TFJobexample.yaml

apiVersion: "kubeflow.org/v1"
kind: "TFJob"
metadata:
  name: "inception-train-job"
spec:
  replicaSpecs:
    - replicas: 4
      tfReplicaType: WORKER
      template:
        spec:
          containers:
            - image: banzaicloud/tensorflow-inception-example:v0.1
              name: tensorflow
              command: ["bazel-bin/inception/imagenet_distributed_train"]
              args: ["--batch_size=32", "--num_gpus=0", "--data_dir=/my-pv/image-data", "--train_dir=/my-pv/train"]
              volumeMounts:
                - name: pvc-efs
                  mountPath: "/my-pv"
          volumes:
            - name: pvc-efs
              persistentVolumeClaim:
                claimName: pvc-1
          restartPolicy: OnFailure
    - replicas: 2
      tfReplicaType: PS
  tensorboard:
    logDir: /my-pv/train
    serviceType: LoadBalancer
    volumes:
      - name: pvc-efs
        persistentVolumeClaim:
          claimName: pvc-1
    volumeMounts:
      - name: pvc-efs
        mountPath: "/my-pv"
  terminationPolicy:
    chief:
      replicaName: WORKER
      replicaIndex: 0