? (Only Guide You Need)
What Is Computer Vision as a Service? (Only Guide You Need)What Is Computer Vision as a Service? (Only Guide You Need)
What Is Computer Vision as a Service? (Only Guide You Need)Kavika Roy
 
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018Amazon Web Services
 
Proposal -co_win_india_valardigital-converted
Proposal  -co_win_india_valardigital-convertedProposal  -co_win_india_valardigital-converted
Proposal -co_win_india_valardigital-convertedUpendraSharma53
 
AI for Element Selection
AI for Element SelectionAI for Element Selection
AI for Element Selectiontestdotai
 
hari_duche_updated
hari_duche_updatedhari_duche_updated
hari_duche_updatedHari Duche
 
Brad Kenstler - A new way to learn machine learning.pdf
Brad Kenstler - A new way to learn machine learning.pdfBrad Kenstler - A new way to learn machine learning.pdf
Brad Kenstler - A new way to learn machine learning.pdfAmazon Web Services
 
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 FineMongoDB
 
Mobile backends with Google Cloud Platform (MBLTDev'14)
Mobile backends with Google Cloud Platform (MBLTDev'14)Mobile backends with Google Cloud Platform (MBLTDev'14)
Mobile backends with Google Cloud Platform (MBLTDev'14)Natalia Efimtseva
 
Azure Data Factory v2
Azure Data Factory v2Azure Data Factory v2
Azure Data Factory v2inovex GmbH
 
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...Amazon Web Services Korea
 
Chris O'Brien - Building AI into Power Platform solutions
Chris O'Brien - Building AI into Power Platform solutionsChris O'Brien - Building AI into Power Platform solutions
Chris O'Brien - Building AI into Power Platform solutionsChris O'Brien
 
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...e-Legion
 
Azure Cognitive Services - Custom Vision
Azure Cognitive Services  - Custom VisionAzure Cognitive Services  - Custom Vision
Azure Cognitive Services - Custom VisionLuis Beltran
 
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成Amazon Web Services
 

Similar to Introduction To Einstein Vision - Zen4orce (20)

Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
 
Google cloud platform
Google cloud platformGoogle cloud platform
Google cloud platform
 
What Is Computer Vision as a Service? (Only Guide You Need)
What Is Computer Vision as a Service? (Only Guide You Need)What Is Computer Vision as a Service? (Only Guide You Need)
What Is Computer Vision as a Service? (Only Guide You Need)
 
How to be like amazon
How to be like amazonHow to be like amazon
How to be like amazon
 
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
Build a Custom Model for Object & Logo Detection (AIM421) - AWS re:Invent 2018
 
#TDXRecap India tour
#TDXRecap India tour#TDXRecap India tour
#TDXRecap India tour
 
Proposal -co_win_india_valardigital-converted
Proposal  -co_win_india_valardigital-convertedProposal  -co_win_india_valardigital-converted
Proposal -co_win_india_valardigital-converted
 
AI for Element Selection
AI for Element SelectionAI for Element Selection
AI for Element Selection
 
hari_duche_updated
hari_duche_updatedhari_duche_updated
hari_duche_updated
 
Brad Kenstler - A new way to learn machine learning.pdf
Brad Kenstler - A new way to learn machine learning.pdfBrad Kenstler - A new way to learn machine learning.pdf
Brad Kenstler - A new way to learn machine learning.pdf
 
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
 
Why Startups Are Still On AWS
Why Startups Are Still On AWSWhy Startups Are Still On AWS
Why Startups Are Still On AWS
 
Mobile backends with Google Cloud Platform (MBLTDev'14)
Mobile backends with Google Cloud Platform (MBLTDev'14)Mobile backends with Google Cloud Platform (MBLTDev'14)
Mobile backends with Google Cloud Platform (MBLTDev'14)
 
Azure Data Factory v2
Azure Data Factory v2Azure Data Factory v2
Azure Data Factory v2
 
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...
Operationalizing Machine Learning (Rajeev Dutt, CEO, Co-Founder, DimensionalM...
 
Portafolio
PortafolioPortafolio
Portafolio
 
Chris O'Brien - Building AI into Power Platform solutions
Chris O'Brien - Building AI into Power Platform solutionsChris O'Brien - Building AI into Power Platform solutions
Chris O'Brien - Building AI into Power Platform solutions
 
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...
#MBLTdev: Разработка backend для мобильного приложения с использованием Googl...
 
Azure Cognitive Services - Custom Vision
Azure Cognitive Services  - Custom VisionAzure Cognitive Services  - Custom Vision
Azure Cognitive Services - Custom Vision
 
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成
AI ﹑大數據媒體應用和利用機器學習與 AWS 媒體服務實現自動化內容生成
 

More from Thinqloud

Salesforce summer 18 release notes highlights by thinqloud
Salesforce summer 18 release notes highlights by thinqloudSalesforce summer 18 release notes highlights by thinqloud
Salesforce summer 18 release notes highlights by thinqloudThinqloud
 
Salesforce news sumary may 2018 - thinqloud
Salesforce news sumary   may 2018 - thinqloudSalesforce news sumary   may 2018 - thinqloud
Salesforce news sumary may 2018 - thinqloudThinqloud
 
Salesforce spring 18 release highlights by thinqloud
Salesforce spring 18 release highlights by thinqloudSalesforce spring 18 release highlights by thinqloud
Salesforce spring 18 release highlights by thinqloudThinqloud
 
Salesforce Recap 2017 by Thinqloud
Salesforce Recap 2017 by ThinqloudSalesforce Recap 2017 by Thinqloud
Salesforce Recap 2017 by ThinqloudThinqloud
 
Women In Tech (WIT) Jaipur - Jina Chetia - Thinqloud
Women In Tech (WIT) Jaipur - Jina Chetia - ThinqloudWomen In Tech (WIT) Jaipur - Jina Chetia - Thinqloud
Women In Tech (WIT) Jaipur - Jina Chetia - ThinqloudThinqloud
 
Winter 18 Release Notes Highlights - Zen4orce
Winter 18 Release Notes Highlights - Zen4orceWinter 18 Release Notes Highlights - Zen4orce
Winter 18 Release Notes Highlights - Zen4orceThinqloud
 
What Is Salesforce CRM, Editions, Licenses?
What Is Salesforce CRM, Editions, Licenses?What Is Salesforce CRM, Editions, Licenses?
What Is Salesforce CRM, Editions, Licenses?Thinqloud
 
Salesforce Summer '17 Release Highlights | Zen4orce
Salesforce Summer '17 Release Highlights | Zen4orceSalesforce Summer '17 Release Highlights | Zen4orce
Salesforce Summer '17 Release Highlights | Zen4orceThinqloud
 
2016 Salesforce Release Highlights
2016 Salesforce Release Highlights2016 Salesforce Release Highlights
2016 Salesforce Release HighlightsThinqloud
 
Salesforce Lightning Tips & Tricks
Salesforce Lightning Tips & Tricks Salesforce Lightning Tips & Tricks
Salesforce Lightning Tips & Tricks Thinqloud
 
Get started with data migration
Get started with data migrationGet started with data migration
Get started with data migrationThinqloud
 
Handling of Large Data by Salesforce
Handling of Large Data by SalesforceHandling of Large Data by Salesforce
Handling of Large Data by SalesforceThinqloud
 
Our top picks from Salesforce Winter'17 release !!
Our top picks from Salesforce Winter'17 release !!Our top picks from Salesforce Winter'17 release !!
Our top picks from Salesforce Winter'17 release !!Thinqloud
 
Digital Marketing Automation with Salesforce Marketing Cloud
Digital Marketing Automation with Salesforce Marketing CloudDigital Marketing Automation with Salesforce Marketing Cloud
Digital Marketing Automation with Salesforce Marketing CloudThinqloud
 
Salesforce Lightning Process builder
Salesforce Lightning Process builderSalesforce Lightning Process builder
Salesforce Lightning Process builderThinqloud
 
Fundraising applications For NonProfits
Fundraising applications For NonProfitsFundraising applications For NonProfits
Fundraising applications For NonProfitsThinqloud
 
Security Testing using ZAP in SFDC
Security Testing using ZAP in SFDCSecurity Testing using ZAP in SFDC
Security Testing using ZAP in SFDCThinqloud
 
Learning jQuery made exciting in an interactive session by one of our team me...
Learning jQuery made exciting in an interactive session by one of our team me...Learning jQuery made exciting in an interactive session by one of our team me...
Learning jQuery made exciting in an interactive session by one of our team me...Thinqloud
 
Discover the Connection - NonProfits and CRM
Discover the Connection - NonProfits and CRMDiscover the Connection - NonProfits and CRM
Discover the Connection - NonProfits and CRMThinqloud
 

More from Thinqloud (19)

Salesforce summer 18 release notes highlights by thinqloud
Salesforce summer 18 release notes highlights by thinqloudSalesforce summer 18 release notes highlights by thinqloud
Salesforce summer 18 release notes highlights by thinqloud
 
Salesforce news sumary may 2018 - thinqloud
Salesforce news sumary   may 2018 - thinqloudSalesforce news sumary   may 2018 - thinqloud
Salesforce news sumary may 2018 - thinqloud
 
Salesforce spring 18 release highlights by thinqloud
Salesforce spring 18 release highlights by thinqloudSalesforce spring 18 release highlights by thinqloud
Salesforce spring 18 release highlights by thinqloud
 
Salesforce Recap 2017 by Thinqloud
Salesforce Recap 2017 by ThinqloudSalesforce Recap 2017 by Thinqloud
Salesforce Recap 2017 by Thinqloud
 
Women In Tech (WIT) Jaipur - Jina Chetia - Thinqloud
Women In Tech (WIT) Jaipur - Jina Chetia - ThinqloudWomen In Tech (WIT) Jaipur - Jina Chetia - Thinqloud
Women In Tech (WIT) Jaipur - Jina Chetia - Thinqloud
 
Winter 18 Release Notes Highlights - Zen4orce
Winter 18 Release Notes Highlights - Zen4orceWinter 18 Release Notes Highlights - Zen4orce
Winter 18 Release Notes Highlights - Zen4orce
 
What Is Salesforce CRM, Editions, Licenses?
What Is Salesforce CRM, Editions, Licenses?What Is Salesforce CRM, Editions, Licenses?
What Is Salesforce CRM, Editions, Licenses?
 
Salesforce Summer '17 Release Highlights | Zen4orce
Salesforce Summer '17 Release Highlights | Zen4orceSalesforce Summer '17 Release Highlights | Zen4orce
Salesforce Summer '17 Release Highlights | Zen4orce
 
2016 Salesforce Release Highlights
2016 Salesforce Release Highlights2016 Salesforce Release Highlights
2016 Salesforce Release Highlights
 
Salesforce Lightning Tips & Tricks
Salesforce Lightning Tips & Tricks Salesforce Lightning Tips & Tricks
Salesforce Lightning Tips & Tricks
 
Get started with data migration
Get started with data migrationGet started with data migration
Get started with data migration
 
Handling of Large Data by Salesforce
Handling of Large Data by SalesforceHandling of Large Data by Salesforce
Handling of Large Data by Salesforce
 
Our top picks from Salesforce Winter'17 release !!
Our top picks from Salesforce Winter'17 release !!Our top picks from Salesforce Winter'17 release !!
Our top picks from Salesforce Winter'17 release !!
 
Digital Marketing Automation with Salesforce Marketing Cloud
Digital Marketing Automation with Salesforce Marketing CloudDigital Marketing Automation with Salesforce Marketing Cloud
Digital Marketing Automation with Salesforce Marketing Cloud
 
Salesforce Lightning Process builder
Salesforce Lightning Process builderSalesforce Lightning Process builder
Salesforce Lightning Process builder
 
Fundraising applications For NonProfits
Fundraising applications For NonProfitsFundraising applications For NonProfits
Fundraising applications For NonProfits
 
Security Testing using ZAP in SFDC
Security Testing using ZAP in SFDCSecurity Testing using ZAP in SFDC
Security Testing using ZAP in SFDC
 
Learning jQuery made exciting in an interactive session by one of our team me...
Learning jQuery made exciting in an interactive session by one of our team me...Learning jQuery made exciting in an interactive session by one of our team me...
Learning jQuery made exciting in an interactive session by one of our team me...
 
Discover the Connection - NonProfits and CRM
Discover the Connection - NonProfits and CRMDiscover the Connection - NonProfits and CRM
Discover the Connection - NonProfits and CRM
 

Recently uploaded

Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 

Recently uploaded (20)

Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 

Introduction To Einstein Vision - Zen4orce

  • 2. INTRODUCTION TO EINSTEIN VISION Einstein vision is a part of Einstein Platform services technology which provides services in the form of API to build AI powered apps. Using Einstein Vision, you can ▸ Leverage pre-trained classifiers ▸ Train custom classifiers ▸ Bring the power of image recognition to CRM or other third party applications 2
  • 3. The Einstein Vision APIs 3 Einstein Image Classification API ● Enables developers to train deep learning models for image classification and recognition Einstein Object Detection (Pilot) API ● Enables developers to train models to recognize and count multiple distinct objects within an image ● Provide granular details like the size and location of each object.
  • 4. WHERE CAN YOU USE IT? Gain new insights of your customer and leverage it for Sales, Service and Marketing of your products or services. 4 1. Visual Search Visual Filters to Find Product Search By Product Photo
  • 5. WHERE CAN YOU USE IT? 5 2. Brand Detection Understand Customer Preferences Monitor User-Generated Images Evaluate Banner Advertisement Exposure
  • 6. WHERE CAN YOU USE IT? 6 3. Product Identification Early Product Issue Identification Streamline Inventory Restocking Optimize Product Selling Priorities
  • 8. HOW EINSTEIN VISION WORK? Einstein Vision is a concept from Deep Learning, deep learning is a branch of Machine Learning. Machine Learning allows computers to predict more accurately without being explicitly programmed. 8
  • 10. EINSTEIN VISION FUNDAMENTALS 10 Dataset Label Training Prediction Model It defined set of the similar data at one place. It is a set of data that need to be pass to API of the Einstein Vision User need to train the data by classifying user's dataset. Finally the Model will return results where the input matches in the dataset. Machine learning will construct the unique Model on providing correctly trained dataset.
  • 11. Build Your Own Einstein Vision Application 11
  • 12. Have you registered for Einstein Platform Services? 12 Download Private Key (einstein_platform.pem) Register on api.einstein.ai/signup Upload key on api.einstein.ai/token Upload Private Key (.pem file) in the org (Files->Upload Files) Get TokenAdd Remote Site Settings - api.einstein.ai
  • 13. 13 Steps: ▸ Create Examples (following these rules) from a zip file ▸ To Create a Dataset we need to upload the .zip file (from Local or Cloud) using cURL ▸ Upload a .zip file to the location https://api.einstein. ai/v2/vision/dataset s/upload How do we Create a Dataset? For Better performance, it is recommended that to create a Dataset and uploading a .zip file.
  • 14. Command to Upload a .zip file at Local Machine Request: curl -X POST -H "Authorization: Bearer 358101028905754f22cf4e96ce8d9f6071ecc5a5" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "type=image" -F "data=@D:/Projects/Salesforce Einstein/Electronics_SAC.zip" https://api.einstein.ai/v2/vision/datasets/upload Response: {"id":1014352,"name":"Electronics_SAC","createdAt":"2017-09-27T05:54: 10.000+0000","updatedAt":"2017-09-27T05:54:10.000+0000","labelSummary ":{"labels":[]},"totalExamples":0,"available":false,"statusMsg":"UPLO ADING","type":"image","object":"dataset"} Get Status: Using Dataset id we get in response curl -X GET -H "Authorization: Bearer 85c1d97ee86b43551ebdb28ed9414689a55f6e61" -H "Cache-Control: no-cache" https://api.einstein.ai/v2/vision/datasets/1014352 14
  • 15. Request: curl -X POST -H "Authorization: Bearer 358101028905754f22cf4e96ce8d9f6071ecc5a5" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "type=image" -F "path=http://einstein.ai/images/mountainvsbeach.zip" https://api.einstein.ai/v2/vision/datasets/upload Response we get and Status can be checked as similar to mentioned in the previous slide Command to Upload a .zip file in the Cloud 15
  • 16. Request: curl -X POST -H "Authorization: Bearer dbc706627fae59df668940d32c14d00170e45ac5" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "name=Animal Model" -F "datasetId=1014363" https://api.einstein.ai/v2/vision/train Response: {"datasetId":1014363,"datasetVersionId":0,"name":"Animal Model","status":"QUEUED","progress":0,"createdAt":"2017-09-27T08:35:1 9.000+0000","updatedAt":"2017-09-27T08:35:19.000+0000","learningRate" :0.0,"epochs":0,"queuePosition":1,"object":"training","modelId":"TWJX XO432WIVBNKMM7AVPGGTIA","trainParams":null,"trainStats":null,"modelTy pe":"image"} Get Training Status: Using Model id that we get in response curl -X GET -H "Authorization: Bearer dbc706627fae59df668940d32c14d00170e45ac5" -H "Cache-Control: no-cache" https://api.einstein.ai/v2/vision/train/TWJXXO432WIVBNKMM7AVPGGTIA Train the Dataset **To Train the dataset you need to have 40 examples 16
  • 17. Prediction Using Image File Request: curl -X POST -H "Authorization: Bearer 85c1d97ee86b43551ebdb28ed9414689a55f6e61" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "sampleId=Photo Prediction" -F "sampleContent=@/FileToPredict/camel.jpg" -F "modelId=TWJXXO432WIVBNKMM7AVPGGTIA" https://api.einstein.ai/v2/vision/predict Response: (Prediction:[label=Domestic Animal, probability=0.5282774], Prediction:[label=Wild Animals, probability=0.47172257]) Application UI: Download Code 17
  • 18. What’s new with Einstein Vision in Winter’ 18? 18 Switch to the new API End point Use Feedback API to Optimize Your Model Identify Multiple Objects with a Multi-Label Model Classify Images with two Prebuilt Models Add Data to a Model with Global Datasets Creating a Dataset Requires a Dataset Type
  • 19. Created By: Jina Chetia (Founder) Amar Kulkarni (Sr. Tech Lead) Sukanya Banekar (Salesforce Developer) Designed By: Chetan More (Digital Marketer) Nilesh Bhongale (Graphic Designer) 19
  • 20. Advisory Services Integrated Solution Salesforce Automation Lightning Development Product Development Salesforce Customization & Development