kubeflow_sample_job.yaml

# Training job contains 1 Tensorflow master,1 Tensorflow worker and 2 parameter servers.
# In replica specifications, we specify replica type and replica specific details like container image etc.
apiVersion: "kubeflow.org/v1alpha1"
kind: "TFJob"
metadata:
  name: "example-job"
spec:
  replicaSpecs:
    - replicas: 1
      tfReplicaType: MASTER
      template:
        spec:
          containers:
            - image: gcr.io/tf-on-k8s-dogfood/tf_sample:dc944ff
              name: tensorflow
          restartPolicy: OnFailure
    - replicas: 1
      tfReplicaType: WORKER
      template:
        spec:
          containers:
            - image: gcr.io/tf-on-k8s-dogfood/tf_sample:dc944ff
              name: tensorflow
          restartPolicy: OnFailure
    - replicas: 2
      tfReplicaType: PS