SlideShare a Scribd company logo
1 of 34
Download to read offline
Copyright © 2017 LUXOFT 1
Alexey Rybakov, LUXOFT
May 2017
Deep Learning Beyond Cats and Cars
Developing a Real-life DNN-based Embedded Vision Product
for Agriculture, Construction, Medical, or Retail
Copyright © 2017 LUXOFT 2
What This Talk is About
Key Decisions
in a Deep Learning Computer Vision Project
1. Data 2. Compute Pipeline
3. Training and
Tuning
• Data acquisition, and
how much is enough
• Data processing
pipeline
• Compute infrastructure
• AI platform and model
• Data preparation
• Network training
• Fine tuning
Copyright © 2017 LUXOFT 3
Why We Are Giving This Talk
Our AI Practice:
- Computer vision
- ..and non-vision AI
Pharma
AgricultureRetail
Industrial
Automotive
Copyright © 2017 LUXOFT 4
Introduction: Paradigm Shift in Software R&D
0.
Copyright © 2017 LUXOFT 5
Paradigm Shift in Software R&D
Traditional Software R&D AI-driven Software R&D
Coding / testing
Integration, roll-out and
maintenance
Developers
IT Support
Knowledge
(Algorithm development)
System design
SME
System
Architects
Data selection
Learning Pipeline Design
Data preparation,
Training, Tuning
Integration, roll-out and
maintenance
SME
AI Architects
Data
specialists
Data and AI
Support
Access to DataFocus
of this
talk
New
Professions!
Copyright © 2017 LUXOFT 6
Data is the King
1.
Copyright © 2017 LUXOFT 7
Paradigm Shift: Another Way to Look At It
Was Becoming
Subject Matter Experts Data
Algorithm Development No algorithm Development
Domain (Vertical) Knowledge AI (System) Knowledge
Decision Quality is Art Decision Quality is Predictable
The single most important investment you can make in AI project
is Data Strategy
Copyright © 2017 LUXOFT 8
1. Data coverage - needs to be representative - cover all cases (more than you
think)
2. Data balance (normalization) - about equal amount of data for each
class/case/scenario
3. Amount of data
Data Sourcing: It Starts with Data!
Acquire
Data
Prepare
Data
Six data guidelines that we consider important
…to achieve the best results (accuracy, false positives, false negatives).
4. Data formatting - make it work with existing/selected DNN architectures: Like
ROI selection, breaking big picture into smaller, video into frames, etc
5. Data synthesis and augmentation - “cat and mirror reflection of a cat are two
different cats”. Often easier to transform existing data than to obtain new data
6. Data annotation
Copyright © 2017 LUXOFT 9
Example: Pharma Data
Crystal clear media
before dissolution
Just after the sample
is dropped, and
remains a single solid
piece
When the sample
started to swell, still a
single piece
When the sample
continues to swell, and
produces many small
particles: low-contrast
media
Copyright © 2017 LUXOFT 10
Pharma Improper Data Sampling – Imbalanced Set
Accuracy paradox
Imbalanced dataset Balanced dataset
60%
65%
70%
75%
80%
85%
90%
95%
100%
overall cloudy media
Labeled video sample
Problem: dataset imbalance
• Tricky to identify
• What to do: change performance metric for trained network
What to do:
• Use penalized models: adjust cost function for imbalance
• Decompose large classes into smaller
• Resample: over- and under-sample to balance
Copyright © 2017 LUXOFT 11
Pharma Improper Data Sampling (contd.)
Different optimization approaches to
find separate thresholds for each class
(1,2,3)
3 options of Uniform class distribution
(balanced datasets)
Proper data shuffling is important
Common approaches used by NVidia
DIGITS (conventional 2-stage shuffling)
Our custom data shuffling gave us up
to 1.3% of increase in accuracy in
comparison with conventional scheme
Balandced dataset 1 Balandced dataset 2 Balandced dataset 3
90%
91%
92%
93%
94%
95%
96%
97%
conventional shuffling
custom shuffling
Top 1% accuracy
Balanced dataset 1 Balanced dataset 2 Balanced dataset 3
Copyright © 2017 LUXOFT 12
Data Processing Pipeline
2.
Copyright © 2017 LUXOFT 13
Machine Learning vs. Deep Learning
[Ian Goodfellow et all, ISBN 978-0262035613]
Classic ML
Deep Learning
Copyright © 2017 LUXOFT 14
100% Deep Learning: possible but not practical
• In this diagram, it seems that deep learning works
from raw data. In reality this is the most ideal
case
• Needs infinite data + infinite compute
• Practical implementations are still in between
Classic ML and DL with a lot of upfront non-neural
efforts in data selection and preparation.
That is why we need to build data processing
pipeline
Machine Learning vs. Deep Learning
[Ian Goodfellow et all, ISBN 978-0262035613]
Copyright © 2017 LUXOFT 15
Feeding raw data straight to Deep Network is still a dream. Asymptotically possible, but
practically inefficient.
• Therefore we pipeline processing blocks, like this:
Visual Data Processing Pipeline
Visual Pre-
processing
Rough
Features
More
Abstract
Features
Meta Data
Output
Raw Data
Input
• May be non-AI: like HOG (spatial),
inter-frame diff (temporal)
• ..or AI: like YOLO to detect object
classes and ROI boundaries
• AI Block for
complex
abstractions: scene
classification, action
recognition,..
• Basic processing:
color conversion,
de-noise,..
• AI is still rare here
Copyright © 2017 LUXOFT 16
• Purpose:
• Region of interest (ROI) detection
• Camera calibration
• Detect shakes and shifts
• Solution
• Based on YOLO (you look only once,
http://pjreddie.com/darknet/yolo/)
• Processing in real-time
Example: Pharma Processing Pipeline (One of the
AI Parts)
Copyright © 2017 LUXOFT 17
• Wobbling detection
• Represent video in temporal
space
• Search for sinusoid amplitude
• RPM detection
• Treat paddle as a signal
• Fourier transformation for
frequency detection
• Implemented for 20 FPS
• Calibration required
Example: Pharma Processing Pipeline (One of the Non-
AI Parts)
Spatial (left) and temporal (right) representation of video data
ROI (left) and signal (right) of paddle appearance
Copyright © 2017 LUXOFT 18
Platform selection (Caffe / Torch / TensorFlow / etc) - is like selecting a java app server, or web server:
many similarities and hard to chose, however this is what we use:
• Availability of models for your task
• Deployment compatibility: both enterprise and embedded
• Works with your cloud? Like Amazon AWS or MS Azure?
• Works on your device? Like ARM or NVidia GPUs?
• Distributed processing choices: Cloud / Edge
• Embedded optimization opportunities
• Maintenance considerations
• Support for training models, tools and scenarios <= important to think ahead
Platform Selection Guidelines
Copyright © 2017 LUXOFT 19
We often hear: “use the latest, greatest model”.
However, we’d rather use “simple model for simple data”. Same as “good-enough”
concept.
Important selection criteria we encounter
• Production accuracy
• “Cascadability”
• Production run-time speed
• Training and fine-tuning scenarios: amount and
kind of required training data, efforts to train
Pharma example: Winner is AlexNet (yes!):
quick learner, fast to run, good accuracy on our data
Model Selection Guidelines
Accuracy
Training Epoch
Copyright © 2017 LUXOFT 20
• Total number of different classes ~100,000
• We use a cascade of networks
• Level 1: Type-search network
• Level 2: Different Classification networks
for each type
• Conventional accuracy metrics
for type-search networks:
• mAP, Precision, Recall
• These metrics always use fixed IoU at =0.5
• IoU = Intersection over Union
• Classification accuracy strongly depends on IoU
• IoU = 0.5  classification probability =~ 0.68
• IoU > 0.7  classification probability > 0.90
Retail Example: “Cascadability” of a Search
Network
IoU=1 IoU=0.5
IoU
Classification
Probability
What is IoU:
Copyright © 2017 LUXOFT 21
Model Training and Tuning (Data Again!)
3.
Copyright © 2017 LUXOFT 22
AI System Development Is More Iterative
Traditional SW Engineering Deep Learning SW Engineering
Copyright © 2017 LUXOFT 23
A. Create dataset for training
1. Manually classify a limited set of data
2. Train a network (well known architecture) on
classified data
3. Test on a new data set, check accuracy
4. Manually classify new data based on network hints
5. Add new data into training set and go to 1 or 2
B. DNN Architecture
1. Tune DNN architecture
2. Train the network on the data set
3. Test on a new data set, check accuracy, goto #1
C. Verify the network
Example: Pharma Iterative Training Workflow
database: ~5,000 images for
each class
Uniform distribution of
classes required
Training Epoch
Copyright © 2017 LUXOFT 24
Example: Pharma Iterative Training Workflow
DNN
Human
Legend
Crystal clear media
Sample dropped
Sample Swelling
Sample dissolving
Precipitate presented
Media Foggy
Iterative DNN training
Use trained DNN for fixing data labelling that follows "Pseudo-Label" technique
Visualize your data
Copyright © 2017 LUXOFT 25
1. Data coverage - needs to be representative - cover all cases (more than you
think)
2. Data balance (normalization) - about equal amount of data for each
class/case/scenario
3. Amount of data
Model Training: Time to Use Your Data!
Acquire
Data
Prepare
Data
Six data guidelines that we consider important
…to achieve the best results (accuracy, false positives, false negatives).
4. Data formatting - make it work with existing/selected DNN architectures: Like
ROI selection, breaking big picture into smaller, video into frames, etc
5. Data synthesis and augmentation - “cat and mirror reflection of a cat are two
different cats”. Often easier to transform existing data than to obtain new data
6. Data annotation
Copyright © 2017 LUXOFT 26
Data Preparation and Annotation Scenarios
Data Annotation
(Labeling)
Use Cases
Real / raw Manual Sometimes good choice for total greenfield. Need human resources.
Tools dramatically increase the efficiency
Computer, then
human
Rudimentary AI provides draft annotation. Then humans
confirm/correct.
Example: house number captcha
Human, then
computer
Humans annotate 1st frame. Then existing CV methods provide
object tracking on subsequent frames. Very efficient for dynamic
scenes
Augmented Automated Use high quality labeled dataset and augment to simulate real-life
conditions. Example: “German Traffic Sign” dataset could have been
almost entirely synthesized trough augmentation.
Synthetic Automated Use 3D rendering software and scripts to generate scenes. Our
construction example.
Copyright © 2017 LUXOFT 27
Retail Example. Data Augmentation and Synthesis
Normal Light Conditions WB Deviations ISO Simulation
Year Synthesis
Copyright © 2017 LUXOFT 28
Railway Safety Example: Synthetic Data for
Training
Copyright © 2017 LUXOFT 29
Lessons Learned and Resources
!.
Copyright © 2017 LUXOFT 30
Lessons Learned
model
effort
data
effort
data
effort
Copyright © 2017 LUXOFT 31
• The most important decision is data strategy
• Data acquisition: Need lots of data, full coverage, well balanced.
• Model decisions: Best overall may be not the best for you.
• Pipeline decisions: Cascade and combine: Classic and AI algorithms.
• Training: A lot can be achieved by data preparation and
synthesis.
Annotation tools save millions.
• Be prepared to stop. AI development is a very iterative process
Lessons Learned
Copyright © 2017 LUXOFT 32
• Our website: www.luxoft.com
• Our last year talk here at the Summit 2016 about computer vision pipeline
optimization:
• Available in full on Embedded Vision Alliance website:
https://www.embedded-vision.com/platinum-members/luxoft/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit
Resources
Copyright © 2017 LUXOFT 33
Check out the demos at LUXOFT booth!
Extremely optimized artificial
intelligence and computer vision
pipelines running on low-power
embedded platforms and GPU
architectures: stereo vision, video and
image processing, DNNs; as well as
our Hybrid AI Platform that distributes
and manages both deep learning and
classic computation across cloud and
edge devices.
*photo of our last year booth
Copyright © 2017 LUXOFT 34
Alexey Rybakov
ARybakov@luxoft.com
LUXOFT
4400 Bohannon Dr Ste 235
Menlo Park, CA 94025
Thank you!
:)

More Related Content

What's hot

"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a..."Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...Edge AI and Vision Alliance
 
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al..."Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...Edge AI and Vision Alliance
 
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ..."Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...Edge AI and Vision Alliance
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...Edge AI and Vision Alliance
 
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori..."Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...Edge AI and Vision Alliance
 
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy AnalyticsEdge AI and Vision Alliance
 
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ..."Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...Edge AI and Vision Alliance
 
High Performance Computing
High Performance ComputingHigh Performance Computing
High Performance ComputingDell World
 
“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive
“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive
“TinyML Isn’t Thinking Big Enough,” a Presentation from PerceiveEdge AI and Vision Alliance
 
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...Edge AI and Vision Alliance
 
Very large scale distributed deep learning on BigDL
Very large scale distributed deep learning on BigDLVery large scale distributed deep learning on BigDL
Very large scale distributed deep learning on BigDLDESMOND YUEN
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...Edge AI and Vision Alliance
 
Webinar: Three Reasons Why NAS is No Good for AI and Machine Learning
Webinar: Three Reasons Why NAS is No Good for AI and Machine LearningWebinar: Three Reasons Why NAS is No Good for AI and Machine Learning
Webinar: Three Reasons Why NAS is No Good for AI and Machine LearningStorage Switzerland
 
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from SamsungEdge AI and Vision Alliance
 
Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309DrVictorFang
 
Metaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixMetaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixBill Liu
 
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化NVIDIA Taiwan
 
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart..."Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...Edge AI and Vision Alliance
 

What's hot (20)

"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a..."Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
 
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al..."Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
"Designing CNN Algorithms for Real-time Applications," a Presentation from Al...
 
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ..."Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
 
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori..."Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...
"Blending Cloud and Edge Machine Learning to Deliver Real-time Video Monitori...
 
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
 
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ..."Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...
"Deep Learning and Vision Algorithm Development in MATLAB Targeting Embedded ...
 
High Performance Computing
High Performance ComputingHigh Performance Computing
High Performance Computing
 
“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive
“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive
“TinyML Isn’t Thinking Big Enough,” a Presentation from Perceive
 
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...
“Building an Autonomous Detect-and-Avoid System for Commercial Drones,” a Pre...
 
Very large scale distributed deep learning on BigDL
Very large scale distributed deep learning on BigDLVery large scale distributed deep learning on BigDL
Very large scale distributed deep learning on BigDL
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
 
Webinar: Three Reasons Why NAS is No Good for AI and Machine Learning
Webinar: Three Reasons Why NAS is No Good for AI and Machine LearningWebinar: Three Reasons Why NAS is No Good for AI and Machine Learning
Webinar: Three Reasons Why NAS is No Good for AI and Machine Learning
 
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung
“A Highly Data-Efficient Deep Learning Approach,” a Presentation from Samsung
 
Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309
 
Metaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at NetflixMetaflow: The ML Infrastructure at Netflix
Metaflow: The ML Infrastructure at Netflix
 
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
GTC Taiwan 2017 在 Google Cloud 當中使用 GPU 進行效能最佳化
 
PPI_Technology_Overview
PPI_Technology_OverviewPPI_Technology_Overview
PPI_Technology_Overview
 
On-Device AI
On-Device AIOn-Device AI
On-Device AI
 
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart..."Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...
"Approaches for Vision-based Driver Monitoring," a Presentation from PathPart...
 

Similar to "Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedded Vision Product for Agriculture, Construction, Medical, or Retail," a Presentation from Luxoft

Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsPractical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsAlexey Rybakov
 
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 2018Codemotion
 
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...inside-BigData.com
 
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 Seldon
 
Enterprise deep learning lessons bodkin o reilly ai sf 2017
Enterprise deep learning lessons bodkin o reilly ai sf 2017Enterprise deep learning lessons bodkin o reilly ai sf 2017
Enterprise deep learning lessons bodkin o reilly ai sf 2017Ron Bodkin
 
Machine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERMachine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERGanesan Narayanasamy
 
Think Big | Enterprise Artificial Intelligence
Think Big | Enterprise Artificial IntelligenceThink Big | Enterprise Artificial Intelligence
Think Big | Enterprise Artificial IntelligenceData Science Milan
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDatabricks
 
Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017Clarisse Hedglin
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...Edge AI and Vision Alliance
 
IBM Data Centric Systems & OpenPOWER
IBM Data Centric Systems & OpenPOWERIBM Data Centric Systems & OpenPOWER
IBM Data Centric Systems & OpenPOWERinside-BigData.com
 
Building Data Science Ecosystems for Smart Cities and Smart Commerce
Building Data Science Ecosystems for Smart Cities and Smart CommerceBuilding Data Science Ecosystems for Smart Cities and Smart Commerce
Building Data Science Ecosystems for Smart Cities and Smart CommerceAlex Liu
 
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019 Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019 Stefan Geißler
 
Availability in a cloud native world v1.6 (Feb 2019)
Availability in a cloud native world v1.6 (Feb 2019)Availability in a cloud native world v1.6 (Feb 2019)
Availability in a cloud native world v1.6 (Feb 2019)Haytham Elkhoja
 
Wicsa2011 cloud tutorial
Wicsa2011 cloud tutorialWicsa2011 cloud tutorial
Wicsa2011 cloud tutorialAnna Liu
 
Infrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at ScaleInfrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at ScaleRobb Boyd
 
Introduction to Machine Learning on IBM Power Systems
Introduction to Machine Learning on IBM Power SystemsIntroduction to Machine Learning on IBM Power Systems
Introduction to Machine Learning on IBM Power SystemsDavid Spurway
 
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)Amazon Web Services
 

Similar to "Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedded Vision Product for Agriculture, Construction, Medical, or Retail," a Presentation from Luxoft (20)

Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsPractical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
 
OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar OpenPOWER/POWER9 AI webinar
OpenPOWER/POWER9 AI webinar
 
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
 
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...
The Transformation of HPC: Simulation and Cognitive Methods in the Era of Big...
 
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
 
AI at Scale in Enterprises
AI at Scale in Enterprises AI at Scale in Enterprises
AI at Scale in Enterprises
 
Enterprise deep learning lessons bodkin o reilly ai sf 2017
Enterprise deep learning lessons bodkin o reilly ai sf 2017Enterprise deep learning lessons bodkin o reilly ai sf 2017
Enterprise deep learning lessons bodkin o reilly ai sf 2017
 
Machine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWERMachine Learning AND Deep Learning for OpenPOWER
Machine Learning AND Deep Learning for OpenPOWER
 
Think Big | Enterprise Artificial Intelligence
Think Big | Enterprise Artificial IntelligenceThink Big | Enterprise Artificial Intelligence
Think Big | Enterprise Artificial Intelligence
 
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and PandasDistributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
Distributed Models Over Distributed Data with MLflow, Pyspark, and Pandas
 
Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
 
IBM Data Centric Systems & OpenPOWER
IBM Data Centric Systems & OpenPOWERIBM Data Centric Systems & OpenPOWER
IBM Data Centric Systems & OpenPOWER
 
Building Data Science Ecosystems for Smart Cities and Smart Commerce
Building Data Science Ecosystems for Smart Cities and Smart CommerceBuilding Data Science Ecosystems for Smart Cities and Smart Commerce
Building Data Science Ecosystems for Smart Cities and Smart Commerce
 
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019 Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019
 
Availability in a cloud native world v1.6 (Feb 2019)
Availability in a cloud native world v1.6 (Feb 2019)Availability in a cloud native world v1.6 (Feb 2019)
Availability in a cloud native world v1.6 (Feb 2019)
 
Wicsa2011 cloud tutorial
Wicsa2011 cloud tutorialWicsa2011 cloud tutorial
Wicsa2011 cloud tutorial
 
Infrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at ScaleInfrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
Infrastructure Solutions for Deploying AI/ML/DL Workloads at Scale
 
Introduction to Machine Learning on IBM Power Systems
Introduction to Machine Learning on IBM Power SystemsIntroduction to Machine Learning on IBM Power Systems
Introduction to Machine Learning on IBM Power Systems
 
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)
AWS re:Invent 2016: Bringing Deep Learning to the Cloud with Amazon EC2 (CMP314)
 

More from Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from SamsaraEdge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 

Recently uploaded

Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 

Recently uploaded (20)

Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 

"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedded Vision Product for Agriculture, Construction, Medical, or Retail," a Presentation from Luxoft

  • 1. Copyright © 2017 LUXOFT 1 Alexey Rybakov, LUXOFT May 2017 Deep Learning Beyond Cats and Cars Developing a Real-life DNN-based Embedded Vision Product for Agriculture, Construction, Medical, or Retail
  • 2. Copyright © 2017 LUXOFT 2 What This Talk is About Key Decisions in a Deep Learning Computer Vision Project 1. Data 2. Compute Pipeline 3. Training and Tuning • Data acquisition, and how much is enough • Data processing pipeline • Compute infrastructure • AI platform and model • Data preparation • Network training • Fine tuning
  • 3. Copyright © 2017 LUXOFT 3 Why We Are Giving This Talk Our AI Practice: - Computer vision - ..and non-vision AI Pharma AgricultureRetail Industrial Automotive
  • 4. Copyright © 2017 LUXOFT 4 Introduction: Paradigm Shift in Software R&D 0.
  • 5. Copyright © 2017 LUXOFT 5 Paradigm Shift in Software R&D Traditional Software R&D AI-driven Software R&D Coding / testing Integration, roll-out and maintenance Developers IT Support Knowledge (Algorithm development) System design SME System Architects Data selection Learning Pipeline Design Data preparation, Training, Tuning Integration, roll-out and maintenance SME AI Architects Data specialists Data and AI Support Access to DataFocus of this talk New Professions!
  • 6. Copyright © 2017 LUXOFT 6 Data is the King 1.
  • 7. Copyright © 2017 LUXOFT 7 Paradigm Shift: Another Way to Look At It Was Becoming Subject Matter Experts Data Algorithm Development No algorithm Development Domain (Vertical) Knowledge AI (System) Knowledge Decision Quality is Art Decision Quality is Predictable The single most important investment you can make in AI project is Data Strategy
  • 8. Copyright © 2017 LUXOFT 8 1. Data coverage - needs to be representative - cover all cases (more than you think) 2. Data balance (normalization) - about equal amount of data for each class/case/scenario 3. Amount of data Data Sourcing: It Starts with Data! Acquire Data Prepare Data Six data guidelines that we consider important …to achieve the best results (accuracy, false positives, false negatives). 4. Data formatting - make it work with existing/selected DNN architectures: Like ROI selection, breaking big picture into smaller, video into frames, etc 5. Data synthesis and augmentation - “cat and mirror reflection of a cat are two different cats”. Often easier to transform existing data than to obtain new data 6. Data annotation
  • 9. Copyright © 2017 LUXOFT 9 Example: Pharma Data Crystal clear media before dissolution Just after the sample is dropped, and remains a single solid piece When the sample started to swell, still a single piece When the sample continues to swell, and produces many small particles: low-contrast media
  • 10. Copyright © 2017 LUXOFT 10 Pharma Improper Data Sampling – Imbalanced Set Accuracy paradox Imbalanced dataset Balanced dataset 60% 65% 70% 75% 80% 85% 90% 95% 100% overall cloudy media Labeled video sample Problem: dataset imbalance • Tricky to identify • What to do: change performance metric for trained network What to do: • Use penalized models: adjust cost function for imbalance • Decompose large classes into smaller • Resample: over- and under-sample to balance
  • 11. Copyright © 2017 LUXOFT 11 Pharma Improper Data Sampling (contd.) Different optimization approaches to find separate thresholds for each class (1,2,3) 3 options of Uniform class distribution (balanced datasets) Proper data shuffling is important Common approaches used by NVidia DIGITS (conventional 2-stage shuffling) Our custom data shuffling gave us up to 1.3% of increase in accuracy in comparison with conventional scheme Balandced dataset 1 Balandced dataset 2 Balandced dataset 3 90% 91% 92% 93% 94% 95% 96% 97% conventional shuffling custom shuffling Top 1% accuracy Balanced dataset 1 Balanced dataset 2 Balanced dataset 3
  • 12. Copyright © 2017 LUXOFT 12 Data Processing Pipeline 2.
  • 13. Copyright © 2017 LUXOFT 13 Machine Learning vs. Deep Learning [Ian Goodfellow et all, ISBN 978-0262035613] Classic ML Deep Learning
  • 14. Copyright © 2017 LUXOFT 14 100% Deep Learning: possible but not practical • In this diagram, it seems that deep learning works from raw data. In reality this is the most ideal case • Needs infinite data + infinite compute • Practical implementations are still in between Classic ML and DL with a lot of upfront non-neural efforts in data selection and preparation. That is why we need to build data processing pipeline Machine Learning vs. Deep Learning [Ian Goodfellow et all, ISBN 978-0262035613]
  • 15. Copyright © 2017 LUXOFT 15 Feeding raw data straight to Deep Network is still a dream. Asymptotically possible, but practically inefficient. • Therefore we pipeline processing blocks, like this: Visual Data Processing Pipeline Visual Pre- processing Rough Features More Abstract Features Meta Data Output Raw Data Input • May be non-AI: like HOG (spatial), inter-frame diff (temporal) • ..or AI: like YOLO to detect object classes and ROI boundaries • AI Block for complex abstractions: scene classification, action recognition,.. • Basic processing: color conversion, de-noise,.. • AI is still rare here
  • 16. Copyright © 2017 LUXOFT 16 • Purpose: • Region of interest (ROI) detection • Camera calibration • Detect shakes and shifts • Solution • Based on YOLO (you look only once, http://pjreddie.com/darknet/yolo/) • Processing in real-time Example: Pharma Processing Pipeline (One of the AI Parts)
  • 17. Copyright © 2017 LUXOFT 17 • Wobbling detection • Represent video in temporal space • Search for sinusoid amplitude • RPM detection • Treat paddle as a signal • Fourier transformation for frequency detection • Implemented for 20 FPS • Calibration required Example: Pharma Processing Pipeline (One of the Non- AI Parts) Spatial (left) and temporal (right) representation of video data ROI (left) and signal (right) of paddle appearance
  • 18. Copyright © 2017 LUXOFT 18 Platform selection (Caffe / Torch / TensorFlow / etc) - is like selecting a java app server, or web server: many similarities and hard to chose, however this is what we use: • Availability of models for your task • Deployment compatibility: both enterprise and embedded • Works with your cloud? Like Amazon AWS or MS Azure? • Works on your device? Like ARM or NVidia GPUs? • Distributed processing choices: Cloud / Edge • Embedded optimization opportunities • Maintenance considerations • Support for training models, tools and scenarios <= important to think ahead Platform Selection Guidelines
  • 19. Copyright © 2017 LUXOFT 19 We often hear: “use the latest, greatest model”. However, we’d rather use “simple model for simple data”. Same as “good-enough” concept. Important selection criteria we encounter • Production accuracy • “Cascadability” • Production run-time speed • Training and fine-tuning scenarios: amount and kind of required training data, efforts to train Pharma example: Winner is AlexNet (yes!): quick learner, fast to run, good accuracy on our data Model Selection Guidelines Accuracy Training Epoch
  • 20. Copyright © 2017 LUXOFT 20 • Total number of different classes ~100,000 • We use a cascade of networks • Level 1: Type-search network • Level 2: Different Classification networks for each type • Conventional accuracy metrics for type-search networks: • mAP, Precision, Recall • These metrics always use fixed IoU at =0.5 • IoU = Intersection over Union • Classification accuracy strongly depends on IoU • IoU = 0.5  classification probability =~ 0.68 • IoU > 0.7  classification probability > 0.90 Retail Example: “Cascadability” of a Search Network IoU=1 IoU=0.5 IoU Classification Probability What is IoU:
  • 21. Copyright © 2017 LUXOFT 21 Model Training and Tuning (Data Again!) 3.
  • 22. Copyright © 2017 LUXOFT 22 AI System Development Is More Iterative Traditional SW Engineering Deep Learning SW Engineering
  • 23. Copyright © 2017 LUXOFT 23 A. Create dataset for training 1. Manually classify a limited set of data 2. Train a network (well known architecture) on classified data 3. Test on a new data set, check accuracy 4. Manually classify new data based on network hints 5. Add new data into training set and go to 1 or 2 B. DNN Architecture 1. Tune DNN architecture 2. Train the network on the data set 3. Test on a new data set, check accuracy, goto #1 C. Verify the network Example: Pharma Iterative Training Workflow database: ~5,000 images for each class Uniform distribution of classes required Training Epoch
  • 24. Copyright © 2017 LUXOFT 24 Example: Pharma Iterative Training Workflow DNN Human Legend Crystal clear media Sample dropped Sample Swelling Sample dissolving Precipitate presented Media Foggy Iterative DNN training Use trained DNN for fixing data labelling that follows "Pseudo-Label" technique Visualize your data
  • 25. Copyright © 2017 LUXOFT 25 1. Data coverage - needs to be representative - cover all cases (more than you think) 2. Data balance (normalization) - about equal amount of data for each class/case/scenario 3. Amount of data Model Training: Time to Use Your Data! Acquire Data Prepare Data Six data guidelines that we consider important …to achieve the best results (accuracy, false positives, false negatives). 4. Data formatting - make it work with existing/selected DNN architectures: Like ROI selection, breaking big picture into smaller, video into frames, etc 5. Data synthesis and augmentation - “cat and mirror reflection of a cat are two different cats”. Often easier to transform existing data than to obtain new data 6. Data annotation
  • 26. Copyright © 2017 LUXOFT 26 Data Preparation and Annotation Scenarios Data Annotation (Labeling) Use Cases Real / raw Manual Sometimes good choice for total greenfield. Need human resources. Tools dramatically increase the efficiency Computer, then human Rudimentary AI provides draft annotation. Then humans confirm/correct. Example: house number captcha Human, then computer Humans annotate 1st frame. Then existing CV methods provide object tracking on subsequent frames. Very efficient for dynamic scenes Augmented Automated Use high quality labeled dataset and augment to simulate real-life conditions. Example: “German Traffic Sign” dataset could have been almost entirely synthesized trough augmentation. Synthetic Automated Use 3D rendering software and scripts to generate scenes. Our construction example.
  • 27. Copyright © 2017 LUXOFT 27 Retail Example. Data Augmentation and Synthesis Normal Light Conditions WB Deviations ISO Simulation Year Synthesis
  • 28. Copyright © 2017 LUXOFT 28 Railway Safety Example: Synthetic Data for Training
  • 29. Copyright © 2017 LUXOFT 29 Lessons Learned and Resources !.
  • 30. Copyright © 2017 LUXOFT 30 Lessons Learned model effort data effort data effort
  • 31. Copyright © 2017 LUXOFT 31 • The most important decision is data strategy • Data acquisition: Need lots of data, full coverage, well balanced. • Model decisions: Best overall may be not the best for you. • Pipeline decisions: Cascade and combine: Classic and AI algorithms. • Training: A lot can be achieved by data preparation and synthesis. Annotation tools save millions. • Be prepared to stop. AI development is a very iterative process Lessons Learned
  • 32. Copyright © 2017 LUXOFT 32 • Our website: www.luxoft.com • Our last year talk here at the Summit 2016 about computer vision pipeline optimization: • Available in full on Embedded Vision Alliance website: https://www.embedded-vision.com/platinum-members/luxoft/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit Resources
  • 33. Copyright © 2017 LUXOFT 33 Check out the demos at LUXOFT booth! Extremely optimized artificial intelligence and computer vision pipelines running on low-power embedded platforms and GPU architectures: stereo vision, video and image processing, DNNs; as well as our Hybrid AI Platform that distributes and manages both deep learning and classic computation across cloud and edge devices. *photo of our last year booth
  • 34. Copyright © 2017 LUXOFT 34 Alexey Rybakov ARybakov@luxoft.com LUXOFT 4400 Bohannon Dr Ste 235 Menlo Park, CA 94025 Thank you! :)