Tweet
Tweet

Slide 1

Slide 1 text

$PPLQBEͰ Կ͍ͭͬͯ͘Δʁ ୈճ̘̫ษڧձˏؔ౦ !MVOBSEPH

Slide 2

Slide 2 text

ࣗݾ঺հ • Leszek Rybicki • @lunardog • Poland • 2016 Cookpad R&D

Slide 3

Slide 3 text

ࣗݾ঺հ • 1990 BASIC, ASM, C • 1995 Pascal, VB • 2000 C++ • 2005 D • 2010 C, Python • 2012 PHP • 2015 JS • 2016 Python

Slide 4

Slide 4 text

1"35*
 ྉཧه࿥

Slide 5

Slide 5 text

http://techlife.cookpad.com/entry/2017/09/14/161756

Slide 6

Slide 6 text

'PPE/POGPPE twitter: @teenybiscuit

Slide 7

Slide 7 text

'PPE

Slide 8

Slide 8 text

w QFPQMFBSFOPUGPPE w QFUTBSFOPUGPPE w QPUUFEQMBOUTBSFOPUGPPE w FWJMBMJFOTBSFOPUGPPE w JGJUIBTUFYUPOJU 
 JU`TQSPCBCMZOPUGPPE /PUGPPE

Slide 9

Slide 9 text

DCNN global pooling fully connected RGB x 240 x 240 pixels 2048 features x 8 x 8 one-hot class vector 2048 features food plant person pet other

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

GPPEOPOGPPEBDDVSBDZ QSFDJTJPOSFDBMM

Slide 12

Slide 12 text

No content

Slide 13

Slide 13 text

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

*."(*/"5*0/

Slide 16

Slide 16 text

3&"-*5:

Slide 17

Slide 17 text

5IF w QFPQMFXJUIGPPE w GPPEXJUIPUIFSJUFNT w GPPEXJUIUFYU w GPPE CVUTNBMMJOQIPUP w FEJCMFQMBOUT

Slide 18

Slide 18 text

3VMF "QIPUPUIBU
 DBOCFDSPQQFEUP DPOUBJONPTUMZGPPE
 JTBQIPUPPGGPPE

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

1BUDIJU

Slide 21

Slide 21 text

No content

Slide 22

Slide 22 text

GPPE OPOGPPE

Slide 23

Slide 23 text

DCNN global pooling fully connected RGB x 240 x 240 pixels 2048 features x 8 x 8 one-hot class vector 2048 features DCNN global pooling 1x1 convo layer RGB x 240 x 240 pixels 2048 features x 8 x 8 one-hot class vector food not food not

Slide 24

Slide 24 text

w %$//*ODFQUJPO7 w USBJOFEPOBMMGPPEBOE BMMOPOGPPEQIPUPT
 USBJOJOHJTSFBMMZGBTU w BWFSBHFQPPMJOH w OPHMPCBMQPPMJOHMBZFS BGUFSUSBJOJOH w VTFSFTVMUJOHIFBUNBQ GPSDMBTTJpDBUJPO DCNN global pooling 1x1 convo layer RGB x 512 x 512 pixels 2048 features x 14 x 14 one-hot class vector food not

Slide 25

Slide 25 text

GPPEOPOGPPEBDDVSBDZ QSFDJTJPOSFDBMM

Slide 26

Slide 26 text

GPPEOPOGPPEBDDVSBDZ QSFDJTJPOSFDBMM

Slide 27

Slide 27 text

http://techlife.cookpad.com/entry/2017/09/14/161756 https://storialaw.jp/blog/3420

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

image food person test images from https://snappygoat.com/

Slide 30

Slide 30 text

image food person test images from https://snappygoat.com/

Slide 31

Slide 31 text

$)"--&/(&

Slide 32

Slide 32 text

$-"44*':5)*4

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

test images from https://snappygoat.com/

Slide 38

Slide 38 text

test images from https://snappygoat.com/

Slide 39

Slide 39 text

%&.0

Slide 40

Slide 40 text

·ͱΊ •working on food images is an interesting challenge! • food / non-food: • multi-class classifier is better than two class • fully-convolutional classifier is better than multi-class • multi-class object detection from single-object training data

Slide 41

Slide 41 text

No content