Upgrade to Pro — share decks privately, control downloads, hide ads and more …

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

1ed0b822068d34032bca7d2beeb2f846?s=47 Casey West
October 19, 2017
Technology
0
77

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
120
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
12
2.7k
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
350
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
3
2.7k
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
230
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
250
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
190
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
0
510
1ed0b822068d34032bca7d2beeb2f846?s=48 caseywest
3
530

Other Decks in Technology

See All in Technology
44a210d1299a727e9d601a47dfedeabf?s=48 mot_techtalk
0
120
269258447d4284b5cb2ce0f048d143b2?s=48 shkitayama
0
800
928b1395afedebb5ee48d44ab917c5f1?s=48 ryusa
1
280
D8d463da5ab4a99265ffc1d12e76cbc9?s=48 sagara
1
400
898361eff829c27d6357f23b3d0259f5?s=48 hanafusa1991
0
630
6f411237444fb0f49c63baeb9c5f2a38?s=48 yusukeiwaki
3
650
7cd783377515bdf8207062840b7b2f4e?s=48 soracom
PRO
1
110
325ce6fcd0a74ff78990b8632817da55?s=48 yukihirochiba
0
230
744424a2b6307140bf794ffb00ce5ec1?s=48 yujioshima
1
550
195f71c8183f8d27da66aa0618f293b6?s=48 task4233
0
350
0350fb935be160186cd72472c9e5543b?s=48 hayaosuzuki
0
150
58d2fa98345951d9a57fdd6cfd5d0f64?s=48 aszx87410
0
240

Featured

See All Featured
E43f8dfd01057f8304f5f8fb9a294d7d?s=48 jeffersonlam
335
16k
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
171
7.7k
C86443373fbfe92996aa882d0d7a59f8?s=48 imathis
484
150k
D67fff74178013024d833b3eec6cf27f?s=48 lynnandtonic
277
17k
282d599b414022eba5096510f675b6e2?s=48 chrislema
174
14k
0bce06bd06ee7a2c4f5500f25dcf7f18?s=48 paulrobertlloyd
72
3.9k
61857dafbd287b3027c4dcea9008ad3c?s=48 carmenhchung
43
2.1k
E76911cbe088e5b850d966de3fc7435b?s=48 robhawkes
56
3k
F383c6a4dc55e331bbe2987b622cee6b?s=48 stephaniewalter
263
11k
C9b18d9dff88a9dd2393364c2b3b21bd?s=48 colly
69
3.2k
465724d73fe3a92c0879fdfb43a3a6f3?s=48 philhawksworth
195
9.1k
7653c7c449918ff6542880a8c284f5e7?s=48 jponch
106
5.4k

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