TensorFlow Serving on Kubernetes

tensorflow_serving.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: iris
spec:
  replicas: 3
  selector:
    matchLabels:
      app: iris-classifier
  template:
    metadata:
      labels:
        app: iris-classifier
    spec:
      initContainers:
      - name: download-model
        image: busybox
        command: ["/bin/sh", "-c"]
        args: ["wget -qO- https://s3-us-west-2.amazonaws.com/cortex-blog/tf-serving-k8s/iris.tar.gz | tar xvz -C /models/iris"]
        volumeMounts:
        - name: model
          mountPath: /models/iris
      containers:
      - name: serving
        image: tensorflow/serving
        env:
        - name: MODEL_NAME
          value: iris
        ports:
        - containerPort: 8501
        readinessProbe:
          tcpSocket:
            port: 8500
        volumeMounts:
        - name: model
          mountPath: /models/iris
      volumes:
      - name: model
        emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: iris
spec:
  ports:
  - port: 80
    targetPort: 8501
  selector:
    app: iris-classifier
  type: LoadBalancer