Superpower Your Android apps with ML: Android 11

Slide 1

Slide 1 text

rishit.tech Superpower Your Android apps with ML Rishit Dagli @rishit_dagli

Slide 2

Slide 2 text

rishit.tech $whoami ● 11 Grade Student ● TEDx and Ted-Ed Speaker ● ♡ Hackathons and competitions ● ♡ Research ● My coordinates - https://www.rishit.tech rishit_dagli Rishit-dagli

Slide 3

Slide 3 text

Acknowledgements ● Sayak Paul (ML GDE) ● Khanh LeViet (Google) ● Hoi Lam (Google) rishit.tech

Slide 4

Slide 4 text

rishit.tech Ideal Audience ● Mobile Devs looking for ways to build smarter apps ● Mobile Devs looking for ways to integrate ML in their existing apps easily

Slide 5

Slide 5 text

rishit.tech Why care about ML in Android?

Slide 6

Slide 6 text

rishit.tech Why care about on-device ML in Android?

Slide 7

Slide 7 text

Created by Rishit Dagli for his talk at GDG Ahmedabad This slide is skipped while presenting

Slide 8

Slide 8 text

Created by Rishit Dagli for his talk at GDG Ahmedabad This slide is skipped while presenting

Slide 9

Slide 9 text

rishit.tech

Slide 10

Slide 10 text

rishit.tech

Slide 11

Slide 11 text

rishit.tech

Slide 12

Slide 12 text

rishit.tech

Slide 13

Slide 13 text

rishit.tech Why should you care? ● Power consumption

Slide 14

Slide 14 text

rishit.tech Why should you care? ● Power consumption ● Inference time

Slide 15

Slide 15 text

rishit.tech Why should you care? ● Power consumption ● Inference time ● Network availability

Slide 16

Slide 16 text

rishit.tech Why should you care? ● Power consumption ● Inference time ● Network availability ● Privacy

Slide 17

Slide 17 text

rishit.tech ML Model Binding Plugin

Slide 18

Slide 18 text

rishit.tech ML Model Binding Plugin What’s new for on-device ML in Android? Easier to use Enable Hardware acceleration Faster Development

Slide 19

Slide 19 text

rishit.tech Importing a TF Lite Model

Slide 20

Slide 20 text

rishit.tech Importing a TF Lite Model

Slide 21

Slide 21 text

rishit.tech Importing a TF Lite Model

Slide 22

Slide 22 text

rishit.tech Using the TF Lite Model

Slide 23

Slide 23 text

rishit.tech Creating an instance of model

Slide 24

Slide 24 text

rishit.tech Processing images

Slide 25

Slide 25 text

rishit.tech Passing in data

Slide 26

Slide 26 text

rishit.tech Passing in data

Slide 27

Slide 27 text

rishit.tech Passing in data

Slide 28

Slide 28 text

rishit.tech Passing in data

Slide 29

Slide 29 text

rishit.tech Adding Labels rishit.tech

Slide 30

Slide 30 text

rishit.tech We are done! ☺ rishit.tech

Slide 31

Slide 31 text

rishit.tech GPU acceleration

Slide 32

Slide 32 text

rishit.tech A new ML Kit

Slide 33

Slide 33 text

rishit.tech A new ML Kit What does the latest ML Kit focus on? On-Device ML Better customizability Generic use cases

Slide 34

Slide 34 text

rishit.tech Face detection Barcode scanning Image labeling Smart Reply Language Identification Vision Natural Language Object detection and tracking On-device Translation Text recognition Digital Ink Recognition Pose Detection N EW N EW

Slide 35

Slide 35 text

rishit.tech Setup the model

Slide 36

Slide 36 text

rishit.tech Customize the model

Slide 37

Slide 37 text

rishit.tech

Slide 38

Slide 38 text

rishit.tech TF Lite Model Maker ● High performance ● Super easy to use ● High customization too!

Slide 1

Slide 1 text

Slide 2

Slide 2 text

Slide 3

Slide 3 text

Slide 4

Slide 4 text

Slide 5

Slide 5 text

Slide 6

Slide 6 text

Slide 7

Slide 7 text

Slide 8

Slide 8 text

Slide 9

Slide 9 text

Slide 10

Slide 10 text

Slide 11

Slide 11 text

Slide 12

Slide 12 text

Slide 13

Slide 13 text

Slide 14

Slide 14 text

Slide 15

Slide 15 text

Slide 16

Slide 16 text

Slide 17

Slide 17 text

Slide 18

Slide 18 text

Slide 19

Slide 19 text

Slide 20

Slide 20 text

Slide 21

Slide 21 text

Slide 22

Slide 22 text

Slide 23

Slide 23 text

Slide 24

Slide 24 text

Slide 25

Slide 25 text

Slide 26

Slide 26 text

Slide 27

Slide 27 text

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

Slide 31

Slide 31 text

Slide 32

Slide 32 text

Slide 33

Slide 33 text

Slide 34

Slide 34 text

Slide 35

Slide 35 text

Slide 36

Slide 36 text

Slide 37

Slide 37 text

Slide 38

Slide 38 text

Slide 39

Slide 39 text

Slide 40

Slide 40 text