SlideShare ist ein Scribd-Unternehmen logo
1 von 38
Downloaden Sie, um offline zu lesen
© Metta Innovations 2017
Jun 2017
An Introduction to Deep Learning
applied to Video Analytics
Aurélio Figueiredo
aurelio@mettainnovations.com.br
© Metta Innovations 2017
*Minimal Similarity Accumulation Attribute Using
Dimensionality Reduction with Feature Extraction.
In 78th European Association of Geoscientists and
Engineers (EAGE) Conference and Exhibition 2016
Metta Innovations
Great know-how in solutions applied
to Oil & Gas Industry
. Computational Geophysics
. Machine Learning / Deep Learning
. Automatic Seismic Interpretation
. ...
Autoencoder
EAGE 2016*
© Metta Innovations 2017
Metta Innovations
Expertise:
. Visualization
. Virtual and augmented reality
. High Performance Computing (HPC)
. Computer Vision
. Big Data
. Deep Learning
© Metta Innovations 2017
Agenda
Open Source Libraries
&
Examples and
Applications
What is Deep
Learning?
Why Deep Learning?
How to Use CNTK?
Code sample with CNTK
technology?
© Metta Innovations 2017
What is Deep Learning?
Deep learning (or deep structured learning or hierarchical learning):
1. Subfield of machine learning inspired by function of the brain
2. Artificial neural networks (ANNs) with many hidden layers
3. Suitable when target function is very complex (datasets REALLY large)
© Metta Innovations 2017
What is Deep Learning?
Deep Learning is the state-of-art approach to:
1. Computer Vision
2. Speech Recognition & Natural Language
Processing
3. Audio Recognition & Machine Translation
4. Social Network Filtering
5. Bioinformatics
In all these fields they produced results
comparable to or superior to human experts!
© Metta Innovations 2017
Why Deep Learning?
Automatically extracting features instead of manual extraction in feature engineering:
1. You don’t have to figure out the features ahead of time
2. We can use the same neural net approach for many different problems
Open sourcing is predominant in deep learning:
© Metta Innovations 2017
Why Deep Learning?
ImageNet Large Scale Visual Recognition Competition (ILSVRC*):
1. Evaluate algorithms for object detection at large scale
2. Measure progress of computer vision for large scale image
*http://www.image-net.org/challenges/LSVRC/
2010
Nec America
2011
Xerox
2012
AlexNet
2013
Clarify
2014
VGG
2014
GoogleNet
2015
MS ResNet
ImageNet Classification top-5 error (%)
30.0
20.0
10.0
0
28.2
25.8
16.4
11.7
7.3 3.6
6.7
© Metta Innovations 2017
Open Source
Libraries
© Metta Innovations 2017
Developed by Berkeley Vision and Learning Center
Extended by Facebook ( Caffe2 )
Mainly focusing on computer vision applications
Platforms:
● Linux
● macOS
● Windows
Supported programming languages:
● Python
● C++
● MATLAB
Caffe
© Metta Innovations 2017
Developed by Microsoft Research - Released Jan/2016
Platforms:
● Windows
● Linux
Supported programming languages:
● Python (versions supported are 2.7, 3.4, and 3.5)
● C++
● C#/.NET Managed
Microsoft Cognitive Toolkit
© Metta Innovations 2017
Developed by DMLC team (used on Amazon AWS)
Platforms:
● Linux
● macOS
● Windows
● Android/iOS
● AWS
MXNet
Supported programming languages:
● Python
● C++
● Scala
● R
● Perl
● MATLAB
© Metta Innovations 2017
Developed by Google - Released Nov/2015:
Platforms:
● Linux
● macOS
● Windows
● Android (new!)
Supported programming languages:
● Python
● C/C++
● Java
● Go
● R
Tensor Flow
© Metta Innovations 2017
Developed by University of Montreal
Platforms:
● Linux
● macOS
● Windows
Supported programming languages:
● Python
Theano
© Metta Innovations 2017
Developed by R Collobert, K Kavukcuoglu, C Farabet - Released Oct/2002
Platforms:
● Linux
● Mac OS X
● Windows
● Android
Supported programming languages:
● Lua
● LuaJIT
● C
● C++/OpenCL
Torch
© Metta Innovations 2017
Libraries Comparison
Single GPU - Benchmarking State-of-the-Art Deep Learning Software:
http://dlbench.comp.hkbu.edu.hk
FCN-8 AlexNet ResNet-50 LSTM-64
CNTK 0.037 0.040 0.207 0.122
Caffe 0.038 0.026 0.307 ---
TensorFlow 0.063 --- --- 0.144
Torch 0.048 0.033 0.188 0.194
Seconds per minibatch on G1080 (G980) GPU. Lower is better. *November 2016.
*Benchmarking State-of-the-Art Deep Learning Software:
http://dlbench.comp.hkbu.edu.hk
© Metta Innovations 2017
1 GPU
CNTK Theano TensorFlow Torch Caffe
Libraries Comparison
Speed comparison (samples / second). Higher is better. *December 2015.
80000
60000
40000
20000
0
1 x 4 GPUs 2 x 4 GPUs (8 GPUs)
*Benchmarking State-of-the-Art Deep Learning Software:
http://dlbench.comp.hkbu.edu.hk
Multiples GPU - Benchmarking State-of-the-Art Deep Learning Software:
http://dlbench.comp.hkbu.edu.hk
© Metta Innovations 2017
Using Microsoft Cognitive
Toolkit
© Metta Innovations 2017
How to Use CNTK
The Microsoft Cognitive Toolkit (CNTK) 2.0:
1. Arbitrary Neural Networks expressed through
building blocks
2. Compose simple blocks into complex Computational
Networks
3. Support relevant Network Types and Applications
4. LEGO-Like composability allows CNTK support
wide range of Networks and Applications
© Metta Innovations 2017
The 3 Main Steps to Train Instances
How to Use CNTK
Creating / Training the Network Model (3 steps):
1. Reader - reads and prepares dataset to be trained
2. Network Model - defines and configures network topology
3. Trainer - chooses the criteria used to train the nodes
Reader
Minibatch Source
Deserializer (task specific)
Automatic Randomization
Train / Test Samples
Network
Model Function
Criterion Function
Engine Config. (GPU/CPU)
Padding
Trainer & Evaluator
Stochastic Gradient Descent
1. Momentum
2. Adam
3. ...
Mini batching
Evaluates the error
Training
Data
Trained
Model
© Metta Innovations 2017
Activation
Function
(W2
, b2
)
Network Model
Model Function:
● Transforms Entry Features into Predictions
● Defines Model Structure and Initialization
Criterion Function:
● Compares Output Features with Labels
● Measure Training Loss & Additional Metrics
● Defines Training & Evaluation Criteria
● Provides Gradients according to the Training
Criteria
How to Use CNTK
Softmax
(W1
, b1
)
Cross Entropy
Activation
Function
Activation
Function
(Wout
, bout
)
x y
© Metta Innovations 2017
Create / Train the Network Model:
1. Reader - reads and prepares
dataset to be trained
2. Network Model - defines and
configures network topology
3. Trainer - chooses the criteria
used to train the nodes
How to Use CNTK
© Metta Innovations 2017
Create / Train the Network Model:
1. Reader - reads and prepares
dataset to be trained
2. Network Model - defines and
configures network topology
3. Trainer - chooses the criteria
used to train the nodes
How to Use CNTK
© Metta Innovations 2017
Create / Train the Network Model:
1. Reader - reads and prepares
dataset to be trained
2. Network Model - defines and
configures network topology
3. Trainer - chooses the criteria
used to train the nodes
How to Use CNTK
Basic autoencoder:
● MNIST handwritten digits data
● Each image 28x28 = 784 pixels
© Metta Innovations 2017
Create / Train the Network Model:
1. Reader - reads and prepares
dataset to be trained
2. Network Model - defines and
configures network topology
3. Trainer - chooses the criteria used
to train the nodes
How to Use CNTK
© Metta Innovations 2017
Create / Train the Network Model:
1. Reader - reads and prepares
dataset to be trained
2. Network Model - defines and
configures network topology
3. Trainer - chooses the criteria
used to train the nodes
How to Use CNTK
© Metta Innovations 2017
Call to Action
https://notebooks.azure.com/
© Metta Innovations 2017
Applications & Examples
© Metta Innovations 2017
Microsoft Build 2017 - Workplace Safety
© Metta Innovations 2017
NEC - Face Recognition
© Metta Innovations 2017
Amazon Go
© Metta Innovations 2017
Metta Intelligent Market
© Metta Innovations 2017
NVIDIA DriveNet Demo
© Metta Innovations 2017
Metta Objects Detection
© Metta Innovations 2017
We are hiring
careers@mettainnovations.com.br
Join the team
© Metta Innovations 2017
Contact Us
Aurélio Figueiredo
aurelio@mettainnovations.com.br
© Metta Innovations 2017
Thank you!
© Metta Innovations 2017

Weitere ähnliche Inhalte

Was ist angesagt?

Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
Naoki (Neo) SATO
 
Cloud Computing
Cloud ComputingCloud Computing
Cloud Computing
butest
 

Was ist angesagt? (20)

Mastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Recent developments in Deep Learning
Recent developments in Deep LearningRecent developments in Deep Learning
Recent developments in Deep Learning
 
On-device machine learning: TensorFlow on Android
On-device machine learning: TensorFlow on AndroidOn-device machine learning: TensorFlow on Android
On-device machine learning: TensorFlow on Android
 
Deep Learning with Microsoft R Open
Deep Learning with Microsoft R OpenDeep Learning with Microsoft R Open
Deep Learning with Microsoft R Open
 
Deep learning an Introduction with Competitive Landscape
Deep learning an Introduction with Competitive LandscapeDeep learning an Introduction with Competitive Landscape
Deep learning an Introduction with Competitive Landscape
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for Robotics
 
Deep learning on mobile
Deep learning on mobileDeep learning on mobile
Deep learning on mobile
 
Deep learning on mobile - 2019 Practitioner's Guide
Deep learning on mobile - 2019 Practitioner's GuideDeep learning on mobile - 2019 Practitioner's Guide
Deep learning on mobile - 2019 Practitioner's Guide
 
Big data app meetup 2016-06-15
Big data app meetup 2016-06-15Big data app meetup 2016-06-15
Big data app meetup 2016-06-15
 
Android and Deep Learning
Android and Deep LearningAndroid and Deep Learning
Android and Deep Learning
 
Rethinking computation: A processor architecture for machine intelligence
Rethinking computation: A processor architecture for machine intelligenceRethinking computation: A processor architecture for machine intelligence
Rethinking computation: A processor architecture for machine intelligence
 
Introduction to Deep Learning and neon at Galvanize
Introduction to Deep Learning and neon at GalvanizeIntroduction to Deep Learning and neon at Galvanize
Introduction to Deep Learning and neon at Galvanize
 
Chainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_otaChainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_ota
 
An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)
 
Deep Learning Computer Build
Deep Learning Computer BuildDeep Learning Computer Build
Deep Learning Computer Build
 
Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
Deep Learning, Microsoft Cognitive Toolkit (CNTK) and Azure Machine Learning ...
 
Deep Learning with CNTK
Deep Learning with CNTKDeep Learning with CNTK
Deep Learning with CNTK
 
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike WangIntroduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
 
Cloud Computing
Cloud ComputingCloud Computing
Cloud Computing
 

Ähnlich wie Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics

Deep Learning Applications and Image Processing
Deep Learning Applications and Image ProcessingDeep Learning Applications and Image Processing
Deep Learning Applications and Image Processing
ijtsrd
 
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea GalloDeep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Linaro
 

Ähnlich wie Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics (20)

TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform TensorFlow 16: Building a Data Science Platform
TensorFlow 16: Building a Data Science Platform
 
Deep learning beyond the learning - Jörg Schad - Codemotion Amsterdam 2018
Deep learning beyond the learning - Jörg Schad - Codemotion Amsterdam 2018Deep learning beyond the learning - Jörg Schad - Codemotion Amsterdam 2018
Deep learning beyond the learning - Jörg Schad - Codemotion Amsterdam 2018
 
Webinar: Deep Learning Pipelines Beyond the Learning
Webinar: Deep Learning Pipelines Beyond the LearningWebinar: Deep Learning Pipelines Beyond the Learning
Webinar: Deep Learning Pipelines Beyond the Learning
 
Deep Learning Applications and Image Processing
Deep Learning Applications and Image ProcessingDeep Learning Applications and Image Processing
Deep Learning Applications and Image Processing
 
OpenPOWER Boot camp in Zurich
OpenPOWER Boot camp in ZurichOpenPOWER Boot camp in Zurich
OpenPOWER Boot camp in Zurich
 
ExaNoDe: European Exascale Processor & Memory Node Design
ExaNoDe: European Exascale Processor & Memory Node DesignExaNoDe: European Exascale Processor & Memory Node Design
ExaNoDe: European Exascale Processor & Memory Node Design
 
Phoenix Data Conference - Big Data Analytics for IoT 11/4/17
Phoenix Data Conference - Big Data Analytics for IoT 11/4/17Phoenix Data Conference - Big Data Analytics for IoT 11/4/17
Phoenix Data Conference - Big Data Analytics for IoT 11/4/17
 
Deep learning beyond the learning - Jörg Schad - Codemotion Rome 2018
Deep learning beyond the learning - Jörg Schad - Codemotion Rome 2018 Deep learning beyond the learning - Jörg Schad - Codemotion Rome 2018
Deep learning beyond the learning - Jörg Schad - Codemotion Rome 2018
 
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
 
Cytoscape: Now and Future
Cytoscape: Now and FutureCytoscape: Now and Future
Cytoscape: Now and Future
 
Final project report format
Final project report formatFinal project report format
Final project report format
 
HPC in higher education
HPC in higher educationHPC in higher education
HPC in higher education
 
Democratizing Data Science on Kubernetes
Democratizing Data Science on Kubernetes Democratizing Data Science on Kubernetes
Democratizing Data Science on Kubernetes
 
LEGaTO: Use cases
LEGaTO: Use casesLEGaTO: Use cases
LEGaTO: Use cases
 
Trends and Hot Topics in Networking 2023 - IA377 Seminar FEEC-UNICAMP
Trends and Hot Topics in Networking 2023 - IA377 Seminar FEEC-UNICAMPTrends and Hot Topics in Networking 2023 - IA377 Seminar FEEC-UNICAMP
Trends and Hot Topics in Networking 2023 - IA377 Seminar FEEC-UNICAMP
 
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea GalloDeep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
 
No More Cumbersomeness: Automatic Predictive Modeling on Apache Spark with Ma...
No More Cumbersomeness: Automatic Predictive Modeling on Apache Spark with Ma...No More Cumbersomeness: Automatic Predictive Modeling on Apache Spark with Ma...
No More Cumbersomeness: Automatic Predictive Modeling on Apache Spark with Ma...
 
Migrating from OpenTracing to OpenTelemetry - Kubernetes Community Days Munic...
Migrating from OpenTracing to OpenTelemetry - Kubernetes Community Days Munic...Migrating from OpenTracing to OpenTelemetry - Kubernetes Community Days Munic...
Migrating from OpenTracing to OpenTelemetry - Kubernetes Community Days Munic...
 
ECML PKDD 2021 ML meets IoT Tutorial Part II: Creating ML based Self learning...
ECML PKDD 2021 ML meets IoT Tutorial Part II: Creating ML based Self learning...ECML PKDD 2021 ML meets IoT Tutorial Part II: Creating ML based Self learning...
ECML PKDD 2021 ML meets IoT Tutorial Part II: Creating ML based Self learning...
 
Resume
ResumeResume
Resume
 

Kürzlich hochgeladen

If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New Nigeria
Kayode Fayemi
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
Sheetaleventcompany
 
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
amilabibi1
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
raffaeleoman
 
Uncommon Grace The Autobiography of Isaac Folorunso
Uncommon Grace The Autobiography of Isaac FolorunsoUncommon Grace The Autobiography of Isaac Folorunso
Uncommon Grace The Autobiography of Isaac Folorunso
Kayode Fayemi
 

Kürzlich hochgeladen (20)

SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, YardstickSaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
 
Sector 62, Noida Call girls :8448380779 Noida Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Noida Escorts | 100% verifiedSector 62, Noida Call girls :8448380779 Noida Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Noida Escorts | 100% verified
 
If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New Nigeria
 
Causes of poverty in France presentation.pptx
Causes of poverty in France presentation.pptxCauses of poverty in France presentation.pptx
Causes of poverty in France presentation.pptx
 
Air breathing and respiratory adaptations in diver animals
Air breathing and respiratory adaptations in diver animalsAir breathing and respiratory adaptations in diver animals
Air breathing and respiratory adaptations in diver animals
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
 
The workplace ecosystem of the future 24.4.2024 Fabritius_share ii.pdf
The workplace ecosystem of the future 24.4.2024 Fabritius_share ii.pdfThe workplace ecosystem of the future 24.4.2024 Fabritius_share ii.pdf
The workplace ecosystem of the future 24.4.2024 Fabritius_share ii.pdf
 
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
Bring back lost lover in USA, Canada ,Uk ,Australia ,London Lost Love Spell C...
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
 
My Presentation "In Your Hands" by Halle Bailey
My Presentation "In Your Hands" by Halle BaileyMy Presentation "In Your Hands" by Halle Bailey
My Presentation "In Your Hands" by Halle Bailey
 
lONG QUESTION ANSWER PAKISTAN STUDIES10.
lONG QUESTION ANSWER PAKISTAN STUDIES10.lONG QUESTION ANSWER PAKISTAN STUDIES10.
lONG QUESTION ANSWER PAKISTAN STUDIES10.
 
Presentation on Engagement in Book Clubs
Presentation on Engagement in Book ClubsPresentation on Engagement in Book Clubs
Presentation on Engagement in Book Clubs
 
Dreaming Marissa Sánchez Music Video Treatment
Dreaming Marissa Sánchez Music Video TreatmentDreaming Marissa Sánchez Music Video Treatment
Dreaming Marissa Sánchez Music Video Treatment
 
BDSM⚡Call Girls in Sector 97 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 97 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 97 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 97 Noida Escorts >༒8448380779 Escort Service
 
Dreaming Music Video Treatment _ Project & Portfolio III
Dreaming Music Video Treatment _ Project & Portfolio IIIDreaming Music Video Treatment _ Project & Portfolio III
Dreaming Music Video Treatment _ Project & Portfolio III
 
Report Writing Webinar Training
Report Writing Webinar TrainingReport Writing Webinar Training
Report Writing Webinar Training
 
ICT role in 21st century education and it's challenges.pdf
ICT role in 21st century education and it's challenges.pdfICT role in 21st century education and it's challenges.pdf
ICT role in 21st century education and it's challenges.pdf
 
Uncommon Grace The Autobiography of Isaac Folorunso
Uncommon Grace The Autobiography of Isaac FolorunsoUncommon Grace The Autobiography of Isaac Folorunso
Uncommon Grace The Autobiography of Isaac Folorunso
 
Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)
 
Aesthetic Colaba Mumbai Cst Call girls 📞 7738631006 Grant road Call Girls ❤️-...
Aesthetic Colaba Mumbai Cst Call girls 📞 7738631006 Grant road Call Girls ❤️-...Aesthetic Colaba Mumbai Cst Call girls 📞 7738631006 Grant road Call Girls ❤️-...
Aesthetic Colaba Mumbai Cst Call girls 📞 7738631006 Grant road Call Girls ❤️-...
 

Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics

  • 1. © Metta Innovations 2017 Jun 2017 An Introduction to Deep Learning applied to Video Analytics Aurélio Figueiredo aurelio@mettainnovations.com.br
  • 2. © Metta Innovations 2017 *Minimal Similarity Accumulation Attribute Using Dimensionality Reduction with Feature Extraction. In 78th European Association of Geoscientists and Engineers (EAGE) Conference and Exhibition 2016 Metta Innovations Great know-how in solutions applied to Oil & Gas Industry . Computational Geophysics . Machine Learning / Deep Learning . Automatic Seismic Interpretation . ... Autoencoder EAGE 2016*
  • 3. © Metta Innovations 2017 Metta Innovations Expertise: . Visualization . Virtual and augmented reality . High Performance Computing (HPC) . Computer Vision . Big Data . Deep Learning
  • 4. © Metta Innovations 2017 Agenda Open Source Libraries & Examples and Applications What is Deep Learning? Why Deep Learning? How to Use CNTK? Code sample with CNTK technology?
  • 5. © Metta Innovations 2017 What is Deep Learning? Deep learning (or deep structured learning or hierarchical learning): 1. Subfield of machine learning inspired by function of the brain 2. Artificial neural networks (ANNs) with many hidden layers 3. Suitable when target function is very complex (datasets REALLY large)
  • 6. © Metta Innovations 2017 What is Deep Learning? Deep Learning is the state-of-art approach to: 1. Computer Vision 2. Speech Recognition & Natural Language Processing 3. Audio Recognition & Machine Translation 4. Social Network Filtering 5. Bioinformatics In all these fields they produced results comparable to or superior to human experts!
  • 7. © Metta Innovations 2017 Why Deep Learning? Automatically extracting features instead of manual extraction in feature engineering: 1. You don’t have to figure out the features ahead of time 2. We can use the same neural net approach for many different problems Open sourcing is predominant in deep learning:
  • 8. © Metta Innovations 2017 Why Deep Learning? ImageNet Large Scale Visual Recognition Competition (ILSVRC*): 1. Evaluate algorithms for object detection at large scale 2. Measure progress of computer vision for large scale image *http://www.image-net.org/challenges/LSVRC/ 2010 Nec America 2011 Xerox 2012 AlexNet 2013 Clarify 2014 VGG 2014 GoogleNet 2015 MS ResNet ImageNet Classification top-5 error (%) 30.0 20.0 10.0 0 28.2 25.8 16.4 11.7 7.3 3.6 6.7
  • 9. © Metta Innovations 2017 Open Source Libraries
  • 10. © Metta Innovations 2017 Developed by Berkeley Vision and Learning Center Extended by Facebook ( Caffe2 ) Mainly focusing on computer vision applications Platforms: ● Linux ● macOS ● Windows Supported programming languages: ● Python ● C++ ● MATLAB Caffe
  • 11. © Metta Innovations 2017 Developed by Microsoft Research - Released Jan/2016 Platforms: ● Windows ● Linux Supported programming languages: ● Python (versions supported are 2.7, 3.4, and 3.5) ● C++ ● C#/.NET Managed Microsoft Cognitive Toolkit
  • 12. © Metta Innovations 2017 Developed by DMLC team (used on Amazon AWS) Platforms: ● Linux ● macOS ● Windows ● Android/iOS ● AWS MXNet Supported programming languages: ● Python ● C++ ● Scala ● R ● Perl ● MATLAB
  • 13. © Metta Innovations 2017 Developed by Google - Released Nov/2015: Platforms: ● Linux ● macOS ● Windows ● Android (new!) Supported programming languages: ● Python ● C/C++ ● Java ● Go ● R Tensor Flow
  • 14. © Metta Innovations 2017 Developed by University of Montreal Platforms: ● Linux ● macOS ● Windows Supported programming languages: ● Python Theano
  • 15. © Metta Innovations 2017 Developed by R Collobert, K Kavukcuoglu, C Farabet - Released Oct/2002 Platforms: ● Linux ● Mac OS X ● Windows ● Android Supported programming languages: ● Lua ● LuaJIT ● C ● C++/OpenCL Torch
  • 16. © Metta Innovations 2017 Libraries Comparison Single GPU - Benchmarking State-of-the-Art Deep Learning Software: http://dlbench.comp.hkbu.edu.hk FCN-8 AlexNet ResNet-50 LSTM-64 CNTK 0.037 0.040 0.207 0.122 Caffe 0.038 0.026 0.307 --- TensorFlow 0.063 --- --- 0.144 Torch 0.048 0.033 0.188 0.194 Seconds per minibatch on G1080 (G980) GPU. Lower is better. *November 2016. *Benchmarking State-of-the-Art Deep Learning Software: http://dlbench.comp.hkbu.edu.hk
  • 17. © Metta Innovations 2017 1 GPU CNTK Theano TensorFlow Torch Caffe Libraries Comparison Speed comparison (samples / second). Higher is better. *December 2015. 80000 60000 40000 20000 0 1 x 4 GPUs 2 x 4 GPUs (8 GPUs) *Benchmarking State-of-the-Art Deep Learning Software: http://dlbench.comp.hkbu.edu.hk Multiples GPU - Benchmarking State-of-the-Art Deep Learning Software: http://dlbench.comp.hkbu.edu.hk
  • 18. © Metta Innovations 2017 Using Microsoft Cognitive Toolkit
  • 19. © Metta Innovations 2017 How to Use CNTK The Microsoft Cognitive Toolkit (CNTK) 2.0: 1. Arbitrary Neural Networks expressed through building blocks 2. Compose simple blocks into complex Computational Networks 3. Support relevant Network Types and Applications 4. LEGO-Like composability allows CNTK support wide range of Networks and Applications
  • 20. © Metta Innovations 2017 The 3 Main Steps to Train Instances How to Use CNTK Creating / Training the Network Model (3 steps): 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes Reader Minibatch Source Deserializer (task specific) Automatic Randomization Train / Test Samples Network Model Function Criterion Function Engine Config. (GPU/CPU) Padding Trainer & Evaluator Stochastic Gradient Descent 1. Momentum 2. Adam 3. ... Mini batching Evaluates the error Training Data Trained Model
  • 21. © Metta Innovations 2017 Activation Function (W2 , b2 ) Network Model Model Function: ● Transforms Entry Features into Predictions ● Defines Model Structure and Initialization Criterion Function: ● Compares Output Features with Labels ● Measure Training Loss & Additional Metrics ● Defines Training & Evaluation Criteria ● Provides Gradients according to the Training Criteria How to Use CNTK Softmax (W1 , b1 ) Cross Entropy Activation Function Activation Function (Wout , bout ) x y
  • 22. © Metta Innovations 2017 Create / Train the Network Model: 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes How to Use CNTK
  • 23. © Metta Innovations 2017 Create / Train the Network Model: 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes How to Use CNTK
  • 24. © Metta Innovations 2017 Create / Train the Network Model: 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes How to Use CNTK Basic autoencoder: ● MNIST handwritten digits data ● Each image 28x28 = 784 pixels
  • 25. © Metta Innovations 2017 Create / Train the Network Model: 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes How to Use CNTK
  • 26. © Metta Innovations 2017 Create / Train the Network Model: 1. Reader - reads and prepares dataset to be trained 2. Network Model - defines and configures network topology 3. Trainer - chooses the criteria used to train the nodes How to Use CNTK
  • 27. © Metta Innovations 2017 Call to Action https://notebooks.azure.com/
  • 28. © Metta Innovations 2017 Applications & Examples
  • 29. © Metta Innovations 2017 Microsoft Build 2017 - Workplace Safety
  • 30. © Metta Innovations 2017 NEC - Face Recognition
  • 31. © Metta Innovations 2017 Amazon Go
  • 32. © Metta Innovations 2017 Metta Intelligent Market
  • 33. © Metta Innovations 2017 NVIDIA DriveNet Demo
  • 34. © Metta Innovations 2017 Metta Objects Detection
  • 35. © Metta Innovations 2017 We are hiring careers@mettainnovations.com.br Join the team
  • 36. © Metta Innovations 2017 Contact Us Aurélio Figueiredo aurelio@mettainnovations.com.br
  • 37. © Metta Innovations 2017 Thank you!