apiVersion: "kubeflow.org/v1alpha1"
kind: StudyJob
metadata:
  namespace: kubeflow
  labels:
    controller-tools.k8s.io: "1.0"
  name: tfjob-example
spec:
  studyName: tfjob-example
  owner: crd
  optimizationtype: maximize
  objectivevaluename: accuracy_1
  optimizationgoal: 0.99
  requestcount: 4
  metricsnames:
    - accuracy_1
  parameterconfigs:
    - name: --learning_rate
      parametertype: double
      feasible:
        min: "0.01"
        max: "0.05"
    - name: --batch_size
      parametertype: int
      feasible:
        min: "100"
        max: "200"
  workerSpec:
    goTemplate:
        rawTemplate: |-
          apiVersion: "kubeflow.org/v1beta1"
          kind: TFJob
          metadata:
            name: {{.WorkerID}}
            namespace: kubeflow
          spec:
           tfReplicaSpecs:
            Worker:
              replicas: 1
              restartPolicy: Never
              template:
                spec:
                  containers:
                    - name: tensorflow
                      image: gcr.io/kubeflow-ci/tf-mnist-with-summaries:1.0
                      command:
                        - "python"
                        - "/var/tf_mnist/mnist_with_summaries.py"
                        - "--log_dir=/train/{{.WorkerID}}"
                        {{- with .HyperParameters}}
                        {{- range .}}
                        - "{{.Name}}={{.Value}}"
                        {{- end}}
                        {{- end}}
                      volumeMounts:
                        - mountPath: "/train"
                          name: "train"
                  volumes:
                    - name: "train"
                      persistentVolumeClaim:
                        claimName: "tfevent-volume"
  metricsCollectorSpec:
    goTemplate:
      rawTemplate: |-
        apiVersion: batch/v1beta1
        kind: CronJob
        metadata:
          name: {{.WorkerID}}
          namespace: kubeflow
        spec:
          schedule: "*/1 * * * *"
          successfulJobsHistoryLimit: 0
          failedJobsHistoryLimit: 1
          jobTemplate:
            spec:
              template:
                spec:
                  containers:
                  - name: {{.WorkerID}}
                    image: gcr.io/kubeflow-ci/katib/tfevent-metrics-collector:v0.1.2-alpha-77-g9324cad
                    args:
                    - "python"
                    - "main.py"
                    - "-m"
                    - "vizier-core"
                    - "-s"
                    - "{{.StudyID}}"
                    - "-w"
                    - "{{.WorkerID}}"
                    - "-d"
                    - "/train/{{.WorkerID}}"
                    volumeMounts:
                        - mountPath: "/train"
                          name: "train"
                  volumes:
                    - name: "train"
                      persistentVolumeClaim:
                          claimName: "tfevent-volume"
                  restartPolicy: Never
                  serviceAccountName: metrics-collector
  suggestionSpec:
    suggestionAlgorithm: "random"
    requestNumber: 3