Tweet
Tweet

Slide 1

Slide 1 text

Enhance! Deploying Image Recognition with TensorFlow and Kubernetes Casey West ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 1

Slide 2

Slide 2 text

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

Slide 3

Slide 3 text

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

Slide 4

Slide 4 text

I know enough to be dangerous. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 4

Slide 5

Slide 5 text

In 40 minutes you will also know enough to be dangerous. ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 5

Slide 6

Slide 6 text

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

Slide 7

Slide 7 text

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

Slide 8

Slide 8 text

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

Slide 9

Slide 9 text

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

Slide 10

Slide 10 text

Training a Model 1. Data 2. Time 3. Procedure ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 10

Slide 11

Slide 11 text

Training a Model 1. Data Historical or available data. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 11

Slide 12

Slide 12 text

Training a Model 2. Time Iterations you have time to make. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 12

Slide 13

Slide 13 text

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

Slide 14

Slide 14 text

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

Slide 15

Slide 15 text

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

Slide 16

Slide 16 text

Image Recognition: Inception v3 https://github.com/tensorflow/models/tree/master/research/inception ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 16

Slide 17

Slide 17 text

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

Slide 18

Slide 18 text

Pre-trained models exist! ! Let's containerize them before they get away! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 18

Slide 19

Slide 19 text

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

Slide 20

Slide 20 text

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

Slide 21

Slide 21 text

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

Slide 22

Slide 22 text

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

Slide 23

Slide 23 text

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

Slide 24

Slide 24 text

The Machines Have Already Learned Using ML isn't doing ML. ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 24

Slide 25

Slide 25 text

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

Slide 26

Slide 26 text

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

Slide 27

Slide 27 text

We did it! ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 27

Slide 28

Slide 28 text

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

Slide 29

Slide 29 text

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

Slide 30

Slide 30 text

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

Slide 31

Slide 31 text

Let's be friends @caseywest ! ! @caseywest @googlecloud @VoxxedBelgrade #" #VBD17 #machinelearning #tensorflow #kubernetes 31