SlideShare uma empresa Scribd logo
1 de 64
Baixar para ler offline
NAS 也可以揀土豆
Open source application
Hello!
I am Cage Chung
I am here because I like to
share my experiences.
You can find me at:
QNAP 雲端應用部資深工程師
/ http://kaichu.io
Andy
https://www.facebook.com/groups/GCPUG.TW/
https://plus.google.com/u/0/communities/116100913832589966421
Google Cloud Platform User Group Taiwan
我們是Google Cloud Platform Taiwan User Group。在Google雲端服務在台灣地區展露頭角之後,
有許多新的服務、新的知識、新的創意,歡迎大家一起分享,一起了解 Google雲端服務...
GCPUG透過網際網路串聯喜好 Google Cloud的使用者,分享與交流使用 GCP的點滴鑑驗。如果您
是Google Cloud Platform的初學者,您應該來聽聽前輩們的使用經驗;如果您是 Google Cloud
Platform的Expert,您應該來分享一下寶貴的經驗,並與更多高手互相交流;如果您還沒開始用
Google Cloud Platform,那麼您應該馬上來聽聽我們是怎麼使用 Google Cloud的!
“
Lessons learned building a
classifier for NAS. Try to get a big
picture, get some useful
keywords
I cannot explain everything, you cannot get every details
General user
○ Videos
○ Music
○ Movies
○ Photos
○ Files
○ Games
Photographer
○ Photos (jpeg, RAW)
Musicians
○ Music files (mp3)
○ Videos
NAS | usage
Our scenario is easy
Portrait
landscape
wildlife
sports
folk
Retrain Inception classifier
Photographer
Product
NAS
outline
◎ Machine learning
◎ Deep learning
○ Neural Network
○ Convolutional neural network
◎ Building a classifier for NAS
◎ Study information
1.
Machine Learning
Let’s start with the first set of slides
Supervised Learning
[image](http://www.safebee.com/family/5-healthy-hygiene-habits-your-child-needs-learn)
Supervised Learning workflow
Raw Data
Labes
Feature
Extraction
Train
the
Model
Eval
Model
Model
Feature
Extraction Predict
New Data
Model
Labels
Training
Predicting
Supervised Learning workflow
Raw Data
Labes
Feature
Extraction
Train
the
Model
Eval
Model
Model
Feature
Extraction Predict
New Data
Model
Labels
Training
Predicting
Ripe Raw
Color/Shape
etc...
Ripe
Raw
Ripe
Raw
Unsupervised Learning
[image](http://thoughtcatalog.com/nikolao-montaya/2014/06/how-to-be-cool-in-high-school/)
Ripe
Ripe
Raw
Raw
Raw Data Automated Clusters
Learning
Algorithm
[image](http://www.artbooms.com/blog/primo-toy-cubetto-robot-legno-programmazione-prescolare)
Semi-Supervised Learning
Reinforcement Learning
[image](https://www.shutterstock.com/search/horse%20carrot)
Reinforcement Learning (RL)
[AlphaGo: Mastering the Game of Go with Deep Neural Networks and Tree
…](http://www.slideshare.net/KarelHa1/alphago-mastering-the-game-of-go-with-deep-neural-networks-and-tree-search)
Mario - Machine Learning for Video Games 1
[NEATEvolve.lua - Pastebin.com](http://pastebin.com/ZZmSNaHX)
Mario - Machine Learning for Video Games 2
[NEATEvolve.lua - Pastebin.com](http://pastebin.com/ZZmSNaHX)
Smart
programs can
learn from
examples
[image](https://www.engadget.com/2016/07/12/machine-learning-ai/)
2.
Deep Learning
Let’s start with the second set of
slides
Deep learning
[Deep Learning - Convolutional Neural Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neural-networks)
Deep learning
[自然言語処理のためのDeep Learning](http://www.slideshare.net/yutakikuchi927/deep-learning-26647407)
one
architecture
to rule them
all
[image](http://www.consultparagon.com/blog/what-is-leadership-digital-transformation)
2.1.
Neural Network
Neural Network Architecture
[Neural networks and deep learning](http://neuralnetworksanddeeplearning.com/chap1.html)
First Example: MNIST handwritten digits
a few seconds
60,000 images
MNIST resource
Intel HD Graphics
CPU build-in graphics
Piece of cake ...
90% AccuracyFeeling good? But Google said it’s shameful ...
2.2.
Convolutional
Neural Network
The Google “Inception” deep neural network architecture. Source: Christian Szegedy et. al. Going deeper with convolutions. CVPR 2015.
WHAT IS CONVOLUTION?
Source: http://deeplearning.stanford.edu/wiki/index.php/Feature_extraction_using_convolution
Convolution with 3×3 Filter.
WHAT IS CONVOLUTION?
Source: http://deeplearning.stanford.edu/wiki/index.php/Feature_extraction_using_convolution
Convolutional Neural Network, CNN
[Understanding Convolutional Neural Networks for NLP –
WildML](http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/)
Convolutional Neural Network, CNN
Convolutional Neural Network, CNN
becomes
Peeking inside Convnets
[Peeking inside Convnets | Audun M Øygard](https://auduno.github.io/2016/06/18/peeking-inside-convnets/)
a few hours
60,000 images
MNIST resource
Intel i5 2.5GhzCPU build-in graphics
Not as easy as we think ...
99% AccuracyMy Goodness ...
Deep learning is
a kind of neural
network, and a
neural network
is a kind of
machine
learning.
[image](https://www.hpcwire.com/2015/04/30/machine-learning-guru-sees-future-in-multi-gpu
-clusters/)
3.
Building a
classifier for NAS
Let’s start with the third set of
slides
Outline | Building a classifier for NAS
◎ How to train ?
○ Train from scratch
○ Re-train from inception modal
◎ Photo classifier Case study
○ Flickr Photos/ Google search
○ Fuji photography society monthly competition
○ Imagenet sources
◎ Image type classifier (photos、scan document、business card)
◎ Demo
◎ Next Steps
○ video post-processing?
○ Musicians?
◎ Search
2 weeksSpend a lot of time
14,197,122 images
ImageNet resource
8 NVIDIA Tesla K40s
High-end professional graphics
[Research Blog: Train your own image classifier with Inception in
TensorFlow](https://research.googleblog.com/2016/03/train-your-own-image-classifier-with.html)
Retrain Inception's Final Layer for New Categories
◎ reuse Imagenet
pre-trained model
extract features to
predict new tasks?
◎ Transfer learning
◎ General visual features
DeCAF: A Deep Convolutional Activation
Feature for Generic Visual Recognition
Retrain Inception's Final Layer for New Categories Cont.
◎ Installing and Running the TensorFlow Docker Image
(gcr.io/tensorflow/tensorflow:latest-devel)
◎ Preparing target images
○ Quantity > 100
○ representation
◎ Use Python to train your own image classifier
○ Distortions (--random_crop, --random_scale ects.)
○ Hyper-parameters (--learning_rate ects.)
◎ Classify images with your trained classifier
[TensorFlow For Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/index.html?index=..%2F..%2Findex#0)
Case study: Types of Photography via Flickr
Portrait landscape wildlife
folk sport art
68.8 %Final test accuracy
23,666 images
Flickr photos & Google search
Art x 4545 , Folk x 4782, Landscape x 3379
Portrait x 3706, Sport x 4967, Wildlife x 2887
5000 times
Retain iterator
89.0 %Final test accuracy
10,349 images
Flickr photos
Folk x 2083, Landscape x 3497
Portrait x 3215, Wildlife x 1554
4000 times
Retain iterator
97.0 %Final test accuracy
13,685 images
Imagenet 11 categories
Agaric/bolete/buckeye, horse chestnut, conker/coral fungus/ear,
spike, capitulum/earthstar/gyromitra/hen-of-the-woods, hen of the
woods, Polyporus frondosus, Grifola frondosa/peanut/stinkhorn,
carrion fungus/toilet tissue, toilet paper, bathroom tissue/
4000 times
Retain iterator
Case study: Types of Photography via Fuji photography
society (富士生活攝影協會月賽)
Portrait landscape wildlife
folk sport conceptual
Case study: Types of Photography via Fuji photography
society (富士生活攝影協會月賽)
competitor
銅牌
佳作
入選乙
入選甲
優選
金牌 銀牌
碩學會士/博學會士
45.8 %Final test accuracy
424 images
Fuji photography society monthly competition photos
佳作 x 32, 入選乙 x 137, 入選甲 x 255, 優選 x 2, 未入
選?
4000 times
Retain iterator
Demo
Custom Photo classifier
Image type classifier
Invoices Business cards Scan documents
Next Steps | video
[Large-scale Video Classification with Convolutional Neural Networks (CVPR 2014)](http://cs.stanford.edu/people/karpathy/deepvideo/)
Next Steps | music
[Large-scale Video Classification with Convolutional Neural Networks (CVPR 2014)](http://cs.stanford.edu/people/karpathy/deepvideo/)
[Deep Learning - Convolutional Neural Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neural-networks)
Search
Open framework, models and worked examples for deep
learning | Caffe
Caffe offers the
○ model definitions
○ optimization settings
○ pre-trained weights
so you can start right away.
The BVLC models are licensed for
unrestricted use.
The community shares models in our
Model Zoo.
[DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google
Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48)
Brewing by the Numbers … | Caffe
Speed with Krizhevsky's 2012 model:
○ 2 ms/image on K40 GPU
○ <1 ms inference with Caffe + cuDNN v4 on Titan X
○ 72 million images/day with batched IO
○ 8-core CPU: ~20 ms/image Intel optimization in progress
9k lines of C++ code (20k with tests)
[DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google
Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48)
4.
Study information
Let’s start with the fourth set of
slides
◎ [Deep Learning |
Udacity](https://www.udacity.com/course/deep-learning--ud730)
◎ [Research Blog: Train your own image classifier with Inception in
TensorFlow](https://research.googleblog.com/2016/03/train-your-own-image-cla
ssifier-with.html)
◎ [jtoy/awesome-tensorflow: TensorFlow - A curated list of dedicated resources
http://tensorflow.org](https://github.com/jtoy/awesome-tensorflow)
◎ [Deep Learning - Convolutional Neural
Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neura
l-networks)
◎ [Neural networks and deep
learning](http://neuralnetworksanddeeplearning.com/chap1.html)
◎ [Multiple Component Learning](http://valse.mmcheng.net/ftp/20150312/dsn.pdf)
◎ [Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7 -
YouTube](https://www.youtube.com/watch?v=Gj0iyo265bc)
Study information
◎ [DIGITS/GettingStarted.md at master ·
NVIDIA/DIGITS](https://github.com/NVIDIA/DIGITS/blob/master/docs/GettingStar
ted.md)
◎ [How to Retrain Inception's Final Layer for New
Categories](https://www.tensorflow.org/versions/r0.9/how_tos/image_retraining
/index.html)
◎ [TensorFlow For
Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/i
ndex.html?index=..%2F..%2Findex#0)
◎ [DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google
Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71
UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48)
◎ [Caffe | Deep Learning Framework](http://caffe.berkeleyvision.org/)
◎ [Understanding Convolutional Neural Networks for NLP –
WildML](http://www.wildml.com/2015/11/understanding-convolutional-neural-n
etworks-for-nlp/)
Study information
Thanks!
Any questions?
You can find me at:
http://kaichu.io
cage.chung@gmail.com

Mais conteúdo relacionado

Mais procurados

How to integrate front end tool via gruntjs
How to integrate front end tool via gruntjsHow to integrate front end tool via gruntjs
How to integrate front end tool via gruntjs
Bo-Yi Wu
 

Mais procurados (20)

Google apps script introduction
Google apps script introductionGoogle apps script introduction
Google apps script introduction
 
How to integrate front end tool via gruntjs
How to integrate front end tool via gruntjsHow to integrate front end tool via gruntjs
How to integrate front end tool via gruntjs
 
Dev fest 2020 taiwan how to debug microservices on kubernetes as a pros (ht...
Dev fest 2020 taiwan   how to debug microservices on kubernetes as a pros (ht...Dev fest 2020 taiwan   how to debug microservices on kubernetes as a pros (ht...
Dev fest 2020 taiwan how to debug microservices on kubernetes as a pros (ht...
 
Heroku 101 py con 2015 - David Gouldin
Heroku 101   py con 2015 - David GouldinHeroku 101   py con 2015 - David Gouldin
Heroku 101 py con 2015 - David Gouldin
 
Devfest 2021' - Artifact Registry Introduction (Taipei)
Devfest 2021' - Artifact Registry Introduction (Taipei)Devfest 2021' - Artifact Registry Introduction (Taipei)
Devfest 2021' - Artifact Registry Introduction (Taipei)
 
Screenshot as a service
Screenshot as a serviceScreenshot as a service
Screenshot as a service
 
如何透過 Go-kit 快速搭建微服務架構應用程式實戰
如何透過 Go-kit 快速搭建微服務架構應用程式實戰如何透過 Go-kit 快速搭建微服務架構應用程式實戰
如何透過 Go-kit 快速搭建微服務架構應用程式實戰
 
Ultimate Survival - React-Native edition
Ultimate Survival - React-Native editionUltimate Survival - React-Native edition
Ultimate Survival - React-Native edition
 
Introduction to Grunt.js on Taiwan JavaScript Conference
Introduction to Grunt.js on Taiwan JavaScript ConferenceIntroduction to Grunt.js on Taiwan JavaScript Conference
Introduction to Grunt.js on Taiwan JavaScript Conference
 
Noah Zoschke at Waza 2013: Heroku Secrets
Noah Zoschke at Waza 2013: Heroku SecretsNoah Zoschke at Waza 2013: Heroku Secrets
Noah Zoschke at Waza 2013: Heroku Secrets
 
COSCUP 2020 Google 技術 x 公共參與 x 開源 口罩地圖技術開源
COSCUP 2020 Google 技術 x 公共參與 x 開源 口罩地圖技術開源COSCUP 2020 Google 技術 x 公共參與 x 開源 口罩地圖技術開源
COSCUP 2020 Google 技術 x 公共參與 x 開源 口罩地圖技術開源
 
Automating your workflow with Gulp.js
Automating your workflow with Gulp.jsAutomating your workflow with Gulp.js
Automating your workflow with Gulp.js
 
容器化後,持續交付不可缺的敲門磚 - Helm
容器化後,持續交付不可缺的敲門磚 - Helm容器化後,持續交付不可缺的敲門磚 - Helm
容器化後,持續交付不可缺的敲門磚 - Helm
 
Waldo-gcp
Waldo-gcpWaldo-gcp
Waldo-gcp
 
Python maya 2018 setup note
Python maya 2018 setup notePython maya 2018 setup note
Python maya 2018 setup note
 
Groovy in the Cloud
Groovy in the CloudGroovy in the Cloud
Groovy in the Cloud
 
手把手教你如何串接 Log 到各種網路服務
手把手教你如何串接 Log 到各種網路服務手把手教你如何串接 Log 到各種網路服務
手把手教你如何串接 Log 到各種網路服務
 
Frontend JS workflow - Gulp 4 and the like
Frontend JS workflow - Gulp 4 and the likeFrontend JS workflow - Gulp 4 and the like
Frontend JS workflow - Gulp 4 and the like
 
Automating Large Applications on Modular and Structured Form with Gulp
Automating Large Applications on Modular and Structured Form with GulpAutomating Large Applications on Modular and Structured Form with Gulp
Automating Large Applications on Modular and Structured Form with Gulp
 
2014-08-19 Multiple Approaches to Managing Puppet Modules @ Puppet Camp Chicago
2014-08-19 Multiple Approaches to Managing Puppet Modules @ Puppet Camp Chicago2014-08-19 Multiple Approaches to Managing Puppet Modules @ Puppet Camp Chicago
2014-08-19 Multiple Approaches to Managing Puppet Modules @ Puppet Camp Chicago
 

Semelhante a Nas 也可以揀土豆

Machine Learning Model for Gender Detection
Machine Learning Model for Gender DetectionMachine Learning Model for Gender Detection
Machine Learning Model for Gender Detection
TecnoIncentive
 
Session-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networksSession-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networks
Zimin Park
 

Semelhante a Nas 也可以揀土豆 (20)

DSC Cloud Study Jams
DSC Cloud Study JamsDSC Cloud Study Jams
DSC Cloud Study Jams
 
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate ImagingChallenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
Challenges of Deep Learning in Computer Vision Webinar - Tessellate Imaging
 
Creating Virtual Reality Training Using Interactive 360 Videos and Images wit...
Creating Virtual Reality Training Using Interactive 360 Videos and Images wit...Creating Virtual Reality Training Using Interactive 360 Videos and Images wit...
Creating Virtual Reality Training Using Interactive 360 Videos and Images wit...
 
Deep Learning Applications (dadada2017)
Deep Learning Applications (dadada2017)Deep Learning Applications (dadada2017)
Deep Learning Applications (dadada2017)
 
Easy path to machine learning (Spring 2020)
Easy path to machine learning (Spring 2020)Easy path to machine learning (Spring 2020)
Easy path to machine learning (Spring 2020)
 
2 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 22 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 2
 
Deep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeedDeep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeed
 
Stor c gregynog colloquium
Stor c   gregynog colloquiumStor c   gregynog colloquium
Stor c gregynog colloquium
 
Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4
 
Global Azure Bootcamp 2016 - Lyon : Keynote Quantum : Concepts explained & Li...
Global Azure Bootcamp 2016 - Lyon : Keynote Quantum : Concepts explained & Li...Global Azure Bootcamp 2016 - Lyon : Keynote Quantum : Concepts explained & Li...
Global Azure Bootcamp 2016 - Lyon : Keynote Quantum : Concepts explained & Li...
 
Parallelformers
ParallelformersParallelformers
Parallelformers
 
Dl4j in the wild
Dl4j in the wildDl4j in the wild
Dl4j in the wild
 
Easy path to machine learning (Spring 2021)
Easy path to machine learning (Spring 2021)Easy path to machine learning (Spring 2021)
Easy path to machine learning (Spring 2021)
 
Applied Data Science: Building a Beer Recommender | Data Science MD - Oct 2014
Applied Data Science: Building a Beer Recommender | Data Science MD - Oct 2014Applied Data Science: Building a Beer Recommender | Data Science MD - Oct 2014
Applied Data Science: Building a Beer Recommender | Data Science MD - Oct 2014
 
Machine Learning Model for Gender Detection
Machine Learning Model for Gender DetectionMachine Learning Model for Gender Detection
Machine Learning Model for Gender Detection
 
Session-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networksSession-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networks
 
IRJET - Applications of Image and Video Deduplication: A Survey
IRJET -  	  Applications of Image and Video Deduplication: A SurveyIRJET -  	  Applications of Image and Video Deduplication: A Survey
IRJET - Applications of Image and Video Deduplication: A Survey
 
Deep Learning Jump Start
Deep Learning Jump StartDeep Learning Jump Start
Deep Learning Jump Start
 
User Testing Doesn't Have to Be Hard
User Testing Doesn't Have to Be HardUser Testing Doesn't Have to Be Hard
User Testing Doesn't Have to Be Hard
 
USING VISION SENSORS FOR INNOVATIVE HCI
USING VISION SENSORS FOR INNOVATIVE HCIUSING VISION SENSORS FOR INNOVATIVE HCI
USING VISION SENSORS FOR INNOVATIVE HCI
 

Mais de KAI CHU CHUNG

Mais de KAI CHU CHUNG (12)

Devfest 2023 - Service Weaver Introduction - Taipei.pdf
Devfest 2023 - Service Weaver Introduction - Taipei.pdfDevfest 2023 - Service Weaver Introduction - Taipei.pdf
Devfest 2023 - Service Weaver Introduction - Taipei.pdf
 
DevFest 2022 - Skaffold 2 Deep Dive Taipei.pdf
DevFest 2022 - Skaffold 2 Deep Dive Taipei.pdfDevFest 2022 - Skaffold 2 Deep Dive Taipei.pdf
DevFest 2022 - Skaffold 2 Deep Dive Taipei.pdf
 
DevFest 2022 - Cloud Workstation Introduction TaiChung
DevFest 2022 - Cloud Workstation Introduction TaiChungDevFest 2022 - Cloud Workstation Introduction TaiChung
DevFest 2022 - Cloud Workstation Introduction TaiChung
 
Velero search &amp; practice 20210609
Velero search &amp; practice 20210609Velero search &amp; practice 20210609
Velero search &amp; practice 20210609
 
GDG Cloud Taipei: Meetup #52 - Istio Security: API Authorization
GDG Cloud Taipei: Meetup #52 - Istio Security: API AuthorizationGDG Cloud Taipei: Meetup #52 - Istio Security: API Authorization
GDG Cloud Taipei: Meetup #52 - Istio Security: API Authorization
 
GDG Cloud Taipei meetup #50 - Build go kit microservices at kubernetes with ...
GDG Cloud Taipei meetup #50 - Build go kit microservices at kubernetes  with ...GDG Cloud Taipei meetup #50 - Build go kit microservices at kubernetes  with ...
GDG Cloud Taipei meetup #50 - Build go kit microservices at kubernetes with ...
 
GDG Devfest 2019 - Build go kit microservices at kubernetes with ease
GDG Devfest 2019 - Build go kit microservices at kubernetes with easeGDG Devfest 2019 - Build go kit microservices at kubernetes with ease
GDG Devfest 2019 - Build go kit microservices at kubernetes with ease
 
Global GDG Leaders Summit, Google I/O 2018 經驗分享
Global GDG Leaders Summit, Google I/O 2018 經驗分享Global GDG Leaders Summit, Google I/O 2018 經驗分享
Global GDG Leaders Summit, Google I/O 2018 經驗分享
 
Google apps script introduction
Google apps script introductionGoogle apps script introduction
Google apps script introduction
 
Google app engine (gae) 演進史
Google app engine (gae) 演進史Google app engine (gae) 演進史
Google app engine (gae) 演進史
 
痞客趴趴走 Waldo
痞客趴趴走   Waldo痞客趴趴走   Waldo
痞客趴趴走 Waldo
 
Introduction to chrome extension development
Introduction to chrome extension developmentIntroduction to chrome extension development
Introduction to chrome extension development
 

Último

Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
amitlee9823
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
amitlee9823
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
amitlee9823
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
amitlee9823
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 

Último (20)

Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
Mg Road Call Girls Service: 🍓 7737669865 🍓 High Profile Model Escorts | Banga...
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 

Nas 也可以揀土豆

  • 2. Hello! I am Cage Chung I am here because I like to share my experiences. You can find me at: QNAP 雲端應用部資深工程師 / http://kaichu.io
  • 4. https://www.facebook.com/groups/GCPUG.TW/ https://plus.google.com/u/0/communities/116100913832589966421 Google Cloud Platform User Group Taiwan 我們是Google Cloud Platform Taiwan User Group。在Google雲端服務在台灣地區展露頭角之後, 有許多新的服務、新的知識、新的創意,歡迎大家一起分享,一起了解 Google雲端服務... GCPUG透過網際網路串聯喜好 Google Cloud的使用者,分享與交流使用 GCP的點滴鑑驗。如果您 是Google Cloud Platform的初學者,您應該來聽聽前輩們的使用經驗;如果您是 Google Cloud Platform的Expert,您應該來分享一下寶貴的經驗,並與更多高手互相交流;如果您還沒開始用 Google Cloud Platform,那麼您應該馬上來聽聽我們是怎麼使用 Google Cloud的!
  • 5. “ Lessons learned building a classifier for NAS. Try to get a big picture, get some useful keywords I cannot explain everything, you cannot get every details
  • 6. General user ○ Videos ○ Music ○ Movies ○ Photos ○ Files ○ Games Photographer ○ Photos (jpeg, RAW) Musicians ○ Music files (mp3) ○ Videos NAS | usage
  • 7. Our scenario is easy Portrait landscape wildlife sports folk Retrain Inception classifier Photographer Product NAS
  • 8. outline ◎ Machine learning ◎ Deep learning ○ Neural Network ○ Convolutional neural network ◎ Building a classifier for NAS ◎ Study information
  • 9. 1. Machine Learning Let’s start with the first set of slides
  • 11. Supervised Learning workflow Raw Data Labes Feature Extraction Train the Model Eval Model Model Feature Extraction Predict New Data Model Labels Training Predicting
  • 12. Supervised Learning workflow Raw Data Labes Feature Extraction Train the Model Eval Model Model Feature Extraction Predict New Data Model Labels Training Predicting Ripe Raw Color/Shape etc... Ripe Raw Ripe Raw
  • 14. Ripe Ripe Raw Raw Raw Data Automated Clusters Learning Algorithm
  • 17. Reinforcement Learning (RL) [AlphaGo: Mastering the Game of Go with Deep Neural Networks and Tree …](http://www.slideshare.net/KarelHa1/alphago-mastering-the-game-of-go-with-deep-neural-networks-and-tree-search)
  • 18. Mario - Machine Learning for Video Games 1 [NEATEvolve.lua - Pastebin.com](http://pastebin.com/ZZmSNaHX)
  • 19. Mario - Machine Learning for Video Games 2 [NEATEvolve.lua - Pastebin.com](http://pastebin.com/ZZmSNaHX)
  • 21. 2. Deep Learning Let’s start with the second set of slides
  • 22. Deep learning [Deep Learning - Convolutional Neural Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neural-networks)
  • 26. Neural Network Architecture [Neural networks and deep learning](http://neuralnetworksanddeeplearning.com/chap1.html)
  • 27. First Example: MNIST handwritten digits
  • 28.
  • 29.
  • 30.
  • 31.
  • 32. a few seconds 60,000 images MNIST resource Intel HD Graphics CPU build-in graphics Piece of cake ... 90% AccuracyFeeling good? But Google said it’s shameful ...
  • 33. 2.2. Convolutional Neural Network The Google “Inception” deep neural network architecture. Source: Christian Szegedy et. al. Going deeper with convolutions. CVPR 2015.
  • 34. WHAT IS CONVOLUTION? Source: http://deeplearning.stanford.edu/wiki/index.php/Feature_extraction_using_convolution Convolution with 3×3 Filter.
  • 35. WHAT IS CONVOLUTION? Source: http://deeplearning.stanford.edu/wiki/index.php/Feature_extraction_using_convolution
  • 36. Convolutional Neural Network, CNN [Understanding Convolutional Neural Networks for NLP – WildML](http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/)
  • 39. becomes Peeking inside Convnets [Peeking inside Convnets | Audun M Øygard](https://auduno.github.io/2016/06/18/peeking-inside-convnets/)
  • 40. a few hours 60,000 images MNIST resource Intel i5 2.5GhzCPU build-in graphics Not as easy as we think ... 99% AccuracyMy Goodness ...
  • 41. Deep learning is a kind of neural network, and a neural network is a kind of machine learning. [image](https://www.hpcwire.com/2015/04/30/machine-learning-guru-sees-future-in-multi-gpu -clusters/)
  • 42. 3. Building a classifier for NAS Let’s start with the third set of slides
  • 43. Outline | Building a classifier for NAS ◎ How to train ? ○ Train from scratch ○ Re-train from inception modal ◎ Photo classifier Case study ○ Flickr Photos/ Google search ○ Fuji photography society monthly competition ○ Imagenet sources ◎ Image type classifier (photos、scan document、business card) ◎ Demo ◎ Next Steps ○ video post-processing? ○ Musicians? ◎ Search
  • 44. 2 weeksSpend a lot of time 14,197,122 images ImageNet resource 8 NVIDIA Tesla K40s High-end professional graphics [Research Blog: Train your own image classifier with Inception in TensorFlow](https://research.googleblog.com/2016/03/train-your-own-image-classifier-with.html)
  • 45. Retrain Inception's Final Layer for New Categories ◎ reuse Imagenet pre-trained model extract features to predict new tasks? ◎ Transfer learning ◎ General visual features DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
  • 46. Retrain Inception's Final Layer for New Categories Cont. ◎ Installing and Running the TensorFlow Docker Image (gcr.io/tensorflow/tensorflow:latest-devel) ◎ Preparing target images ○ Quantity > 100 ○ representation ◎ Use Python to train your own image classifier ○ Distortions (--random_crop, --random_scale ects.) ○ Hyper-parameters (--learning_rate ects.) ◎ Classify images with your trained classifier [TensorFlow For Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/index.html?index=..%2F..%2Findex#0)
  • 47. Case study: Types of Photography via Flickr Portrait landscape wildlife folk sport art
  • 48. 68.8 %Final test accuracy 23,666 images Flickr photos & Google search Art x 4545 , Folk x 4782, Landscape x 3379 Portrait x 3706, Sport x 4967, Wildlife x 2887 5000 times Retain iterator
  • 49. 89.0 %Final test accuracy 10,349 images Flickr photos Folk x 2083, Landscape x 3497 Portrait x 3215, Wildlife x 1554 4000 times Retain iterator
  • 50. 97.0 %Final test accuracy 13,685 images Imagenet 11 categories Agaric/bolete/buckeye, horse chestnut, conker/coral fungus/ear, spike, capitulum/earthstar/gyromitra/hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa/peanut/stinkhorn, carrion fungus/toilet tissue, toilet paper, bathroom tissue/ 4000 times Retain iterator
  • 51. Case study: Types of Photography via Fuji photography society (富士生活攝影協會月賽) Portrait landscape wildlife folk sport conceptual
  • 52. Case study: Types of Photography via Fuji photography society (富士生活攝影協會月賽) competitor 銅牌 佳作 入選乙 入選甲 優選 金牌 銀牌 碩學會士/博學會士
  • 53. 45.8 %Final test accuracy 424 images Fuji photography society monthly competition photos 佳作 x 32, 入選乙 x 137, 入選甲 x 255, 優選 x 2, 未入 選? 4000 times Retain iterator
  • 55. Image type classifier Invoices Business cards Scan documents
  • 56. Next Steps | video [Large-scale Video Classification with Convolutional Neural Networks (CVPR 2014)](http://cs.stanford.edu/people/karpathy/deepvideo/)
  • 57. Next Steps | music [Large-scale Video Classification with Convolutional Neural Networks (CVPR 2014)](http://cs.stanford.edu/people/karpathy/deepvideo/) [Deep Learning - Convolutional Neural Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neural-networks)
  • 59. Open framework, models and worked examples for deep learning | Caffe Caffe offers the ○ model definitions ○ optimization settings ○ pre-trained weights so you can start right away. The BVLC models are licensed for unrestricted use. The community shares models in our Model Zoo. [DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48)
  • 60. Brewing by the Numbers … | Caffe Speed with Krizhevsky's 2012 model: ○ 2 ms/image on K40 GPU ○ <1 ms inference with Caffe + cuDNN v4 on Titan X ○ 72 million images/day with batched IO ○ 8-core CPU: ~20 ms/image Intel optimization in progress 9k lines of C++ code (20k with tests) [DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48)
  • 61. 4. Study information Let’s start with the fourth set of slides
  • 62. ◎ [Deep Learning | Udacity](https://www.udacity.com/course/deep-learning--ud730) ◎ [Research Blog: Train your own image classifier with Inception in TensorFlow](https://research.googleblog.com/2016/03/train-your-own-image-cla ssifier-with.html) ◎ [jtoy/awesome-tensorflow: TensorFlow - A curated list of dedicated resources http://tensorflow.org](https://github.com/jtoy/awesome-tensorflow) ◎ [Deep Learning - Convolutional Neural Networks](http://www.slideshare.net/perone/deep-learning-convolutional-neura l-networks) ◎ [Neural networks and deep learning](http://neuralnetworksanddeeplearning.com/chap1.html) ◎ [Multiple Component Learning](http://valse.mmcheng.net/ftp/20150312/dsn.pdf) ◎ [Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7 - YouTube](https://www.youtube.com/watch?v=Gj0iyo265bc) Study information
  • 63. ◎ [DIGITS/GettingStarted.md at master · NVIDIA/DIGITS](https://github.com/NVIDIA/DIGITS/blob/master/docs/GettingStar ted.md) ◎ [How to Retrain Inception's Final Layer for New Categories](https://www.tensorflow.org/versions/r0.9/how_tos/image_retraining /index.html) ◎ [TensorFlow For Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/i ndex.html?index=..%2F..%2Findex#0) ◎ [DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe - Google Slides](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71 UMscNPlvArsWER41PsU/edit#slide=id.gc2fcdcce7_216_48) ◎ [Caffe | Deep Learning Framework](http://caffe.berkeleyvision.org/) ◎ [Understanding Convolutional Neural Networks for NLP – WildML](http://www.wildml.com/2015/11/understanding-convolutional-neural-n etworks-for-nlp/) Study information
  • 64. Thanks! Any questions? You can find me at: http://kaichu.io cage.chung@gmail.com