tf-job

tf-job.yaml

apiVersion: kubeflow.org/v1alpha2
kind: TFJob
metadata:
  labels:
    experiment: experiment10
  name: tfjob-gpu
spec:
  tfReplicaSpecs:
    Ps:
      replicas: 1
      template:
        metadata:
          creationTimestamp: null
        spec:
          containers:
          - args:
            - python
            - tf_cnn_benchmarks.py
            - --batch_size=32
            - --model=resnet50
            - --variable_update=parameter_server
            - --flush_stdout=true
            - --num_gpus=1
            - --local_parameter_device=cpu
            - --device=gpu
            - --data_format=NHWC
            image: gcr.io/kubeflow/tf-benchmarks-gpu:v20171202-bdab599-dirty-284af3
            name: tensorflow
            ports:
            - containerPort: 2222
              name: tfjob-port
            resources: {}
            workingDir: /opt/tf-benchmarks/scripts/tf_cnn_benchmarks
          restartPolicy: OnFailure
    Worker:
      replicas: 1
      template:
        metadata:
          creationTimestamp: null
        spec:
          containers:
          - args:
            - python
            - tf_cnn_benchmarks.py
            - --batch_size=32
            - --model=resnet50
            - --variable_update=parameter_server
            - --flush_stdout=true
            - --num_gpus=1
            - --local_parameter_device=cpu
            - --device=gpu
            - --data_format=NHWC
            image: gcr.io/kubeflow/tf-benchmarks-gpu:v20171202-bdab599-dirty-284af3
            name: tensorflow
            ports:
            - containerPort: 2222
              name: tfjob-port
            resources: {}
            workingDir: /opt/tf-benchmarks/scripts/tf_cnn_benchmarks
          restartPolicy: OnFailure
status:
  conditions:
  - lastTransitionTime: 2018-07-29T00:31:48Z
    lastUpdateTime: 2018-07-29T00:31:48Z
    message: TFJob tfjob is running.
    reason: TFJobRunning
    status: "True"
    type: Running
  startTime: 2018-07-29T21:40:13Z
  tfReplicaStatuses:
    PS:
      active: 1
    Worker:
      active: 1