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
Voxxed Days Belgrade 2017: Deploying Image Reco...
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Casey West
October 19, 2017
Technology
200
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Voxxed Days Belgrade 2017: Deploying Image Recognition with TensorFlow and Kubernetes
Casey West
October 19, 2017
More Decks by Casey West
See All by Casey West
TechSummit Amsterdam 2017: Enhance! Deploying Image Recognition with TensorFlow and Kubernetes
caseywest
0
200
Said no CEO ever: Things that don't matter in the cloud
caseywest
12
3.4k
OperabilityIO 2016 – Achieving Cloud-Native Operability
caseywest
0
680
ContainerCon North America – Cloud Anti-Patterns
caseywest
3
3.4k
Abstractions – Pittsburgh – The Twelve-Factor Container + BONUS
caseywest
0
440
Velocity — Minimum Viable Platform
caseywest
0
310
Minimum Viable Platform - Devops MSP
caseywest
0
270
How Platforms Work
caseywest
0
740
Linux Conf Australia 2016 - The Twelve-Factor Container
caseywest
3
600
Other Decks in Technology
See All in Technology
Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
spatial_ai_network
0
130
ソニー銀行におけるビジネスアジリティ向上のためのクラウドシフト戦略
srenext
0
770
Type-safe IaC for Dart
coborinai
0
160
非定型なドキュメントを効率よくリファクタする 〜えぇ!?仕様書27本の移行が1日で終わったって!?〜
subroh0508
2
550
LLMやAIエージェントをソフトウェアに組み込むプラクティス
shibuiwilliam
2
420
Control Planeで育てるBtoB SaaSの認証基盤 - SRE NEXT 2026
pokohide
1
2.6k
SRE Next 2026 何でも屋からの脱却
bto
0
950
AI Coding Agent時代のcdk-nagガードレール 〜組織ルールを強制CIで守り抜く設計の挑戦〜
mhrtech
3
420
美しいコードを書くためにF#を学んでみた話
yud0uhu
1
460
2年前に削除したPHPクラスが、 ある日突然決済をエラーにした
ykagano
1
290
はじめてのWDM
miyukichi_ospf
1
150
DMM.com 購入改善推進チーム におけるCodeRabbitを用いた レビューフロー改善の一例
ysknsid25
2
670
Featured
See All Featured
Thoughts on Productivity
jonyablonski
76
5.2k
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
490
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
420
WENDY [Excerpt]
tessaabrams
11
38k
AI Search: Where Are We & What Can We Do About It?
aleyda
0
7.7k
Chasing Engaging Ingredients in Design
codingconduct
0
240
Bash Introduction
62gerente
615
220k
Evolving SEO for Evolving Search Engines
ryanjones
0
240
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
0
450
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
62
45k
Raft: Consensus for Rubyists
vanstee
141
7.6k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.8k
Transcript
Enhance! Deploying Image Recognition with TensorFlow and Kubernetes Casey West
! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 1
I am… —Dad, software architect, technical lead, change agent, programmer,
beverage enthusiast, rock climber, cyclist, acro yoga person… —An Architecture Advocate at Google. I am not… —A data scientist. —An expert in machine learning. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 2
however… ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes
3
I know enough to be dangerous. ! @caseywest @googlecloud @VoxxedBelgrade
#" #VBD17 #machinelearning #tensorflow #kubernetes 4
In 40 minutes you will also know enough to be
dangerous. ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 5
Let's get dangerous. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning
#tensorflow #kubernetes 6
Project Plan —Phase 0: Understand ML Basics —Phase 1: Create
TensorFlow Serving model —Phase 2: Create TensorFlow Serving client app —Phase 3: Deploy on Kubernetes —Phase 4: Play! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 7
Understand ML Basics ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning
#tensorflow #kubernetes 8
Understand ML Basics ¯\_(ϑ)_/¯ ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17
#machinelearning #tensorflow #kubernetes 9
Training a Model 1. Data 2. Time 3. Procedure !
@caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 10
Training a Model 1. Data Historical or available data. !
@caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 11
Training a Model 2. Time Iterations you have time to
make. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 12
Training a Model 3. Procedure Discover data preparation procedures, an
algorithm to use, and how to configure it. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 13
Training a Model: Steps 1. Get a data set. 2.
Split it into training and testing data. 3. Train the algorithm. 4. Test the algorithm. 5. Ship it! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 14
Training a Model: Know More in Five Minutes https://www.youtube.com/watch?v=2FmcHiLCwTU —
Siraj Raval ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 15
Image Recognition: Inception v3 https://github.com/tensorflow/models/tree/master/research/inception ! @caseywest @googlecloud @VoxxedBelgrade #"
#VBD17 #machinelearning #tensorflow #kubernetes 16
Serving the model with TensorFlow Serving —Continuous training pipeline —gRPC
interface —Production ready https://www.tensorflow.org/serving/ ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 17
Pre-trained models exist! ! Let's containerize them before they get
away! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 18
Create a Docker Image: TensorFlow Serving Inception v3 Docker Machine
docker-machine create \ --driver google \ --google-project goog-caseywest \ --google-zone us-central1-a \ --google-machine-type n1-standard-4 \ docker-machine eval $(docker-machine env docker-machine) ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 19
Create a Docker Image: TensorFlow Serving Inception v3 Run developer
container git clone
[email protected]
:tensorflow/serving.git cd serving docker build --pull \ -t $USER/tensorflow-serving-devel \ -f tensorflow_serving/tools/docker/Dockerfile.devel . docker run --name=inception_container -it \ $USER/tensorflow-serving-devel ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 20
Create a Docker Image: TensorFlow Serving Inception v3 Build in
the devel the container git clone --recurse-submodules \ https://github.com/tensorflow/serving cd serving/tensorflow ./configure # interactive :-( cd .. bazel build -c opt tensorflow_serving/... ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 21
Create a Docker Image: TensorFlow Serving Inception v3 Export inception
in the devel the container curl -LO http://cwe.st/tf-inception-v3 tar xzf inception-v3-2016-03-01.tar.gz bazel-bin/tensorflow_serving/example/inception_saved_model \ --checkpoint_dir=inception-v3 \ --output_dir=inception-export ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 22
Create a Docker Image: TensorFlow Serving Inception v3 Commit and
deploy container docker commit inception_container \ $USER/inception_serving docker tag $USER/inception_serving \ gcr.io/goog-caseywest/inception gcloud docker -- push \ gcr.io/goog-caseywest/inception ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 23
The Machines Have Already Learned Using ML isn't doing ML.
! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 24
Deploy Inception Service on Kubernetes Create a cluster gcloud container
clusters create \ image-recognition-cluster \ --num-nodes 5 ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 25
Let's do it live… ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17
#machinelearning #tensorflow #kubernetes 26
We did it! ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17
#machinelearning #tensorflow #kubernetes 27
Takeaways —Training models is hard. —Serving models is kind of
easy. —gRPC and protobuf have steep learning curves. —therefore, client libraries are challenging. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 28
Want the code? —DM me @caseywest —Email me
[email protected]
—Try
a similar tutorial —https://tensorflow.github.io/serving/ serving_inception ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 29
Want to try more ML? —TensorFlow —https://www.tensorflow.org/ —MXNet —http://mxnet.io/ —Google
Cloud Playground —https://cloud.google.com/vision/ ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 30
Let's be friends @caseywest ! ! @caseywest @googlecloud @VoxxedBelgrade #"
#VBD17 #machinelearning #tensorflow #kubernetes 31