Voxxed Days Belgrade 2017: Deploying Image Recognition with TensorFlow and Kubernetes

1ed0b822068d34032bca7d2beeb2f846?s=47 Casey West
October 19, 2017
Technology
0
72

Voxxed Days Belgrade 2017: Deploying Image Recognition with TensorFlow and Kubernetes

1ed0b822068d34032bca7d2beeb2f846?s=128

Casey West

October 19, 2017
Tweet

More Decks by Casey West

See All by Casey West
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
110
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
12
2.6k
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
340
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
3
2.6k
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
230
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
1
240
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
180
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
1
480
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
3
530

Other Decks in Technology

See All in Technology
8065fe5a0d33908c6f71c5ae28939dcd?s=48 ayatokura
0
120
7cd783377515bdf8207062840b7b2f4e?s=48 soracom
0
110
Cd823abda454a7a2065fe6fe273ae84b?s=48 viva_tweet_x
1
390
Ff98f59b09d38b46d177e9a12b77dad4?s=48 yksn
0
230
C58d9fc209cfdc0b822f851911110fa6?s=48 coe
14
6.3k
665aa20c57717b4f34d0635308d272f7?s=48 kwada
0
110
3115a782126be714b5f94d24073c957d?s=48 oracle4engineer
0
190
9fbbe5d0b8e2ee1cdc3a576b55a2d63d?s=48 uzimaru0000
1
130
Dd7fa413be25d8672c03a487db6a8fe6?s=48 fujiihda
3
690
53e2d354b3299d64a54af680865516d5?s=48 satotakeshi
3
710
57e8d22493c141fd3c7e7dbe62196c1b?s=48 uenitty
1
310
88f4e84b94fe07cddbd9e6479d689192?s=48 soudai
1
380

Featured

See All Featured
812e1705ff0f8bc1bcf18587bde687d5?s=48 62gerente
582
200k
D09fad3e36ae6841f54820be0e907f7a?s=48 rocio
154
11k
Eb8975af8e49e19e3dd6b6b84a542e26?s=48 qrush
282
18k
F57e2136eb9895eb95ff5dc8a1c02677?s=48 zakiwarfel
86
3.2k
D83926c323d4f9289f947b4b4e76b939?s=48 jensimmons
205
9.9k
7c8469ee8c9e594c65c59b919626c08d?s=48 scottboms
250
11k
170b760e0147792d0140e59ec78e9893?s=48 eitanlees
106
9.5k
20bfe76b3d6105641f879fe45cfc9272?s=48 bkeepers
407
57k
B6a8f005f39d23ffc930508ac9da68b9?s=48 vanstee
115
4.7k
5b6a2bd86ef643786a381a212e0ef2f1?s=48 geoffreycrofte
11
290
78b475797a14c84799063c7cd073962f?s=48 holman
287
130k
Ae14cc4491ac334f9cd23f9f93b4305e?s=48 orderedlist
PRO
326
35k

Transcript

  1. Enhance! Deploying Image Recognition with TensorFlow and Kubernetes Casey West

    ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 1

  2. 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

  3. however… ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes

    3

  4. I know enough to be dangerous. ! @caseywest @googlecloud @VoxxedBelgrade

    #" #VBD17 #machinelearning #tensorflow #kubernetes 4

  5. In 40 minutes you will also know enough to be

    dangerous. ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 5

  6. Let's get dangerous. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning

    #tensorflow #kubernetes 6

  7. 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

  8. Understand ML Basics ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning

    #tensorflow #kubernetes 8

  9. Understand ML Basics ¯\_(ϑ)_/¯ ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17

    #machinelearning #tensorflow #kubernetes 9

  10. Training a Model 1. Data 2. Time 3. Procedure !

    @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 10

  11. Training a Model 1. Data Historical or available data. !

    @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 11

  12. Training a Model 2. Time Iterations you have time to

    make. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 12

  13. 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

  14. 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

  15. 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

  16. Image Recognition: Inception v3 https://github.com/tensorflow/models/tree/master/research/inception ! @caseywest @googlecloud @VoxxedBelgrade #"

    #VBD17 #machinelearning #tensorflow #kubernetes 16

  17. 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

  18. Pre-trained models exist! ! Let's containerize them before they get

    away! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 18

  19. 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

  20. Create a Docker Image: TensorFlow Serving Inception v3 Run developer

    container git clone git@github.com: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

  21. 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

  22. 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

  23. 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

  24. The Machines Have Already Learned Using ML isn't doing ML.

    ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 24

  25. 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

  26. Let's do it live… ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17

    #machinelearning #tensorflow #kubernetes 26

  27. We did it! ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17

    #machinelearning #tensorflow #kubernetes 27

  28. 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

  29. Want the code? —DM me @caseywest —Email me caseywest@google.com —Try

    a similar tutorial —https://tensorflow.github.io/serving/ serving_inception ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 29

  30. 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

  31. Let's be friends @caseywest ! ! @caseywest @googlecloud @VoxxedBelgrade #"

    #VBD17 #machinelearning #tensorflow #kubernetes 31