Presentation by Serge Palaric, VP Sales and Marketing, EMEA, NVIDIA

1. Serge Palaric, VP Sales & Marketing EMEA - Embedded
JETSON : AI AT THE EDGE

2. 2
NVIDIA: THE AI COMPUTING COMPANY
GPU Computing Visual Computing Artificial Intelligence

3. 3
AMAZING ACHIEVEMENTS IN AI
Play Go Play Doom Learn Paint Style Synthesize Voice
Write Captions Learn Motor Skills Learn to Walk Drive

4. 4
NVIDIA AI COMPUTING ECOSYSTEM
AI-powered
Consumer Services
AI-as-a-Service AI for Enterprise >1,500 AI Startups
iQIYI JD.comGoogleFlickr
Amazon FacebookeBayBaidu
ShazamQihoo 360 Skype Sogou
Periscope PinterestNetflixMicrosoft
TwitterTencent Yandex Yelp
AI for Auto

5. 5
GPU DEEP LEARNING
IS A NEW COMPUTING MODEL
DGX-1
Training Datacenter Inference
Tesla
Inference at the Edge
Jetson

6. 6
WHY AI AT THE EDGE MATTERS
LatencyBandwidth Availability
1 billion cameras WW (2020)
30B Inference/Second
30 images per second
200ms latency
“Billions of intelligent devices will take advantage of DNNs
to provide personalization and localization as GPUs
become faster and faster over the next several years.” —
Tractica
50% of world at less than 8mbps
Only 73% 3G/4G availability WW

7. 7
JETSON: THE PLATFORM FOR AI AT THE EDGE
Industrial InspectionSearch and Rescue
Package DeliveryFactory AutomationEnterprise Collaboration Public Safety
Personal Assist
Service Robotics
Portable Medical Academia and Research

8. 8
AI Smart Industries
Mining
Logistics
Intelligent Factory
Intelligent Warehouse
Smart Operation
….
Smart Camera
NVR
Appliances
Servers
Service Robots
Universities
Logistic
Agriculture
Inspection
Security
Emergency
Planes
Radars
Tanks
Trains
Vision system
….
Cameras
Scanners
Diagnostic
….

9. 9
AI: THE NEW INDUSTRIAL REVOLUTION
Intelligent Factory
Pick and place
Complex/custom tasks
Visual inspection
Task consolidation
Dynamic reconfiguration
Collaborative robotics
Efficiency optimization
Factory simulation
Smart
Operations
Infrastructure inspection
Predictive maintenance
Physical security
Logistics
Autopilot/self-driving
trucks
Robot/drone delivery
and support
Intelligent
Warehouse
Inventory management
Bin picking
Pallet movement
Mining
Equipment automation
Operational safety

10. 10
SMART FACTORY EXAMPLE
AOI
• Autonomous Optical Inspection
Operational efficiency
• Energy efficiency
• Improved Uptime
• Predictive Maintenance
• Make one of many
• Make many of one
• Picking-placing
• Screwing/fastening/riveting
Man-Machine Co-existence
• Collaborative Human-Robot
Traceability
Challenge
• Inspection/Quality
assurance
• DL-Picking and placing
• Cobot applications ( Deep
Learning)
• Big Data analytics
• Real time analysis of data
from sensors
Solution

11. 11
AI FOR INDUSTRIAL AND COMMERCIAL UAVS
Logistics
Warehouse automation
Package delivery
Inspection
Wind turbines
Bridges
Oil rigs
Pipelines
High-voltage power lines
Cell towers
Precision Agriculture
Planting
Spraying
Security
Enterprise security
Ad hoc security systems
Emergency Response
First Responder
Search and Rescue

12. 12
Problem
Aerial inspection is
- Imprecise: often needs
multiple flights
- Time consuming: manual
review of footage
- Dangerous: drone crashes
into subject or operator
Solution
Automate the process
- Vision-enabled navigation
- On-board verification
- On-board fault
classification

13. 13
AI CITY — 1B CAMERAS BY 2020
~1 billion cameras worldwide by 2020
 30 billion inferences/sec
Tesla P40: 2,500 inferences/sec @ 720P
 AI City needs ~10M P40 servers
DATA: 1B cameras, IHS “Video Surveillance Intelligence Service, Aug. 2016”

14. 14NVIDIA CONFIDENTIAL. DO NOT DISTRIBUTE.
FROM CAMERA TO CLOUD
CAMERA APPLIANCE DATACENTER
Trained Neural Networks
+
ESLA
EDGE CLOUD
TRAINING
DATA
JETSON
JETSON
TESLA
TESLA

15. 15
JETSON FOR AI AT THE EDGE
Decode Detectors
Classifiers
Trackers
Composite Encode
4K display
4K video
Jetson TX1 AI Pipeline
JETSON TX1
3 DNNs
Object tracking
4K30 video decode
Video compositing
4K HDMI output
H.265 video encode

16. 16
Jetson TX1
AI Computer on a Module
Advanced tech for intelligent machines
Unmatched performance under 10W
Smaller than a credit card

17. 17
Develop and deploy
Jetson TX1 Developer Kit & Jetson TX1 Module

18. 18
Jetson TX1
Developer Kit
Jetson TX1
Developer Board
5MP Camera

19. 19
Jetpack SDK
Libraries
Developer tools
Design collateral
Developer Forum
Training and Tutorials
Ecosystem
http://developer.nvidia.com/embedded-computing
COMPREHENSIVE DEVELOPER SITE - JEP

20. 20
JETSON TX1
GPU 1 TFLOP/s 256-core Maxwell
CPU 64-bit ARM A57 CPUs
Memory 4 GB LPDDR4 | 25.6 GB/s
Storage 16 GB eMMC
Wifi/BT 802.11 2x2 ac/BT Ready
Networking 1 Gigabit Ethernet
Size 50mm x 87mm
Interface 400 pin board-to-board connector

21. 21
NVIDIA JETPACK 2.3
SDK for embedded AI computing
Deep Learning
TensorRT
cuDNN
DIGITS Workflow
Computer Vision
VisionWorks
OpenCV
Multimedia
ISP Support
Camera Imaging
Video CODEC
Also includes ROS compatibility, OpenGL, advanced developer tools, and much more
CUDA
CUDA Libs
GPU Compute

22. 22
JETSON TX1: 20X DEEP LEARNING EFFICIENCY
Footnotes:
The efficiency was measured using the methodology outlined in the whitepaper:
https://www.nvidia.com/content/tegra/embedded-systems/pdf/jetson_tx1_whitepaper.pdf
Jetson TX1 efficiency is measured at GPU frequency of 691 MHz.
Intel Core i7-6700k efficiency was measured for 4 GHz CPU clock.
GoogLeNet batch size was limited to 64; that is the maximum supported by Jetpack 2.0. With Jetpack 2.3 and TensorRT,
GoogLeNet batch size 128 is also supported for higher perf.
FP16 results for Jetson TX1 are comparable to FP32 results for Intel Core i7-6700k as FP16 incurs no classification
accuracy loss over FP32.
Latest publicly available software versions of IntelCaffe and MKL2017 beta were used.
For Jetpack 2.0 and Intel Core i7, non-zero data was used for both weights and input images. For Jetpack 2.3 (TensorRT)
real images and weights were used.
0
5
10
15
20
25
1 2 64
Images/sec/watt
Batch Size
Inference (GoogLeNet)
Intel core i7-6700k
Jetson TX1/Jetpack 2.1 - Nov '15
Jetson TX1/Jetpack 2.3 - Sept '16

23. 23
DEEP LEARNING END-TO-END
Train
Step 1: Train
Optimize Deploy
NVIDIA DGX-1: Train
your model with
NVIDIA DIGITS
Software on DGX-1,
this highest
performance training
solution for DNNs
TensorRT
TensorRT:
Dramatically speed
up and reduce
memory usage for
your model on Jetson
TX1
Jetson TX1: Deploy
your model to your
fleet of Jetson TX1-
enabled products.
Jetson TX1 is the
highest performance
inference solution
under 10W

24. 24
DEEP LEARNING INSTITUTE
Learn the latest Deep Learning
techniques
Online courses
Deep Learning labs
Nanodegrees
Networking and events
www.nvidia.com/object/deep-learning-institute.html

25. 25
TWO DAYS TO A DEMO
Develop a Deep Learning Demo
on Jetson TX1 in two days
Prerequisites:
• GPU-enabled PC or server
• Jetson TX1 Developer Kit
• One engineer
developer.nvidia.com/embedded/twodaystoademo

26. 26
PARTNERSHIP
Latest Technology
GPU/DL Experts
Global Sales & Marketing Network
Training from Deep Learning Institute
INCEPTION
PROGRAM
CONNECTING WITH AI STARTUPS
nvidia.com/Inception

27. 27
Jetson (corp): www.nvidia.com/object/embedded-systems.html
Jetson (dev): developer.nvidia.com/embedded-computing
Embedded Country selector: www.nvidia.com/embedded
Jetpack (under develop/tools): https://developer.nvidia.com/embedded/develop/tools
Jetpack is a one click installer that will perform BSP installation, plus all relevant SDK (CUDA, cuDNN, TensorRT, VisionWorks)
Success Stories: developer.nvidia.com/embedded/learn/success-stories
Partners and Ecosystem: developer.nvidia.com/embedded/community
Deep Learning Institute: www.nvidia.com/object/deep-learning-institute.html
Two Days To A Demo: developer.nvidia.com/embedded/twodaystoademo
Inception Program: www.nvidia.com/inception
RESOURCES

28. 28
END TO END SOLUTION
ONE ARCHITECTURE FOR ALL
HYPERSCALE HPC
TESLA
VISUALIZATION
QUADRO
RESEARCHERS/ EARLY
ADOPTERS
DGX-1
EDGE COMPUTING
JETSON

29. THANK YOU