ms-dist-train.yaml

# WIP example for distributed training
apiVersion: "kubeflow.org/v1"
kind: "MSJob"
metadata:
  name: "msjob-mnist"
spec:
  backend: "tcp"
  masterPort: "23456"
  replicaSpecs:
    - replicas: 1
      replicaType: MASTER
      template:
        spec:
          containers:
          - image: mindspore/mindspore-cpu:0.1.0-alpha
            imagePullPolicy: IfNotPresent
            name: msjob-mnist
            command: ["/bin/bash", "-c", "python /tmp/test/MNIST/lenet.py"]
            volumeMounts:
              - name: training-result
                mountPath: /tmp/result
              - name: ms-mnist-local-file
                mountPath: /tmp/test
          restartPolicy: OnFailure
          volumes:
            - name: training-result
              emptyDir: {}
            - name: entrypoint
              configMap:
                name: dist-train
                defaultMode: 0755
          restartPolicy: OnFailure
    - replicas: 3
      replicaType: WORKER
      template:
        spec:
          containers:
          - image: mindspore/mindspore-cpu:0.1.0-alpha
            imagePullPolicy: IfNotPresent
            name: msjob-mnist
            command: ["/bin/bash", "-c", "python /tmp/test/MNIST/lenet.py"]
            volumeMounts:
              - name: training-result
                mountPath: /tmp/result
              - name: ms-mnist-local-file
                hostPath:
                    path: /root/gopath/src/gitee.com/mindspore/ms-operator/examples
          restartPolicy: OnFailure
          volumes:
            - name: training-result
              emptyDir: {}
            - name: entrypoint
              configMap:
                name: dist-train
                defaultMode: 0755
          restartPolicy: OnFailure