TensorFlow Serving with Kubernetes

1.Build Docker Image

Because you always have problems with your build image, here is a temporary lease on a mirror on Dockerhub docker.io/mochin/tensorflow-serving

Push this image to the Docker registry of the K8s cluster

2. Writing Yaml

In the official example, a yaml is given, but some places are wrong, or the dockerimage is not applicable (probably because of the 0.4.0 version)

Made some changes.

Apiversion:extensions/v1beta1kind:deploymentmetadata:  name:inception-deploymentspec:  replicas:2  Template:    metadata:      Labels:        app:inception-server    Spec:      containers:      -Name: Inception-container        image:registry.lenovo.com:8080/tensorflow-serving:0.4.0        command:        -/bin/sh        -C-        args:        -serving/bazel-bin/tensorflow_serving/example/inception_inference--port=9900 serving/ Inception-export        Ports:        -containerport:9900---apiVersion:v1kind:Servicemetadata:  Labels:    Run:inception-service  Name:inception-servicespec:  ports:  -port:9900    targetport:9900  Selector:    app:inception-server  #type: LoadBalancer  externalips:    -xxx.xxx.xxx.xxx

　　

3. Submit to K8s

Kubectl create-f Xxx.yaml

4. View status

#>kubectl Get Service
NAME cluster-ip external-ip PORT (S) Age
Inception-service xxx.xxx.xxx.xxx xxx.xxx.xxx.xxx 9900/tcp 8m

#>kubectl Get Deployment
NAME desired current up-to-date AVAILABLE age
Inception-deployment 2 2 2 2 3h

5. Conduct the test

Run a Docker container to access the deployed service

Docker Run--rm-it Tensorflow-serving:latest/bin/bash

#>cd Serving

#>./bazel-bin/tensorflow_serving/example/inception_client--server=10.100.208.54:9900--image=./tensorflow/ Tensorflow/examples/label_image/data/grace_hopper.jpg &> Log &

7.863746:military Uniform
6.911478:bow tie, Bow-tie, bowtie
6.642433:mortarboard
5.758826:suit, suit of clothes
5.614463:academic gown, academic robe, judge ' s robe

6. Load Balancing Configuration

Todo

TensorFlow Serving with Kubernetes