Slide 1
Slide 1 text
Χ οί Λ ͭ ͚ ͖ Ε ͳ ͍ ࢲ ͷ
ػ ց ֶ श
M Y M A C H I N E L E A R N I N G
T H AT I C A N ’ T S H O W O F F
K A N A K I TA G A WA
Slide 2
Slide 2 text
AT F I R S T…
Slide 3
Slide 3 text
T H E D E TA I L O F T H I S LT
C U T S B E C A U S E O F
T I M E C O N S T R A I N T S
I’ll talk 30% of that I want to talk.
Slide 4
Slide 4 text
I F Y O U WA N T T O
H E A R M O R E
Slide 5
Slide 5 text
P L E A S E C O M E T O
J AW S - U G K O B E .
Slide 6
Slide 6 text
Welcome to the crazy group
@JAWS-UG KOBE Facebook group
Slide 7
Slide 7 text
A G E N D A
•Who am I?
•LAST YEAR
•What did I do for
machine learning?
•How to use AWS
SageMaker
•Let’s try
Slide 8
Slide 8 text
W H O A M I ?
Slide 9
Slide 9 text
K A N A
K I TA G A WA
• Nickname:Tiger
#MakikomiTiger
• Kansai University student
3rd grade
(major:media art)
• Internship @ Serverworks
• I want to be friend with
AWS Lambda and
Educate
Slide 10
Slide 10 text
L A S T Y E A R
W H AT D I D I D O ?
Slide 11
Slide 11 text
.BS
JAWS DAYS 2018
Slide 12
Slide 12 text
A F T E R T H E D AY,
M Y L I F E B E G A N T O
C H A N G E .
Slide 13
Slide 13 text
@JAWS DAYS
@re:Invent
Taking Photos
Slide 14
Slide 14 text
I H A D
M A C H I N E L E A R N I N G
T R A I N I N G C L A S S .
Because of kind teacher
Slide 15
Slide 15 text
I WA N T T O S AY
“ I C A N D O W I T H
M A C H I N E L E A R N I N G . ”
I think the words cool.
Slide 16
Slide 16 text
J U S T D O I T ! !
Slide 17
Slide 17 text
W H AT D I D I D O W I T H
M A C H I N E L E A R N I N G ?
Slide 18
Slide 18 text
• Having machine learning training class
• Supervised/Unsupervised learning
• Doing assignment with the book
“Machine Learning with Python
(O’REILLY)”
• Using iris dataset
I think it difficult.
Slide 19
Slide 19 text
W H AT I S
I R I S D ATA S E T ?
•Be distributed in UCI Machine Learning
Repository
•Iris petal length and width, and calyx
length and width
•The 3 type(setosa, virginica,
versicolor)*50 samples
Slide 20
Slide 20 text
3 T Y P E S
Slide 21
Slide 21 text
O N E T I M E , I WAT C H E D
T H E S I T E O F T H E D ATA S E T.
Slide 22
Slide 22 text
T H I S I S P E R H A P S T H E B E S T
K N O W N D ATA B A S E T O B E
F O U N D I N T H E PAT T E R N
R E C O G N I T I O N L I T E R AT U R E .
https://archive.ics.uci.edu/ml/datasets/iris
Slide 23
Slide 23 text
I R I S D ATA S E T ?
I S N ’ T I T B A S I C ?
I said I do with Iris dataset
@SOME JAWS
I think it difficult.
Slide 24
Slide 24 text
T H E B A S I S I S
I M P O R TA N T.
I can’t show off.
Slide 25
Slide 25 text
M A K E
T H E C O U R S E C O N T E N T
E A S I E R
USE Amazon
SageMaker
Slide 26
Slide 26 text
G E N E R A L F L O W O F
M A C H I N E L E A R N I N G
Make
Sample data
training
of
the model
deploy
the model
Slide 27
Slide 27 text
A M A Z O N S A G E M A K E R
• Preprocessing sample data on Jupyter
notebook
• You can use the algorithm Amazon
SageMaker offer.
• You can push request to model for inference
use boto or high revel Python library
• Host model, separate
Slide 28
Slide 28 text
L E T ’ S T RY.
Slide 29
Slide 29 text
I H AV E N ’ T U S E D
A M A Z O N
S A G E M A K E R .
Slide 30
Slide 30 text
AT F I R S T,
R E A D A N D T RY T U T O R I A L
( U S E M N I S T D ATA S E T ) .
Slide 31
Slide 31 text
I T R I E D T O D O L I K E
T H I S T U T O R I A L .
B U T I C A N ’ T.
Maybe, I can’t understand it well.
Slide 32
Slide 32 text
I S E A R C H F O R
“ I R I S D ATA S E T
A W S S A G E M A K E R ”
Slide 33
Slide 33 text
@AWS document
https://docs.aws.amazon.com/ja_jp/sagemaker/latest/dg/tf-
examples.html
Slide 34
Slide 34 text
T H E B A S I S I S
I M P O R TA N T.
I can’t show off.
Slide 35
Slide 35 text
J U S T D O I T ! !
with document
Slide 36
Slide 36 text
A F T E R M A K E N O T E B O O K
I N S TA N C E
Do Initializing variables
Slide 37
Slide 37 text
C O N T E N U E
https://docs.aws.amazon.com/ja_jp/sagemaker/latest/
dg/tf-example1-train.html
Slide 38
Slide 38 text
M O D U L E N O T F O U N D E R R O R : N O
M O D U L E N A M E D ' T E N S O R F L O W '
Error message
Slide 39
Slide 39 text
I D I D A C C O R D I N G T O
T H E D O C U M E N T… ?
Slide 40
Slide 40 text
S A M E P R O B L E M S
Slide 41
Slide 41 text
T H E S O L U T I O N
Slide 42
Slide 42 text
W H E R E W I L L I W R I T E … ?
Slide 43
Slide 43 text
I F O U N D I T.
Slide 44
Slide 44 text
T E R M I N A L I S H E R E ! ! !
Slide 45
Slide 45 text
Y E S , Y E S !
Y O U C A N D O I T ! ! !
Slide 46
Slide 46 text
T RY A G A I N
https://docs.aws.amazon.com/ja_jp/sagemaker/latest/
dg/tf-example1-train.html
Slide 47
Slide 47 text
Error message AGAIN
Slide 48
Slide 48 text
No content
Slide 49
Slide 49 text
I T R I E D T O S E E O T H E R
PA G E .
Slide 50
Slide 50 text
A C O L L E C T I O N O F A M A Z O N
S A G E M A K E R S A M P L E N O T E B O O K S .
Slide 51
Slide 51 text
WAT C H N O T E B O O K
Slide 52
Slide 52 text
Look carefully
Slide 53
Slide 53 text
I M I S S E D
N O T E B O O K .
Slide 54
Slide 54 text
C H A N G E A N D D O I T.
Slide 55
Slide 55 text
I T M O V E S ! ! ! ! !
Slide 56
Slide 56 text
M A K E T E N S O R F L O W
C L A S S I N S TA N C E
Slide 57
Slide 57 text
G E T T H E I N F O R M AT I O N O F T H E
T R A I N I N G J O B
Slide 58
Slide 58 text
D E P L O Y T H E M O D E L
Slide 59
Slide 59 text
AT L A S T…
Slide 60
Slide 60 text
I N O T I C E D .
Slide 61
Slide 61 text
I ’ M S O R RY…
Slide 62
Slide 62 text
I S H O U L D C H E C K
C A R E F U L LY .
Slide 63
Slide 63 text
W E ’ R E WA I T I N G F O R
C H A L L E N G E R .
Slide 64
Slide 64 text
I’m looking for job .
Please talk with me.
I want to provide a service
that does not concern
the country and sex of the person using it.
Slide 65
Slide 65 text
T H A N K Y O U F O R L I S T E N I N G ! ! !
@MakikomiTiger Kana Kitagawa