Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Speaker Deck
PRO
Sign in
Sign up for free
YGLF_2019.pdf
Asim Hussain
April 05, 2019
Technology
1
100
YGLF_2019.pdf
Asim Hussain
April 05, 2019
Tweet
Share
More Decks by Asim Hussain
See All by Asim Hussain
JavaScript Saves The World - DotJS 2019
jawache
0
740
Saving the world, one line at a time [CodeLeaders Australia 2019]
jawache
0
55
AI + JavaScript Rocks @ GDGDevFest UA 2018
jawache
0
32
How to hack a web app? WebConfAsia 2018
jawache
0
60
How to scale an SPA? @ AmsterdamJS 2018
jawache
0
17
How to hack an Angular app? - ngConf 2018
jawache
0
590
Getting started with node.js @ AngleBrackets 2018
jawache
1
160
How to hack an Angular app? @ ngVikings 2018
jawache
1
940
How to hack a python app? @ PyCaribbean 2018
jawache
0
140
Other Decks in Technology
See All in Technology
Data in Google I/O - IO Extended GDG Seoul
kennethanceyer
0
150
FoodTechにおける商流・金流・物流の進化/Evolution of Commercial, Financial, and Logistics in FoodTech
dskst
0
410
データをモデリングしていたら、組織をモデリングし始めた話 / engineers-in-carta-vol3-data-engineer
pei0804
4
3.3k
Citizen 개발기
outsider
0
280
紙にまつわる苦しみを機能化してきた カミナシの歴史
kaminashi
0
1.3k
Security Hub のマルチアカウント 管理・運用をサーバレスでやってみる
ch6noota
0
850
QiitaConference2022
fuwasegu
0
190
機械学習システムアーキテクチャ入門 #1
asei
3
1.2k
UIKitのアップデート #WWDC22
akatsuki174
4
340
miisan's career talk
mii3king
0
220
IoTLT88-NTKanazawa-laundry-dry
yukima0707
0
230
Meet passkeys
satotakeshi
1
120
Featured
See All Featured
Building Better People: How to give real-time feedback that sticks.
wjessup
344
17k
The Cult of Friendly URLs
andyhume
68
4.8k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
351
21k
Navigating Team Friction
lara
175
11k
Fireside Chat
paigeccino
12
1.3k
Practical Orchestrator
shlominoach
178
8.6k
What’s in a name? Adding method to the madness
productmarketing
11
1.6k
Done Done
chrislema
174
14k
Typedesign – Prime Four
hannesfritz
34
1.4k
What's in a price? How to price your products and services
michaelherold
229
9.4k
Designing on Purpose - Digital PM Summit 2013
jponch
106
5.6k
The Invisible Customer
myddelton
110
11k
Transcript
The Future of Machine Learning & JavaScript @jawache YGLF 2019
Asim Hussain @jawache codecraft.tv microsoft.com
https://aka.ms/jawache-cda @jawache
@jawache https://www.palinternship.com/
@jawache
Asim Web Development Machine Learning This is @EleanorHaproff's slide
None
@jawache
TheMojifier™ @jawache
None
@jawache themojifier.com
None
How to Calculate Emotion? @jawache
(1) Detect Facial Features @jawache
https://towardsdatascience.com/facial-keypoints-detection-deep-learning-737547f73515
(2) Use a Neural Network @jawache
Neural Networks Axon Dendrites Axons Body @jawache
1 23 8.6 -0.5 2.1 Activation Function @jawache Neural Networks
1 23 8.6 -0.5 2.1 x x activation(...) = -11.5
= 18.06 7.01 !-> !-> } @jawache Neural Networks
Output 0 0 1 Input @jawache Neural Networks
1.1 4.2 0.3 4 12 93 3 @jawache Neural Networks
1.1 4.2 0.3 4 12 93 @jawache 8 - 8
= -5 3 Neural Networks
1.1 4.2 0.3 4 12 93 @jawache - 8 =
-5 3 8 Neural Networks
0.1 9.2 0.2 4 12 93 @jawache 8 8 Neural
Networks
@jawache https://azure.microsoft.com/services/cognitive-services/face/
https:!//<region>.api.cognitive.microsoft.com/face/v1.0/detect { "url": "<path-to-image>" } @jawache
@jawache
Summary @jawache
• Neural Networks are incredibly powerful • Conceptually, they are
simple to understand @jawache Summary
TensorFlow, MobileNet & I'm fine @jawache
@jawache
@jawache
@jawache
TensorFlow.js @jawache
TensorFlow.js Train models Load pre-trained models @jawache
https://github.com/tensorflow/tfjs-models @jawache MobileNet
https://azure.microsoft.com/services/cognitive-services/computer-vision/ @jawache
https://codepen.io/sdras/full/jawPGa/ @jawache
@jawache https://twitter.com/ollee/status/930303340516216832
@jawache https://twitter.com/FrontendNE/status/930120267992616960
@jawache https://twitter.com/chrispiecom/status/930407801402347520
Summary @jawache
• TensorFlow.js doesn't have any dependancies • MobileNet is a
simple way to analyse images • Azure Computer Vision API ❤ @jawache Summary
Image2Image @jawache
DEMO @jawache https://zaidalyafeai.github.io/pix2pix/cats.html
@jawache Generator Discriminator ✅ ❌
@jawache Generator Discriminator ✅ ❌
@jawache Generator Discriminator ✅ ✅
@jawache
@jawache
@jawache
@jawache https://github.com/NVIDIA/vid2vid
@jawache https://github.com/NVIDIA/vid2vid
@jawache https://github.com/NVIDIA/vid2vid
@jawache https://github.com/hanzhanggit/StackGAN
Summary @jawache
• GANs learn to generate new images • They take
a lot of compute to train • But the generator model can be run in the browser @jawache Summary
@jawache aka.ms/mojifier
Asim Hussain @jawache codecraft.tv microsoft.com