SlideShare a Scribd company logo
1 of 28
Machines Can Learn - a Practical Take
on Machine Intelligence Using Spring
Cloud Data Flow and TensorFlow
By Christian Tzolov
@christzolov
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Disclaimer
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Safe Harbor Statement
The following is intended to outline the general direction of Pivotal's offerings. It is intended for information
purposes only and may not be incorporated into any contract. Any information regarding pre-release of Pivotal
offerings, future updates or other planned modifications is subject to ongoing evaluation by Pivotal and is subject to
change. This information is provided without warranty or any kind, express or implied, and is not a commitment to
deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions regarding
Pivotal's offerings. These purchasing decisions should only be based on features currently available. The
development, release, and timing of any features or functionality described for Pivotal's offerings in this
presentation remain at the sole discretion of Pivotal. Pivotal has no obligation to update forward looking
information in this presentation.
3
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Does It Matter?
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Rise of the machines
ā€¢ Machine Learning brings unprecedented
abilities to the Software Engineering field
ā€¢ Provides different way to reason about
problems
ā€¢ Solves un-programmable tasks
5
ā€¢ There is a technological Gap ( e.g. BLAS/CPU, CUDA/GPU, C++/Python)
ā€¢ And cultural differences ļŠ
ā€¢ How Machine Learning can enable us deliver richer business solutions?
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Real-Time Predictions with TensorFlow and Spring
Cloud Data Flow (SCDF)
Focus is on
ā€¢ Supervised, Deep Learning (DL)
ā€¢ TensorFlow and DL4J as DL toolkits
ā€¢ Model Inference (e.g. evaluation, prediction)
ā€¢ (Near) Real-Time - Streaming
ā€¢ Java and Spring
6
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
How to Build SCDF applications like
7
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Can Machine Learn?
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Classical Programming
9
Classical
Programming
Rules
Data
Answers
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Machine Learning Paradigm
10
Machine
Learning
Rulesā€™
Data*
Answers*
* Historical, annotated Datasets
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
ML Lifecycle
11
Model Inference
Output Predictions
MODEL
(e.g. Rules)
New Data
Model Training
Annotated answers
Historical Data
Offline Online (Production)
Software Engineering &
Ops
Data Science
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Remote Server
Model Serving & Embedding
12
Data Source
HTTP/REST, RPC
Processor(s)
Data Sink
Data Source Processor(s)
Model
Data Sink
Runtime
Model
Remote
Serving
In-Pipeline Embedded
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Deep Learning Inference with Java
ā€¢ Deep Learning Java Runtime
ā€¢ Portable Models
13
DL Java Runtime
Input Data
Output
Predictions
Pre-trained Model
(e.g. Rules)
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Deep Learning Frameworks
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Deep Learning Frameworks
ā€¢ Tensorflow (Google)
ā€¢ PyTorch
ā€¢ CNTK (Microsoft)
ā€¢ Caffe2 (Facebook)
ā€¢ MXNet (Amazon)
ā€¢ DeepLearning4J
ā€¢ Keras
15
Deep Learning Java Runtime
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Real-Time Model Evaluation with
Spring Cloud Data Flow
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Transport Middleware
Stream A
Spring Cloud Data Flow (SCDF)
Toolkit for building data integration, real-time, and batch data processing pipelines
ā€¢ Multi-platform support (PCF, Kubernetes)
ā€¢ Comprehensive app lifecycle (Skipper)
ā€¢ Pipes & Filters like DSL: Source | Processor ā€¦ | Sink
Source Processor Processor Sink
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Localizing and identifying multiple objects in a single image
ā€¢ TF Object Detection API: http://bit.ly/tensorflow-object-detection-api
ā€¢ Pre-trained models: http://bit.ly/object-detection-api-model-zoo
ā€¢ Object Detection Processor Doc: http://bit.ly/scdf-object-detection-processor
ā€¢ Blog: https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream
Object Detection Processor
file --directory=ā€˜/tmp/scdf/od/inputā€™
| object-detection
--mode=header
--model='file:/model.pbā€™
--labels='file:/label_map.pbtxtā€™
| image-viewer
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
TensorFlow SCDF Processor
20
TensorFlowService
Message
payload
headers
OutputConverter
InputConverter
Message
payload
headers
Map<String, Tensor>
Load from file:// , http://, classpath://
TensorFlow
Build/Train/Export
TensorFlow
Runtime
TF Model
Offline
Real
Time
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Object Detection - RT Demo
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Available TensorFlow Processors
ā€¢ Object Detection ā€“ TF Object Detection API: [12] [13]
ā€¢ Instance Segmentation, TF Object Detection API: [11]
ā€¢ Semantic Segmentation, TF API: [8][9][10]
ā€¢ Image Recognition (Inception V3), TensorFlow API: [7]
ā€¢ Pose Estimation (OpenPose), TensorFlow API [5], [6]
ā€¢ Twitter Sentiment Analysis, TensorFlow API: [4]
ā€¢ Face Detection (MTCNN), ND4J,
ND4J-Tensorflow, JavaCV: [1], [2]
ā€¢ Face Recognition (FaceNet), TensorFlow API: [3]
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Quick Starters
ā€¢ TensorFlow Spring Cloud Stream App Starters:
https://github.com/spring-cloud-stream-app-starters/tensorflow
ā€¢ Computer Vision Projects (experimental):
https://github.com/tzolov/computer-vision
ā€¢ SCDF TensorFlow Demos (Docker):
https://github.com/tzolov/scdf-tensorflow-demos
ā€¢ Real-time Object-Detection With Spring Cloud Stream
https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream
ā€¢ Real-time Object-Detection With Spring Cloud Stream
https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream
ā€¢ Real-Time Multi-Person, Human Pose Estimation with Spring Cloud Data Flow
and TensorFlow
http://bit.ly/scdf-pose-estimationn-blog
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Conclusions
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Convinced?
ā€¢ Data Science and Deep Learning mature at a rapid pace
ā€¢ Pivotal is committed to make them easily accessible for Spring/Java developers.
ā€¢ Way to start: Check the TensorFlow processors for Spring Cloud Data Flow
ā€¢ You feedback is appreciated!
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Next
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
Unofficial agenda
ā€¢ Top level TensorFlow (or DL) project ā€“ move the utilities and existing
implementations (such as Image Recognition, Object Detection, Sentiment
Analysis) out of SCSt into a top level, generic projects.
ā€¢ Use with Spring Cloud Stream, Spring Cloud Function, Spring Cloud Batch
ā€¢ Research ā€œTransfer Learningā€ possibilities
ā€¢ Evaluate Deeplearning4J, ND4J as Runtime alternative
ā€¢ ONNX Runtime to use models from other DL frameworks
ā€¢ REST, Spring Boot as remote DL serving application
31
Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons
Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/
References
[1] Face Detection Lib: https://github.com/tzolov/mtcnn-java
[2] Face Detection Processor: https://github.com/tzolov/computer-vision/blob/master/spring-cloud-starter-stream-processor-face-detection-mtcnn
[3] Face Recognition: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-face-recognition
[4] Twitter Sentiment Analysis: https://github.com/spring-cloud-stream-app-starters/tensorflow/blob/master/spring-cloud-starter-stream-processor-twitter-sentiment
[5] Pose Estimation Processor: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-pose-estimation
[6] Pose Estimation Blog: https://content.pivotal.io/blog/making-data-science-accessible-to-developers-real-time-multi-person-human-pose-estimation-with-spring-
cloud-data-flow-and-tensorflow
[7] Image Recognition: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-image-recognition
[8] Semantic Segmentation Blog: https://goo.gl/dtwAfo
[9] Semantic Segmentation - Java2D: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-semantic-segmentation
[10] Semantic Segmentation - JavaCV: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-semantic-segmentation-cv
[11] Instance Segmentation - Object Detection Processor with Masks: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-
stream-processor-object-detection
[12] Object Detection Processor: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-object-detection
[13] Object Detection Blog: https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream
32
> Stay Connected.

More Related Content

Similar to Machines Can Learn - a Practical Take on Machine Intelligence Using Spring Cloud Data Flow and TensorFlow

Automation and Culture Changes for 40M Subscriber Platform Operation
Automation and Culture Changes for 40M Subscriber Platform OperationAutomation and Culture Changes for 40M Subscriber Platform Operation
Automation and Culture Changes for 40M Subscriber Platform OperationVMware Tanzu
Ā 
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...VMware Tanzu
Ā 
Building a Data Exchange with Spring Cloud Data Flow
Building a Data Exchange with Spring Cloud Data FlowBuilding a Data Exchange with Spring Cloud Data Flow
Building a Data Exchange with Spring Cloud Data FlowVMware Tanzu
Ā 
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...VMware Tanzu
Ā 
SpringOne2GX 2014 Splunk Presentation
SpringOne2GX 2014 Splunk PresentationSpringOne2GX 2014 Splunk Presentation
SpringOne2GX 2014 Splunk PresentationDamien Dallimore
Ā 
Containerizing a Data Warehouse for Kubernetes
Containerizing a Data Warehouse for KubernetesContainerizing a Data Warehouse for Kubernetes
Containerizing a Data Warehouse for KubernetesVMware Tanzu
Ā 
PCF 2.3: A First Look
PCF 2.3: A First LookPCF 2.3: A First Look
PCF 2.3: A First LookVMware Tanzu
Ā 
Implementing a highly scalable stock prediction system with R, Geode, SpringX...
Implementing a highly scalable stock prediction system with R, Geode, SpringX...Implementing a highly scalable stock prediction system with R, Geode, SpringX...
Implementing a highly scalable stock prediction system with R, Geode, SpringX...William Markito Oliveira
Ā 
SpringOnePlatform2017 recap
SpringOnePlatform2017 recapSpringOnePlatform2017 recap
SpringOnePlatform2017 recapminseok kim
Ā 
riffing on Knative - Scott Andrews
riffing on Knative - Scott Andrewsriffing on Knative - Scott Andrews
riffing on Knative - Scott AndrewsVMware Tanzu
Ā 
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-In
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-InSteeltoe: Develop .NET Microservices Without Cloud Platform Lock-In
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-InVMware Tanzu
Ā 
P to V to C: The Value of Bringing ā€œEverythingā€ to Containers
P to V to C: The Value of Bringing ā€œEverythingā€ to ContainersP to V to C: The Value of Bringing ā€œEverythingā€ to Containers
P to V to C: The Value of Bringing ā€œEverythingā€ to ContainersVMware Tanzu
Ā 
Caching for Microservives - Introduction to Pivotal Cloud Cache
Caching for Microservives - Introduction to Pivotal Cloud CacheCaching for Microservives - Introduction to Pivotal Cloud Cache
Caching for Microservives - Introduction to Pivotal Cloud CacheVMware Tanzu
Ā 
Ratpack - SpringOne2GX 2015
Ratpack - SpringOne2GX 2015Ratpack - SpringOne2GX 2015
Ratpack - SpringOne2GX 2015Daniel Woods
Ā 
Fast 5 Things You Can Do Now to Get Ready for the Cloud
Fast 5 Things You Can Do Now to Get Ready for the CloudFast 5 Things You Can Do Now to Get Ready for the Cloud
Fast 5 Things You Can Do Now to Get Ready for the CloudVMware Tanzu
Ā 
Building a Secure App with Google Polymer and Java / Spring
Building a Secure App with Google Polymer and Java / SpringBuilding a Secure App with Google Polymer and Java / Spring
Building a Secure App with Google Polymer and Java / Springsdeeg
Ā 
Spring Tools 4 - Eclipse and Beyond
Spring Tools 4 - Eclipse and BeyondSpring Tools 4 - Eclipse and Beyond
Spring Tools 4 - Eclipse and BeyondVMware Tanzu
Ā 
Data Driven Action : A Primer on Data Science
Data Driven Action : A Primer on Data ScienceData Driven Action : A Primer on Data Science
Data Driven Action : A Primer on Data ScienceSrivatsan Ramanujam
Ā 
Developer Secure Containers for the Cyberspace Battlefield
Developer Secure Containers for the Cyberspace BattlefieldDeveloper Secure Containers for the Cyberspace Battlefield
Developer Secure Containers for the Cyberspace BattlefieldVMware Tanzu
Ā 

Similar to Machines Can Learn - a Practical Take on Machine Intelligence Using Spring Cloud Data Flow and TensorFlow (20)

Automation and Culture Changes for 40M Subscriber Platform Operation
Automation and Culture Changes for 40M Subscriber Platform OperationAutomation and Culture Changes for 40M Subscriber Platform Operation
Automation and Culture Changes for 40M Subscriber Platform Operation
Ā 
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...
Iterating For Success: A Case Study in Remote Paired Programming, The Evoluti...
Ā 
S1P: Spring Cloud on PKS
S1P: Spring Cloud on PKSS1P: Spring Cloud on PKS
S1P: Spring Cloud on PKS
Ā 
Building a Data Exchange with Spring Cloud Data Flow
Building a Data Exchange with Spring Cloud Data FlowBuilding a Data Exchange with Spring Cloud Data Flow
Building a Data Exchange with Spring Cloud Data Flow
Ā 
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...
Buckets, Funnels, Mobs and Cats or: How We Learned to Love Scaling Apps To Th...
Ā 
SpringOne2GX 2014 Splunk Presentation
SpringOne2GX 2014 Splunk PresentationSpringOne2GX 2014 Splunk Presentation
SpringOne2GX 2014 Splunk Presentation
Ā 
Containerizing a Data Warehouse for Kubernetes
Containerizing a Data Warehouse for KubernetesContainerizing a Data Warehouse for Kubernetes
Containerizing a Data Warehouse for Kubernetes
Ā 
PCF 2.3: A First Look
PCF 2.3: A First LookPCF 2.3: A First Look
PCF 2.3: A First Look
Ā 
Implementing a highly scalable stock prediction system with R, Geode, SpringX...
Implementing a highly scalable stock prediction system with R, Geode, SpringX...Implementing a highly scalable stock prediction system with R, Geode, SpringX...
Implementing a highly scalable stock prediction system with R, Geode, SpringX...
Ā 
SpringOnePlatform2017 recap
SpringOnePlatform2017 recapSpringOnePlatform2017 recap
SpringOnePlatform2017 recap
Ā 
riffing on Knative - Scott Andrews
riffing on Knative - Scott Andrewsriffing on Knative - Scott Andrews
riffing on Knative - Scott Andrews
Ā 
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-In
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-InSteeltoe: Develop .NET Microservices Without Cloud Platform Lock-In
Steeltoe: Develop .NET Microservices Without Cloud Platform Lock-In
Ā 
P to V to C: The Value of Bringing ā€œEverythingā€ to Containers
P to V to C: The Value of Bringing ā€œEverythingā€ to ContainersP to V to C: The Value of Bringing ā€œEverythingā€ to Containers
P to V to C: The Value of Bringing ā€œEverythingā€ to Containers
Ā 
Caching for Microservives - Introduction to Pivotal Cloud Cache
Caching for Microservives - Introduction to Pivotal Cloud CacheCaching for Microservives - Introduction to Pivotal Cloud Cache
Caching for Microservives - Introduction to Pivotal Cloud Cache
Ā 
Ratpack - SpringOne2GX 2015
Ratpack - SpringOne2GX 2015Ratpack - SpringOne2GX 2015
Ratpack - SpringOne2GX 2015
Ā 
Fast 5 Things You Can Do Now to Get Ready for the Cloud
Fast 5 Things You Can Do Now to Get Ready for the CloudFast 5 Things You Can Do Now to Get Ready for the Cloud
Fast 5 Things You Can Do Now to Get Ready for the Cloud
Ā 
Building a Secure App with Google Polymer and Java / Spring
Building a Secure App with Google Polymer and Java / SpringBuilding a Secure App with Google Polymer and Java / Spring
Building a Secure App with Google Polymer and Java / Spring
Ā 
Spring Tools 4 - Eclipse and Beyond
Spring Tools 4 - Eclipse and BeyondSpring Tools 4 - Eclipse and Beyond
Spring Tools 4 - Eclipse and Beyond
Ā 
Data Driven Action : A Primer on Data Science
Data Driven Action : A Primer on Data ScienceData Driven Action : A Primer on Data Science
Data Driven Action : A Primer on Data Science
Ā 
Developer Secure Containers for the Cyberspace Battlefield
Developer Secure Containers for the Cyberspace BattlefieldDeveloper Secure Containers for the Cyberspace Battlefield
Developer Secure Containers for the Cyberspace Battlefield
Ā 

Recently uploaded

CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE9953056974 Low Rate Call Girls In Saket, Delhi NCR
Ā 
%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Harare%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Hararemasabamasaba
Ā 
Harnessing ChatGPT - Elevating Productivity in Today's Agile Environment
Harnessing ChatGPT  - Elevating Productivity in Today's Agile EnvironmentHarnessing ChatGPT  - Elevating Productivity in Today's Agile Environment
Harnessing ChatGPT - Elevating Productivity in Today's Agile EnvironmentVictorSzoltysek
Ā 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfkalichargn70th171
Ā 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...masabamasaba
Ā 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfonteinmasabamasaba
Ā 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
Ā 
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2
Ā 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...SelfMade bd
Ā 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplatePresentation.STUDIO
Ā 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...masabamasaba
Ā 
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...Steffen Staab
Ā 
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļø
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļøcall girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļø
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļøDelhi Call girls
Ā 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...masabamasaba
Ā 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...masabamasaba
Ā 
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Bert Jan Schrijver
Ā 
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park masabamasaba
Ā 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park masabamasaba
Ā 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
Ā 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in sowetomasabamasaba
Ā 

Recently uploaded (20)

CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
Ā 
%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Harare%in Harare+277-882-255-28 abortion pills for sale in Harare
%in Harare+277-882-255-28 abortion pills for sale in Harare
Ā 
Harnessing ChatGPT - Elevating Productivity in Today's Agile Environment
Harnessing ChatGPT  - Elevating Productivity in Today's Agile EnvironmentHarnessing ChatGPT  - Elevating Productivity in Today's Agile Environment
Harnessing ChatGPT - Elevating Productivity in Today's Agile Environment
Ā 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Ā 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
Ā 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
Ā 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
Ā 
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
Ā 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Ā 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation Template
Ā 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
Ā 
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data SpacesĀ - and Epistemic Querying of RDF-...
Ā 
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļø
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļøcall girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļø
call girls in Vaishali (Ghaziabad) šŸ” >ą¼’8448380779 šŸ” genuine Escort Service šŸ”āœ”ļøāœ”ļø
Ā 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
Ā 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
Ā 
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Ā 
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
Ā 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
Ā 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
Ā 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto
Ā 

Machines Can Learn - a Practical Take on Machine Intelligence Using Spring Cloud Data Flow and TensorFlow

  • 1. Machines Can Learn - a Practical Take on Machine Intelligence Using Spring Cloud Data Flow and TensorFlow By Christian Tzolov @christzolov
  • 2. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Disclaimer
  • 3. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Safe Harbor Statement The following is intended to outline the general direction of Pivotal's offerings. It is intended for information purposes only and may not be incorporated into any contract. Any information regarding pre-release of Pivotal offerings, future updates or other planned modifications is subject to ongoing evaluation by Pivotal and is subject to change. This information is provided without warranty or any kind, express or implied, and is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions regarding Pivotal's offerings. These purchasing decisions should only be based on features currently available. The development, release, and timing of any features or functionality described for Pivotal's offerings in this presentation remain at the sole discretion of Pivotal. Pivotal has no obligation to update forward looking information in this presentation. 3
  • 4. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Does It Matter?
  • 5. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Rise of the machines ā€¢ Machine Learning brings unprecedented abilities to the Software Engineering field ā€¢ Provides different way to reason about problems ā€¢ Solves un-programmable tasks 5 ā€¢ There is a technological Gap ( e.g. BLAS/CPU, CUDA/GPU, C++/Python) ā€¢ And cultural differences ļŠ ā€¢ How Machine Learning can enable us deliver richer business solutions?
  • 6. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Real-Time Predictions with TensorFlow and Spring Cloud Data Flow (SCDF) Focus is on ā€¢ Supervised, Deep Learning (DL) ā€¢ TensorFlow and DL4J as DL toolkits ā€¢ Model Inference (e.g. evaluation, prediction) ā€¢ (Near) Real-Time - Streaming ā€¢ Java and Spring 6
  • 7. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ How to Build SCDF applications like 7
  • 8. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Can Machine Learn?
  • 9. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Classical Programming 9 Classical Programming Rules Data Answers
  • 10. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Machine Learning Paradigm 10 Machine Learning Rulesā€™ Data* Answers* * Historical, annotated Datasets
  • 11. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ ML Lifecycle 11 Model Inference Output Predictions MODEL (e.g. Rules) New Data Model Training Annotated answers Historical Data Offline Online (Production) Software Engineering & Ops Data Science
  • 12. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Remote Server Model Serving & Embedding 12 Data Source HTTP/REST, RPC Processor(s) Data Sink Data Source Processor(s) Model Data Sink Runtime Model Remote Serving In-Pipeline Embedded
  • 13. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Deep Learning Inference with Java ā€¢ Deep Learning Java Runtime ā€¢ Portable Models 13 DL Java Runtime Input Data Output Predictions Pre-trained Model (e.g. Rules)
  • 14. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Deep Learning Frameworks
  • 15. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Deep Learning Frameworks ā€¢ Tensorflow (Google) ā€¢ PyTorch ā€¢ CNTK (Microsoft) ā€¢ Caffe2 (Facebook) ā€¢ MXNet (Amazon) ā€¢ DeepLearning4J ā€¢ Keras 15 Deep Learning Java Runtime
  • 16. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Real-Time Model Evaluation with Spring Cloud Data Flow
  • 17. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Transport Middleware Stream A Spring Cloud Data Flow (SCDF) Toolkit for building data integration, real-time, and batch data processing pipelines ā€¢ Multi-platform support (PCF, Kubernetes) ā€¢ Comprehensive app lifecycle (Skipper) ā€¢ Pipes & Filters like DSL: Source | Processor ā€¦ | Sink Source Processor Processor Sink
  • 18. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Localizing and identifying multiple objects in a single image ā€¢ TF Object Detection API: http://bit.ly/tensorflow-object-detection-api ā€¢ Pre-trained models: http://bit.ly/object-detection-api-model-zoo ā€¢ Object Detection Processor Doc: http://bit.ly/scdf-object-detection-processor ā€¢ Blog: https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream Object Detection Processor file --directory=ā€˜/tmp/scdf/od/inputā€™ | object-detection --mode=header --model='file:/model.pbā€™ --labels='file:/label_map.pbtxtā€™ | image-viewer
  • 19. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ TensorFlow SCDF Processor 20 TensorFlowService Message payload headers OutputConverter InputConverter Message payload headers Map<String, Tensor> Load from file:// , http://, classpath:// TensorFlow Build/Train/Export TensorFlow Runtime TF Model Offline Real Time
  • 20. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Object Detection - RT Demo
  • 21. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Available TensorFlow Processors ā€¢ Object Detection ā€“ TF Object Detection API: [12] [13] ā€¢ Instance Segmentation, TF Object Detection API: [11] ā€¢ Semantic Segmentation, TF API: [8][9][10] ā€¢ Image Recognition (Inception V3), TensorFlow API: [7] ā€¢ Pose Estimation (OpenPose), TensorFlow API [5], [6] ā€¢ Twitter Sentiment Analysis, TensorFlow API: [4] ā€¢ Face Detection (MTCNN), ND4J, ND4J-Tensorflow, JavaCV: [1], [2] ā€¢ Face Recognition (FaceNet), TensorFlow API: [3]
  • 22. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Quick Starters ā€¢ TensorFlow Spring Cloud Stream App Starters: https://github.com/spring-cloud-stream-app-starters/tensorflow ā€¢ Computer Vision Projects (experimental): https://github.com/tzolov/computer-vision ā€¢ SCDF TensorFlow Demos (Docker): https://github.com/tzolov/scdf-tensorflow-demos ā€¢ Real-time Object-Detection With Spring Cloud Stream https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream ā€¢ Real-time Object-Detection With Spring Cloud Stream https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream ā€¢ Real-Time Multi-Person, Human Pose Estimation with Spring Cloud Data Flow and TensorFlow http://bit.ly/scdf-pose-estimationn-blog
  • 23. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Conclusions
  • 24. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Convinced? ā€¢ Data Science and Deep Learning mature at a rapid pace ā€¢ Pivotal is committed to make them easily accessible for Spring/Java developers. ā€¢ Way to start: Check the TensorFlow processors for Spring Cloud Data Flow ā€¢ You feedback is appreciated!
  • 25. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Next
  • 26. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ Unofficial agenda ā€¢ Top level TensorFlow (or DL) project ā€“ move the utilities and existing implementations (such as Image Recognition, Object Detection, Sentiment Analysis) out of SCSt into a top level, generic projects. ā€¢ Use with Spring Cloud Stream, Spring Cloud Function, Spring Cloud Batch ā€¢ Research ā€œTransfer Learningā€ possibilities ā€¢ Evaluate Deeplearning4J, ND4J as Runtime alternative ā€¢ ONNX Runtime to use models from other DL frameworks ā€¢ REST, Spring Boot as remote DL serving application 31
  • 27. Unless otherwise indicated, these slides are Ā© 2013 -2018 Pivotal Software, Inc. and licensed under a Creative Commons Attribution-NonCommercial license: http://creativecommons.org/licenses/by -nc/3.0/ References [1] Face Detection Lib: https://github.com/tzolov/mtcnn-java [2] Face Detection Processor: https://github.com/tzolov/computer-vision/blob/master/spring-cloud-starter-stream-processor-face-detection-mtcnn [3] Face Recognition: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-face-recognition [4] Twitter Sentiment Analysis: https://github.com/spring-cloud-stream-app-starters/tensorflow/blob/master/spring-cloud-starter-stream-processor-twitter-sentiment [5] Pose Estimation Processor: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-pose-estimation [6] Pose Estimation Blog: https://content.pivotal.io/blog/making-data-science-accessible-to-developers-real-time-multi-person-human-pose-estimation-with-spring- cloud-data-flow-and-tensorflow [7] Image Recognition: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-image-recognition [8] Semantic Segmentation Blog: https://goo.gl/dtwAfo [9] Semantic Segmentation - Java2D: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-semantic-segmentation [10] Semantic Segmentation - JavaCV: https://github.com/tzolov/computer-vision/tree/master/spring-cloud-starter-stream-processor-semantic-segmentation-cv [11] Instance Segmentation - Object Detection Processor with Masks: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter- stream-processor-object-detection [12] Object Detection Processor: https://github.com/spring-cloud-stream-app-starters/tensorflow/tree/master/spring-cloud-starter-stream-processor-object-detection [13] Object Detection Blog: https://content.pivotal.io/blog/real-time-object-detection-with-spring-cloud-stream 32

Editor's Notes

  1. Machine and Deep Learning (ML/DL) have brought unprecedented abilities to the software engineering field. ML/DL allows you to reason about and to solve otherwise ā€œun-programmableā€ tasks such as computer-vision and language-processing. Thatā€™s why itā€™s so exciting to so many people. [1] (ML) is an approach for learning (data insights) without explicitly being programmed. [2] (DL) is a ML technique for learning features in data using Neural Networks. [3] TensorFlow is a DL framework for defining and executing computational graphs.
  2. Software engineers are trained to think logically and mathematically; We USE ASSERTIONS to prove properties of our program are correct
  3. With ML, the focus shifts from a mathematical science to a natural science: We're making observations about an uncertain world, running experiments, and Using STATISTICS, not logic, to analyze the results of the experiment. Machine learning changes the way you think about a problem. Software engineers are trained to think logically and mathematically; We use assertions to prove properties of our program are correct. With machine learning, the focus shifts from a mathematical science to a natural science: we're making observations about an uncertain world, running experiments, and using statistics, not logic, to analyze the results of the experiment.
  4. Trains Models on Historical Datasets - Data Science (Offline) Run Pre-Trained models for predictive analytics - Software Engineers (Real-Time) Separation of Concerns
  5. My goal is to show you how Spring Cloud Stream and Spring Cloud Data Flow can make this much easier for you.
  6. My goal is to show you how Spring Cloud Stream and Spring Cloud Data Flow can make this much easier for you.
  7. https://cv-tricks.com/deep-learning-2/tensorflow-or-pytorch/
  8. My goal is to show you how Spring Cloud Stream and Spring Cloud Data Flow can make this much easier for you.
  9. My goal is to show you how Spring Cloud Stream and Spring Cloud Data Flow can make this much easier for you.
  10. business applications can seem a daunting task for most developers. But by using the right tools that abstract away some of the complexities of the data science itself, like Spring Cloud Data Flow and TensorFlow, it doesnā€™t have to be.