With IoT, machine learning is going everywhere. Using Amazon SageMaker it's never been easier to build Intelligent Things. In this session we look at how we can push intelligence from cloud-trained models to the edge using AWS Greengrass and explore how devices such as AWS DeepLens make it easy to bring intelligence to your things.
2. Agenda
• Intro to AWS DeepLens
• Cover AWS Sagemaker and AWS Greengrass
• Build and Train a Model using AWS Sagemaker
• Deploy Model and Inference code using AWS Greengrass
• Demo!
3.
4. AWS DeepLens
HD video camera
Custom-designed
deep learning
inference engine
Micro-SD
Mini-HDMI
USB
USB
Reset
Audio out
Power
HD video camera
with on-board
compute
optimised for
deep learning
Tutorials,
examples, demos,
and pre-built
models
From
unboxing to
first inference
in <10 minutes
Integrates with
Amazon
SageMaker and
AWS Lambda
10
MIN
5. Sample Projects
Detect and recognise objects.
OBJECT DETECTION
Classify your food.
HOT DOG NOT HOT DOG
Detect a cat or dog.
CAT AND DOG
Transfer a style onto video.
ARTISTIC STYLE TRANSFER
Recognise common activities.
ACTIVITY RECOGNITION
Detect faces of people.
FACE DETECTION
6. But Why Did We Really Build
This? What Is The Problem?
11. AWS Greengrass: Local Compute, Messaging &
Data Caching
Local
compute
Local
data caching
Secure
communications
Local
messaging
12. AWS Greengrass: How It Works
Built into
devices at
manufacture
Install the Greengrass
runtime
Lambda functions
on AWS & devices
Manage from
AWS Console
Same programming
model
Local
communication
and orchestration
13. Amazon SageMaker
Build, train, and deploy machine learning models
Collect and
prepare
training
data
Choose and
optimise your
ML algorithm
Set up and
manage
environments
for training
Train and
tune model
(trial and
error)
Deploy model
in production
Scale and
manage the
production
environment
14. Amazon SageMaker
Fully managed
hosting with auto-
scaling
One-click
deployment
Pre-built
notebooks
for common
problems
Built-in, high
performance
algorithms
One-click
training
Hyperparameter
optimisation
BUIL D TRAIN DE PL OY
15. AWS Greengrass: ML Inference
U s e A W S
G r e e n g r a s s
c o n s o l e t o
t r a n s f e r m o d e l s
t o y o u r d e v i c e s
I n f e r e n c e
o n t h e
d e v i c e
D e v i c e s t a k e
a c t i o n
q u i c k l y –
e v e n w h e n
d i s c o n n e c t e d
B u i l d a n d t r a i n
m o d e l s i n t h e
c l o u d
19. Build An Amazon SageMaker Model
• Create a Notebook instance
• Import your Data
• Train your model
• Check out reinvent-2017-deeplens-
workshop from github