SlideShare a Scribd company logo
1 of 37
Catalit LLC
TENSORFLOW 2.0 AND KERAS
Francesco Mosconi
Data Weekends
Catalit
Data Science
Zero to
Deep Learning
Catalit LLC
ABOUT US
www.catalit.com
Data Weekends
Catalit
Data Science
Zero to
Deep Learning
www.dataweekends.com bootcamp.zerotodeeplearning.com
Catalit LLC
TODAY
• Changes inTensorflow 2.0
• How it differsTensorflow 1.*
• How it differs from keras.io
Catalit LLC
SOMETIME IN AUGUST 2018 …
Catalit LLC
KEY POINTS
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity withTensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
Catalit LLC
DEV SUMMIT (MARCH 6-7)
https://www.tensorflow.org/alpha
Catalit LLC
ARCHITECTURE
Catalit LLC
TODAY
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity withTensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
Catalit LLC
KEY POINTS
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity withTensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
Catalit LLC
PUBLIC 2.0 DESIGN PROCESS
https://groups.google.com/a/tensorflow.org/forum/#!forum/discuss
https://github.com/tensorflow/community/blob/master/governance/TF-RFCs.md
https://github.com/tensorflow/community/tree/master/rfcs
Catalit LLC
WHAT IT MEANS FORYOU
• Final release expected in summer 2019
• If you’re aTF 1.x developer

=> start updating your code as soon as RFPs are accepted
• There is a conversion tool from 1.x to 2.0 (won’t be
perfect, but hey…)
Catalit LLC
CONVERSION SCRIPT
• https://www.tensorflow.org/alpha/guide/upgrade
• tf_upgrade_v2 --infile tensorfoo.py
--outfile tensorfoo-upgraded.py
Catalit LLC
KEY POINTS
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity withTensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
Catalit LLC
EAGER EXECUTION
• Available since late 2017
• Following Pytorch and Chainer
• Imperative
• Define-by-run
• No static graph & session
Catalit LLC
EAGER EXECUTION
• Faster debugging with Python tools
• Dynamic models with Python control flow
• Support for custom and higher-order gradients
Catalit LLC
IS GRAPH GOING AWAY?
• No, you can still define models using the traditional
static graph
• tf.compat.v1.disable_eager_execution()
Catalit LLC
Standard Tensorflow
Catalit LLC
Standard Tensorflow
Eager Execution
Catalit LLC
Standard Tensorflow
Catalit LLC
Standard Tensorflow Eager Execution
Catalit LLC
WHAT IT MEANS FORYOU
• Debug like Numpy, scale likeTensorflow
• Easier to build and test custom models
• Slower than static graph mode
Catalit LLC
KEY POINTS
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity withTensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
Catalit LLC
MODEL APIS INTF 1.X
• tf.core
• tf.layers
• tf.keras.layers
• tf.estimator.Estimator
• tf.contrib.learn.Estimator
• …
Catalit LLC
MODEL APIS INTF 2.0
• tf.core ====> stripped down
• tf.layers ====> Deprecated
• tf.keras ====> Primary API
• tf.estimator.Estimator ====> API same, implementation changed to tf.keras
• tf.contrib.learn.Estimator ====> Deprecated
• …
Catalit LLC
MODEL APIS INTF 2.0
• tf.core ====> stripped down
• tf.layers ====> Deprecated
• tf.keras ====> Primary API
• tf.estimator.Estimator ====> API same, implementation changed to tf.keras
• tf.contrib.learn.Estimator ====> Deprecated
• …
Catalit LLC
TF.KERAS
• What is it?
• How does it work?
• How does it differ from keras.io implementation?
Catalit LLC
WHAT IS KERAS?
https://towardsdatascience.com/deep-learning-framework-power-scores-2018-23607ddf297a
Catalit LLC
WHAT IS KERAS
• Keras is an API specification to design deep learning model
• https://keras.io/

=> independent reference implementation (usingTF or CNTK as backend)
• tf.keras

=>Tensorflow implementation of the same API spec
• Other frameworks implement some version of the API
Catalit LLC
MODEL DEFINITION IN KERAS
• Sequential API
• Functional API
• Model API
Catalit LLC
SEQUENTIAL API
Catalit LLC
SEQUENTIAL API
Catalit LLC
FUNCTIONAL API
Catalit LLC
MODEL API
Catalit LLC
DIFFERENCES
• Support for Eager Execution
• tf.dataVS python data generators
• Model Exporting
• Compatible with Feature Columns
• Compatible with Estimators
Catalit LLC
KEY POINTS
• Public 2.0 design process
• Eager execution
• Remove deprecated APIs & reduce the amount of duplication
• Compatibility and continuity with Tensorflow 1.x
• Compatibility with 1.x exported models
• No more tf.contrib
• More platforms and languages
https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8
Catalit LLC
bootcamp.zerotodeeplearning.com
March 25 - 29 San Francisco Bay Area
Catalit LLC
THANKYOU
Francesco Mosconi
@framosconis
bootcamp.zerotodeeplearning.com
Data Weekends
Catalit
Data Science
Zero to
Deep Learning

More Related Content

What's hot

Episode 10 - External Services in Salesforce
Episode 10 - External Services in SalesforceEpisode 10 - External Services in Salesforce
Episode 10 - External Services in SalesforceJitendra Zaa
 
Declaring Server App Components in Pure Java
Declaring Server App Components in Pure JavaDeclaring Server App Components in Pure Java
Declaring Server App Components in Pure JavaAtlassian
 
Practical Patterns for Developing a Cross-product Cross-version App
Practical Patterns for Developing a Cross-product Cross-version AppPractical Patterns for Developing a Cross-product Cross-version App
Practical Patterns for Developing a Cross-product Cross-version AppAtlassian
 
Moving from app services to azure functions
Moving from app services to azure functionsMoving from app services to azure functions
Moving from app services to azure functionsMichelangelo van Dam
 
Smart Enterprise Application Integration with Apache Camel
Smart Enterprise Application Integration with Apache Camel Smart Enterprise Application Integration with Apache Camel
Smart Enterprise Application Integration with Apache Camel Kai Wähner
 
GraphQL Munich Meetup #1 - How We Use GraphQL At Commercetools
GraphQL Munich Meetup #1 - How We Use GraphQL At CommercetoolsGraphQL Munich Meetup #1 - How We Use GraphQL At Commercetools
GraphQL Munich Meetup #1 - How We Use GraphQL At CommercetoolsNicola Molinari
 
Developing for the Atlassian Ecosystem
Developing for the Atlassian EcosystemDeveloping for the Atlassian Ecosystem
Developing for the Atlassian EcosystemAlex Henderson
 
Rakuten Ichiba_Rakuten Technology Conference 2016
Rakuten Ichiba_Rakuten Technology Conference 2016Rakuten Ichiba_Rakuten Technology Conference 2016
Rakuten Ichiba_Rakuten Technology Conference 2016Rakuten Group, Inc.
 
Lwc presentation
Lwc presentationLwc presentation
Lwc presentationNithesh N
 
Continuous Integration and Delivery at Shapeways (Matt Boyle)
Continuous Integration and Delivery at Shapeways (Matt Boyle)Continuous Integration and Delivery at Shapeways (Matt Boyle)
Continuous Integration and Delivery at Shapeways (Matt Boyle)Nordic APIs
 
GraphQL across the stack: How everything fits together
GraphQL across the stack: How everything fits togetherGraphQL across the stack: How everything fits together
GraphQL across the stack: How everything fits togetherSashko Stubailo
 
A Day in the Life of a HipChat Developer
A Day in the Life of a HipChat DeveloperA Day in the Life of a HipChat Developer
A Day in the Life of a HipChat DeveloperAtlassian
 
10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing
10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing
10x Test Coverage, Less Drama: Shift Left Functional & Performance TestingSauce Labs
 
Forge App Showcase
Forge App ShowcaseForge App Showcase
Forge App ShowcaseAtlassian
 
Postman Galaxy Tour: San Francisco - Workshop Presentation
Postman Galaxy Tour: San Francisco -  Workshop PresentationPostman Galaxy Tour: San Francisco -  Workshop Presentation
Postman Galaxy Tour: San Francisco - Workshop PresentationPostman
 
Emulators as an Emerging Best Practice for API providers
Emulators as an Emerging Best Practice for API providersEmulators as an Emerging Best Practice for API providers
Emulators as an Emerging Best Practice for API providersPostman
 

What's hot (20)

Episode 10 - External Services in Salesforce
Episode 10 - External Services in SalesforceEpisode 10 - External Services in Salesforce
Episode 10 - External Services in Salesforce
 
Declaring Server App Components in Pure Java
Declaring Server App Components in Pure JavaDeclaring Server App Components in Pure Java
Declaring Server App Components in Pure Java
 
Practical Patterns for Developing a Cross-product Cross-version App
Practical Patterns for Developing a Cross-product Cross-version AppPractical Patterns for Developing a Cross-product Cross-version App
Practical Patterns for Developing a Cross-product Cross-version App
 
GraphQL.net
GraphQL.netGraphQL.net
GraphQL.net
 
Moving from app services to azure functions
Moving from app services to azure functionsMoving from app services to azure functions
Moving from app services to azure functions
 
Smart Enterprise Application Integration with Apache Camel
Smart Enterprise Application Integration with Apache Camel Smart Enterprise Application Integration with Apache Camel
Smart Enterprise Application Integration with Apache Camel
 
Actviti bpm framework 1.0
Actviti bpm framework 1.0Actviti bpm framework 1.0
Actviti bpm framework 1.0
 
GraphQL Munich Meetup #1 - How We Use GraphQL At Commercetools
GraphQL Munich Meetup #1 - How We Use GraphQL At CommercetoolsGraphQL Munich Meetup #1 - How We Use GraphQL At Commercetools
GraphQL Munich Meetup #1 - How We Use GraphQL At Commercetools
 
Developing for the Atlassian Ecosystem
Developing for the Atlassian EcosystemDeveloping for the Atlassian Ecosystem
Developing for the Atlassian Ecosystem
 
Rakuten Ichiba_Rakuten Technology Conference 2016
Rakuten Ichiba_Rakuten Technology Conference 2016Rakuten Ichiba_Rakuten Technology Conference 2016
Rakuten Ichiba_Rakuten Technology Conference 2016
 
Lwc presentation
Lwc presentationLwc presentation
Lwc presentation
 
Continuous Integration and Delivery at Shapeways (Matt Boyle)
Continuous Integration and Delivery at Shapeways (Matt Boyle)Continuous Integration and Delivery at Shapeways (Matt Boyle)
Continuous Integration and Delivery at Shapeways (Matt Boyle)
 
GraphQL across the stack: How everything fits together
GraphQL across the stack: How everything fits togetherGraphQL across the stack: How everything fits together
GraphQL across the stack: How everything fits together
 
GraphQL Europe Recap
GraphQL Europe RecapGraphQL Europe Recap
GraphQL Europe Recap
 
Android CD
Android CDAndroid CD
Android CD
 
A Day in the Life of a HipChat Developer
A Day in the Life of a HipChat DeveloperA Day in the Life of a HipChat Developer
A Day in the Life of a HipChat Developer
 
10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing
10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing
10x Test Coverage, Less Drama: Shift Left Functional & Performance Testing
 
Forge App Showcase
Forge App ShowcaseForge App Showcase
Forge App Showcase
 
Postman Galaxy Tour: San Francisco - Workshop Presentation
Postman Galaxy Tour: San Francisco -  Workshop PresentationPostman Galaxy Tour: San Francisco -  Workshop Presentation
Postman Galaxy Tour: San Francisco - Workshop Presentation
 
Emulators as an Emerging Best Practice for API providers
Emulators as an Emerging Best Practice for API providersEmulators as an Emerging Best Practice for API providers
Emulators as an Emerging Best Practice for API providers
 

Similar to TensorFlow 2.0 Changes Eager Execution Keras Primary API

Introduction to TensorFlow Lite
Introduction to TensorFlow Lite Introduction to TensorFlow Lite
Introduction to TensorFlow Lite Koan-Sin Tan
 
Commodified IaC using Terraform Cloud
Commodified IaC using Terraform CloudCommodified IaC using Terraform Cloud
Commodified IaC using Terraform CloudMarko Bevc
 
KUBEDAY - JAPAN 2022 - Building FaaS Platforms.pdf
KUBEDAY - JAPAN  2022 - Building FaaS Platforms.pdfKUBEDAY - JAPAN  2022 - Building FaaS Platforms.pdf
KUBEDAY - JAPAN 2022 - Building FaaS Platforms.pdfMauricio (Salaboy) Salatino
 
TensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.jsTensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.jsStijn Decubber
 
Full Stack DevOps - Ready To Go
Full Stack DevOps - Ready To GoFull Stack DevOps - Ready To Go
Full Stack DevOps - Ready To GoKallex
 
Paving the way with Jakarta EE and apache TomEE at cloudconferenceday
Paving the way with Jakarta EE and apache TomEE at cloudconferencedayPaving the way with Jakarta EE and apache TomEE at cloudconferenceday
Paving the way with Jakarta EE and apache TomEE at cloudconferencedayCésar Hernández
 
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0César Hernández
 
DITA Quick Start Webinar Series: Getting Started with the DITA Open Toolkit
DITA Quick Start Webinar Series: Getting Started with the DITA Open ToolkitDITA Quick Start Webinar Series: Getting Started with the DITA Open Toolkit
DITA Quick Start Webinar Series: Getting Started with the DITA Open ToolkitSuite Solutions
 
VA Smalltalk Update
VA Smalltalk UpdateVA Smalltalk Update
VA Smalltalk UpdateESUG
 
Kubernetes Java Operator
Kubernetes Java OperatorKubernetes Java Operator
Kubernetes Java OperatorAnthony Dahanne
 
Office add ins community call-January 2019
Office add ins community call-January 2019Office add ins community call-January 2019
Office add ins community call-January 2019Microsoft 365 Developer
 
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...Tasktop
 

Similar to TensorFlow 2.0 Changes Eager Execution Keras Primary API (20)

Introduction to TensorFlow Lite
Introduction to TensorFlow Lite Introduction to TensorFlow Lite
Introduction to TensorFlow Lite
 
Commodified IaC using Terraform Cloud
Commodified IaC using Terraform CloudCommodified IaC using Terraform Cloud
Commodified IaC using Terraform Cloud
 
Stackato
StackatoStackato
Stackato
 
Stackato v6
Stackato v6Stackato v6
Stackato v6
 
KUBEDAY - JAPAN 2022 - Building FaaS Platforms.pdf
KUBEDAY - JAPAN  2022 - Building FaaS Platforms.pdfKUBEDAY - JAPAN  2022 - Building FaaS Platforms.pdf
KUBEDAY - JAPAN 2022 - Building FaaS Platforms.pdf
 
TensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.jsTensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.js
 
Full Stack DevOps - Ready To Go
Full Stack DevOps - Ready To GoFull Stack DevOps - Ready To Go
Full Stack DevOps - Ready To Go
 
Paving the way with Jakarta EE and apache TomEE at cloudconferenceday
Paving the way with Jakarta EE and apache TomEE at cloudconferencedayPaving the way with Jakarta EE and apache TomEE at cloudconferenceday
Paving the way with Jakarta EE and apache TomEE at cloudconferenceday
 
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0
Pavimentando el Camino con Jakarta EE 9 y Apache TomEE 9.0.0
 
DITA Quick Start Webinar Series: Getting Started with the DITA Open Toolkit
DITA Quick Start Webinar Series: Getting Started with the DITA Open ToolkitDITA Quick Start Webinar Series: Getting Started with the DITA Open Toolkit
DITA Quick Start Webinar Series: Getting Started with the DITA Open Toolkit
 
Stackato v4
Stackato v4Stackato v4
Stackato v4
 
VA Smalltalk Update
VA Smalltalk UpdateVA Smalltalk Update
VA Smalltalk Update
 
CATzure Azure Functions
CATzure Azure FunctionsCATzure Azure Functions
CATzure Azure Functions
 
Kubernetes Java Operator
Kubernetes Java OperatorKubernetes Java Operator
Kubernetes Java Operator
 
Netflix MSA and Pivotal
Netflix MSA and PivotalNetflix MSA and Pivotal
Netflix MSA and Pivotal
 
Stackato v2
Stackato v2Stackato v2
Stackato v2
 
Stackato v3
Stackato v3Stackato v3
Stackato v3
 
Office add ins community call-January 2019
Office add ins community call-January 2019Office add ins community call-January 2019
Office add ins community call-January 2019
 
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...
A Customer Success Journey Moving From Tasktop Sync to Tasktop Integration Hu...
 
Stackato v5
Stackato v5Stackato v5
Stackato v5
 

More from Francesco Mosconi

Python for Machine Learning and Deep Learning
Python for Machine Learning and Deep LearningPython for Machine Learning and Deep Learning
Python for Machine Learning and Deep LearningFrancesco Mosconi
 
Intro to deep learning Python Meetup
Intro to deep learning Python MeetupIntro to deep learning Python Meetup
Intro to deep learning Python MeetupFrancesco Mosconi
 
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018Francesco Mosconi
 
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...Francesco Mosconi
 
Machine Learning: Techniques, Best Practices and Practical Application
Machine Learning: Techniques, Best Practices and Practical ApplicationMachine Learning: Techniques, Best Practices and Practical Application
Machine Learning: Techniques, Best Practices and Practical ApplicationFrancesco Mosconi
 
Python libraries for Machine Learning and Deep Learning
Python libraries for Machine Learning and Deep LearningPython libraries for Machine Learning and Deep Learning
Python libraries for Machine Learning and Deep LearningFrancesco Mosconi
 
Intro to scikit learn may 2017
Intro to scikit learn may 2017Intro to scikit learn may 2017
Intro to scikit learn may 2017Francesco Mosconi
 
Intro to Deep Learning April 2017
Intro to Deep Learning April 2017Intro to Deep Learning April 2017
Intro to Deep Learning April 2017Francesco Mosconi
 

More from Francesco Mosconi (10)

Python for Machine Learning and Deep Learning
Python for Machine Learning and Deep LearningPython for Machine Learning and Deep Learning
Python for Machine Learning and Deep Learning
 
Image Similarity Search
Image Similarity SearchImage Similarity Search
Image Similarity Search
 
Intro to deep learning Python Meetup
Intro to deep learning Python MeetupIntro to deep learning Python Meetup
Intro to deep learning Python Meetup
 
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018
Advanced Keras / Global Artificial Intelligence Conference / Santa Clara 2018
 
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...
Introduction to Keras / Global Artificial Intelligence Conference / Santa Cla...
 
Advanced Keras
Advanced KerasAdvanced Keras
Advanced Keras
 
Machine Learning: Techniques, Best Practices and Practical Application
Machine Learning: Techniques, Best Practices and Practical ApplicationMachine Learning: Techniques, Best Practices and Practical Application
Machine Learning: Techniques, Best Practices and Practical Application
 
Python libraries for Machine Learning and Deep Learning
Python libraries for Machine Learning and Deep LearningPython libraries for Machine Learning and Deep Learning
Python libraries for Machine Learning and Deep Learning
 
Intro to scikit learn may 2017
Intro to scikit learn may 2017Intro to scikit learn may 2017
Intro to scikit learn may 2017
 
Intro to Deep Learning April 2017
Intro to Deep Learning April 2017Intro to Deep Learning April 2017
Intro to Deep Learning April 2017
 

Recently uploaded

Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdfQucHHunhnh
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Disha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfDisha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfchloefrazer622
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAssociation for Project Management
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docxPoojaSen20
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...Sapna Thakur
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 

Recently uploaded (20)

Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Disha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdfDisha NEET Physics Guide for classes 11 and 12.pdf
Disha NEET Physics Guide for classes 11 and 12.pdf
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 

TensorFlow 2.0 Changes Eager Execution Keras Primary API

  • 1. Catalit LLC TENSORFLOW 2.0 AND KERAS Francesco Mosconi Data Weekends Catalit Data Science Zero to Deep Learning
  • 2. Catalit LLC ABOUT US www.catalit.com Data Weekends Catalit Data Science Zero to Deep Learning www.dataweekends.com bootcamp.zerotodeeplearning.com
  • 3. Catalit LLC TODAY • Changes inTensorflow 2.0 • How it differsTensorflow 1.* • How it differs from keras.io
  • 4. Catalit LLC SOMETIME IN AUGUST 2018 …
  • 5. Catalit LLC KEY POINTS • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity withTensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages
  • 6. Catalit LLC DEV SUMMIT (MARCH 6-7) https://www.tensorflow.org/alpha
  • 8. Catalit LLC TODAY • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity withTensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages
  • 9. Catalit LLC KEY POINTS • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity withTensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages
  • 10. Catalit LLC PUBLIC 2.0 DESIGN PROCESS https://groups.google.com/a/tensorflow.org/forum/#!forum/discuss https://github.com/tensorflow/community/blob/master/governance/TF-RFCs.md https://github.com/tensorflow/community/tree/master/rfcs
  • 11. Catalit LLC WHAT IT MEANS FORYOU • Final release expected in summer 2019 • If you’re aTF 1.x developer
 => start updating your code as soon as RFPs are accepted • There is a conversion tool from 1.x to 2.0 (won’t be perfect, but hey…)
  • 12. Catalit LLC CONVERSION SCRIPT • https://www.tensorflow.org/alpha/guide/upgrade • tf_upgrade_v2 --infile tensorfoo.py --outfile tensorfoo-upgraded.py
  • 13. Catalit LLC KEY POINTS • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity withTensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages
  • 14. Catalit LLC EAGER EXECUTION • Available since late 2017 • Following Pytorch and Chainer • Imperative • Define-by-run • No static graph & session
  • 15. Catalit LLC EAGER EXECUTION • Faster debugging with Python tools • Dynamic models with Python control flow • Support for custom and higher-order gradients
  • 16. Catalit LLC IS GRAPH GOING AWAY? • No, you can still define models using the traditional static graph • tf.compat.v1.disable_eager_execution()
  • 21. Catalit LLC WHAT IT MEANS FORYOU • Debug like Numpy, scale likeTensorflow • Easier to build and test custom models • Slower than static graph mode
  • 22. Catalit LLC KEY POINTS • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity withTensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages
  • 23. Catalit LLC MODEL APIS INTF 1.X • tf.core • tf.layers • tf.keras.layers • tf.estimator.Estimator • tf.contrib.learn.Estimator • …
  • 24. Catalit LLC MODEL APIS INTF 2.0 • tf.core ====> stripped down • tf.layers ====> Deprecated • tf.keras ====> Primary API • tf.estimator.Estimator ====> API same, implementation changed to tf.keras • tf.contrib.learn.Estimator ====> Deprecated • …
  • 25. Catalit LLC MODEL APIS INTF 2.0 • tf.core ====> stripped down • tf.layers ====> Deprecated • tf.keras ====> Primary API • tf.estimator.Estimator ====> API same, implementation changed to tf.keras • tf.contrib.learn.Estimator ====> Deprecated • …
  • 26. Catalit LLC TF.KERAS • What is it? • How does it work? • How does it differ from keras.io implementation?
  • 27. Catalit LLC WHAT IS KERAS? https://towardsdatascience.com/deep-learning-framework-power-scores-2018-23607ddf297a
  • 28. Catalit LLC WHAT IS KERAS • Keras is an API specification to design deep learning model • https://keras.io/
 => independent reference implementation (usingTF or CNTK as backend) • tf.keras
 =>Tensorflow implementation of the same API spec • Other frameworks implement some version of the API
  • 29. Catalit LLC MODEL DEFINITION IN KERAS • Sequential API • Functional API • Model API
  • 34. Catalit LLC DIFFERENCES • Support for Eager Execution • tf.dataVS python data generators • Model Exporting • Compatible with Feature Columns • Compatible with Estimators
  • 35. Catalit LLC KEY POINTS • Public 2.0 design process • Eager execution • Remove deprecated APIs & reduce the amount of duplication • Compatibility and continuity with Tensorflow 1.x • Compatibility with 1.x exported models • No more tf.contrib • More platforms and languages https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8