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
Mobile, AI and TensorFlow
Search
Supriya Srivatsa
October 05, 2017
Technology
0
530
Mobile, AI and TensorFlow
Supriya Srivatsa
October 05, 2017
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
GIDS18_SupriyaSrivatsa.pdf
supriyasrivatsa
0
520
Other Decks in Technology
See All in Technology
Delta airlines Customer®️ USA Contact Numbers: Complete 2025 Support Guide
deltahelp
0
880
American airlines ®️ USA Contact Numbers: Complete 2025 Support Guide
airhelpsupport
0
390
AI エージェントと考え直すデータ基盤
na0
15
4.7k
VS CodeとGitHub Copilotで爆速開発!アップデートの波に乗るおさらい会 / Rapid Development with VS Code and GitHub Copilot: Catch the Latest Wave
yamachu
2
180
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
54
21k
[ JAWS-UG千葉支部 x 彩の国埼玉支部 ]ムダ遣い卒業!FinOpsで始めるAWSコスト最適化の第一歩
sh_fk2
2
120
United airlines®️ USA Contact Numbers: Complete 2025 Support Guide
unitedflyhelp
0
330
ビジネス職が分析も担う事業部制組織でのデータ活用の仕組みづくり / Enabling Data Analytics in Business-Led Divisional Organizations
zaimy
1
190
United™️ Airlines®️ Customer®️ USA Contact Numbers: Complete 2025 Support Guide
flyunitedguide
0
330
LLM時代の検索
shibuiwilliam
2
410
開発生産性を組織全体の「生産性」へ! 部門間連携の壁を越える実践的ステップ
sudo5in5k
3
7.4k
スタートアップに選択肢を 〜生成AIを活用したセカンダリー事業への挑戦〜
nstock
0
250
Featured
See All Featured
Practical Orchestrator
shlominoach
189
11k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
Music & Morning Musume
bryan
46
6.6k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
35
2.4k
Thoughts on Productivity
jonyablonski
69
4.7k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
357
30k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
3.9k
YesSQL, Process and Tooling at Scale
rocio
173
14k
Facilitating Awesome Meetings
lara
54
6.4k
Optimising Largest Contentful Paint
csswizardry
37
3.3k
Documentation Writing (for coders)
carmenintech
72
4.9k
Build your cross-platform service in a week with App Engine
jlugia
231
18k
Transcript
Mobile, AI and Tensorflow Supriya Srivatsa
None
None
NEURAL NETWORKS Human anatomy inspired learning network.
Neural Networks
Neural Networks
Neural Network – A Peek Inside
Deep Neural Network
PREDICTION AND INFERENCE How it works today. How it shall
work tomorrow.
“Transfer to Infer” Approach
Why On-Device Prediction • Data Privacy • Poor internet connections
• Questionable user experience
To The Rescue…
TensorFlow • Tensor: N Dimensional Arrays • Open source software
library for numerical computation using data flow graphs.
TensorFlow – Data Flow Graphs • Nodes represent mathematical functions
• Edges represent tensors.
Tensorflow – “Deferred Execution” Model • Graph first. Computation Afterward.
import tensorflow as tf x = tf.constant(10) y = tf.Variable(x + 5) print(y)
Tensorflow – “Deferred Execution” Model • Graph first. Computation Afterward.
import tensorflow as tf x = tf.constant(10) y = tf.Variable(x + 5) model = tf.global_variables_initializer() with tf.Session() as session: session.run(model) print(session.run(y))
None
None
Packaging the App and the Model
QUANTIZATION Compress. And Compress More.
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
Quantization - Eight Bit Calculations
None
IMPLEMENTATION Code Away! ☺
Implementation build.gradle buildscript { repositories { jcenter() } dependencies {
classpath 'com.android.tools.build:gradle:2.3.0' } }
Implementation 1. Load 2. Feed 3. Run 4. Fetch
Implementation 1. Load the model 2. Feed in the input
3. Run the model 4. Fetch the output TensorFlowInferenceInterface inferenceInterface = new TensorFlowInferenceInterface(assetManager, modelFile);
Implementation 1. Load the model 2. Feed in the input
3. Run the model 4. Fetch the output // feed(String s, float[] floats, long… longs) inferenceInterface.feed(inputName, floatValues, 1, inputSize, inputSize, 3);
Implementation 1. Load the model 2. Feed in the input
3. Run the model 4. Fetch the output inferenceInterface.run(outputNames);
Implementation 1. Load the model 2. Feed in the input
3. Run the model 4. Fetch the output // fetch(String s, float[] floats) inferenceInterface.fetch(outputName, outputs);
APPLICATIONS Awesomeness.
Google Translate
None
None