Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
GIDS18_SupriyaSrivatsa.pdf
Search
Supriya Srivatsa
April 24, 2018
Technology
0
520
GIDS18_SupriyaSrivatsa.pdf
Supriya Srivatsa
April 24, 2018
Tweet
Share
More Decks by Supriya Srivatsa
See All by Supriya Srivatsa
Forgotten Histories
supriyasrivatsa
0
580
The Story of Villagers, Marbles and Oh, A Blockchain!
supriyasrivatsa
0
550
Going Multiplatform With Kotlin
supriyasrivatsa
0
650
Mobile, AI and TensorFlow
supriyasrivatsa
0
530
Other Decks in Technology
See All in Technology
2025-07-06 QGIS初級ハンズオン「はじめてのQGIS」
kou_kita
0
170
AI時代の開発生産性を加速させるアーキテクチャ設計
plaidtech
PRO
3
150
生まれ変わった AWS Security Hub (Preview) を紹介 #reInforce_osaka / reInforce New Security Hub
masahirokawahara
0
470
Oracle Database@Google Cloud:サービス概要のご紹介
oracle4engineer
PRO
0
110
american airlines®️ USA Contact Numbers: Complete 2025 Support Guide
supportflight
1
110
Lufthansa ®️ USA Contact Numbers: Complete 2025 Support Guide
lufthanahelpsupport
0
190
整頓のジレンマとの戦い〜Tidy First?で振り返る事業とキャリアの歩み〜/Fighting the tidiness dilemma〜Business and Career Milestones Reflected on in Tidy First?〜
bitkey
2
16k
高速なプロダクト開発を実現、創業期から掲げるエンタープライズアーキテクチャ
kawauso
2
9.2k
AWS認定を取る中で感じたこと
siromi
1
190
生成AI時代の開発組織・技術・プロセス 〜 ログラスの挑戦と考察 〜
itohiro73
1
460
第4回Snowflake 金融ユーザー会 Snowflake summit recap
tamaoki
1
280
Backlog ユーザー棚卸しRTA、多分これが一番早いと思います
__allllllllez__
1
150
Featured
See All Featured
Building an army of robots
kneath
306
45k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
35
2.4k
Writing Fast Ruby
sferik
628
62k
A designer walks into a library…
pauljervisheath
207
24k
Agile that works and the tools we love
rasmusluckow
329
21k
Six Lessons from altMBA
skipperchong
28
3.9k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
60k
Faster Mobile Websites
deanohume
307
31k
4 Signs Your Business is Dying
shpigford
184
22k
Automating Front-end Workflow
addyosmani
1370
200k
Transcript
TensorFlow for Mobile Machine Learning Supriya Srivatsa, Software Engineer, Xome
Overview • AI and Mobile – the Convergence • Inference
– Today and Tomorrow • TensorFlow Primer • TensorFlow in your Pocket – TensorFlow Mobile – TensorFlow Lite • PokéDemo • Applications and Case Studies • Q & A
AI AND MOBILE – THE CONVERGENCE
INFERENCE - TODAY AND TOMORROW
The “Transfer to Infer” Approach
Why On Device Prediction • Data Privacy • Poor Internet
Connection • Questionable User Experience
Why On Device Prediction Case Study: Portrait Mode
TENSORFLOW PRIMER
None
TensorFlow – Deferred Execution Model (Building the Computational Graph) import
tensorflow as tf num1 = tf.constant(5) num2 = tf.constant(10) sum = num1 + num2 print(sum) #O/P: Tensor("add:0", shape=(), dtype=int32)
TensorFlow – Deferred Execution Model (Running the Computational Graph) import
tensorflow as tf num1 = tf.constant(5) num2 = tf.constant(10) sum = num1 + num2 with tf.Session() as sess: print(sess.run(sum)) #O/P: 15
None
None
TENSORFLOW IN YOUR POCKET
Pick Your Weapon • Choose a pre-trained TF Model –
Inception V3 Model – MNIST – Smart Reply – Deep Speech • Build a TF Model
Sharpen your Sword • Retrain Model as required.
Neural Network and Transfer Learning
None
TENSORFLOW MOBILE VS TENSORFLOW LITE
TensorFlow Lite • Smaller binary size, better performance. • Ability
to leverage hardware acceleration. • Only supports a limited set of operators.
TensorFlow Mobile and TensorFlow Lite
TensorFlow Mobile and TensorFlow Lite
TensorFlow Mobile and TensorFlow Lite
Optimization • optimize_for_inference • Quantization
Quantization • Round it up • Transform: round_weights • Compression
rates: ~8% => ~70% • Shrink down node names • Transform: obfuscate_names • Eight bit calculations
Quantization – Eight Bit Calculations
Optimization – Before and After
TensorFlow Mobile and TensorFlow Lite
TensorFlow Mobile and TensorFlow Lite
TensorFlow Lite • TOCO – TensorFlow Lite Optimizing Converter –
Pruning unused nodes. – Performance Improvements. – Convert to tflite format. (Generate FlatBuffer file.)
ü Frozen ü Optimized, Quantized ü .tflite / FlatBuffer
How does it work?
Packaging App and Model
CODE AWAY J
Code Away – Gradle Files
Code Away :) Tflite = new Interpreter(<loadmodelfile>) tflite.run(giveInput, outputObject) •
Create Interpreter • Run model with input, fetch output.
POKÉDEMO!
PokéDemo
APPLICATIONS AND CASE STUDIES
Coca Cola
Google Assistant
Smart Reply
Q & A
Thank you