Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
TesnsorFlowJs.pdf
Search
Hiren Dave
October 12, 2019
Technology
110
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
TesnsorFlowJs.pdf
Hiren Dave
October 12, 2019
Transcript
35 slides
Hiren Dave Machine Learning in Browser With TensorFlow.js
What is a Machine Learning?
Data Training Prediction End Machine Learning in Simple Terms
Why ML in Browser?
Proprietary + Confidential No Drivers / No Installs Just Downloads
Source: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis non erat sem $ python –v $ pip install pandas $ pip install django $ pip install numpy $ pip3 install flask $ pip install tensorflow $ pip install sklearn $ python –v $ pip install pandas $ pip install django $ pip install numpy $ pip3 install flask $ pip install tensorflow $ pip install sklearn <script src="https://cdn.jsdelivr.net/npm/@tensorflo w/
[email protected]
/dist/tf.min.js"></script>
Proprietary + Confidential Highly Interactive Source: Lorem ipsum dolor sit
amet, consectetur adipiscing elit. Duis non erat sem $ step 1 – loss – 5.0681 (10 sec/step) $ step 2 – loss – 5.0681 (10 sec/step) $ step 3 – loss – 5.0681 (10 sec/step) $ step 4 – loss – 5.0681 (10 sec/step) $ step 5 – loss – 5.0681 (10 sec/step) $ step 6 – loss – 5.0681 (10 sec/step) $ step 7 – loss – 5.0681 (10 sec/step) $ step 8 – loss – 5.0681 (10 sec/step)
Proprietary + Confidential Access to Sensors Source: Lorem ipsum dolor
sit amet, consectetur adipiscing elit. Duis non erat sem GPS Microphone Camera Gyroscope
Proprietary + Confidential Can Work Offline / Data Privacy Source:
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis non erat sem
Proprietary + Confidential Web Is Every Where Source: Lorem ipsum
dolor sit amet, consectetur adipiscing elit. Duis non erat sem
History of TensorFlow.js
deeplearn.js • Release in August 2017 • GPU Accerelerated via
WebGL • Allows Inference and Training in Browser
What it Offers?
With TensorFlow.js you can • Create models directly in browser
• Import pretrained models for inference • Retrain imported models
TensorFlow.js Architecture
Proprietary + Confidential API Layers API OPs API Browser WebGL
Keras Model TensorFlow Saved Model
A Quick Example
Let’s understand Basic Terms
What is a Tensor • It is n – dimensional
Array • Each element in Tensor has same data type • Retrain imported models
const tensor = tf.tensor(0.1).variable();
What is an Epoch? • When you have huge data
• Divide it in batches for training • Feed batches one by one for training • When all batches are done, that’s the EPOCH
What are the loss functions? • You have huge data
for training • Feed data one by one for training • How to ensure model’s output is correct • A loss function maps decisions to their associated costs.
Create / Load Model in Browser
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfj
[email protected]
/dist/tf.min.js"></script>
Using TensorFlow.js with NodeJs
npm install @tensorflow/tfjs-node
A Quick Example
Save Convert Load End Use Python Model with TensorFlow.js Python
TensorFlow.js
Use Existing Model
Let’s See Some ML Examples
Text Classification • Detect text toxicity • Use prebuilt model
Object Detection • Detect Object Through Webcam
Image Classification
TensorFlow.js Limitations
Hiren Dave, AbhayTech Solutions LLP. @hjdave Thank you!
Q&A
More Decks by Hiren Dave
See All by Hiren Dave
Demystifying UI security
hirendave
0
55
Whats New in Web Platform from Google I/O 2022
hirendave
0
98
Introduction to Web3.0
hirendave
0
270
Using Vite with Laravel
hirendave
0
67
Step Into World of NodeJS
hirendave
0
53
Transfer Learning with TensorFlow
hirendave
0
83
Reactive Programming in Angular with RxJs
hirendave
0
91
AMP-lify your Web Apps
hirendave
0
44
Laravel Eloquent & Its Hidden Power
hirendave
0
140
Other Decks in Technology
See All in Technology
Go でトランザクション、どう書いてますか?
knwoop
1
600
メディアアートを〈拡張〉する——器官学と個体化論を手がかりに
_kotobuki_
0
130
社内アプリ基盤「Quartz」による、 非エンジニアとAIに本番デプロイを 任せても壊れないプラットフォームの設計
staka121
PRO
1
230
gradle-best-practices 使ってみた
mikanichinose
0
230
Is the Website Dying?
miriamschwab
0
160
業務の傍らで進める改善ループエンジニアリング
bengo4com
1
240
その修正で本当に速くなったのか? k6とOpenTelemetryで確かめる性能改善 / Performance review with k6 and OpenTelemetry
ymotongpoo
3
440
Dark Web - Como o Cibercrime Opera na Internet
nicholsjasper
0
110
さようならSSH鍵、こんにちはゼロトラスト ― AIフレンドリーで快適な自宅鯖SSH
atalie2m
14
7.5k
現場に渡し、構造で守る AI エージェントを活用したセルフサーブのデータ基盤の運用
legalontechnologies
PRO
0
110
Webメール開発を大幅に変えたJMAPというゲームチェンジャー
tascript
1
160
コピーオンライト型ファイルシステムと ランダム書き込み
sat
PRO
2
140
Featured
See All Featured
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
670
Accessibility Awareness
sabderemane
1
310
How People are Using Generative and Agentic AI to Supercharge Their Products, Projects, Services and Value Streams Today
helenjbeal
2
410
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
659
62k
Evolving SEO for Evolving Search Engines
ryanjones
0
370
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
610
Visualization
eitanlees
153
17k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
22k
YesSQL, Process and Tooling at Scale
rocio
174
15k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
850
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
3
1.5k
<Decoding/> the Language of Devs - We Love SEO 2024
nikkihalliwell
1
380