KubeFlow安装指南

时间:2025-03-24 15:45:51
  • apiVersion: /v1alpha2
  • kind: TFJob
  • metadata:
  • annotations:
  • /managed: '{"pristine":"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"}'
  • clusterName: ""
  • creationTimestamp: 2018-09-26T15:33:07Z
  • generation: 0
  • labels:
  • /deploy-manager: ksonnet
  • /component: mycnnjob
  • name: mycnnjob
  • namespace: default
  • resourceVersion: "2293964"
  • selfLink: /apis//v1alpha2/namespaces/default/tfjobs/mycnnjob
  • uid: 777da1bb-c1a1-11e8-8661-fa163e4006b8
  • spec:
  • cleanPodPolicy: Running
  • tfReplicaSpecs:
  • PS:
  • replicas: 1
  • restartPolicy: Never
  • 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=cpu
  • - --data_format=NHWC
  • image: /kubeflow/tf-benchmarks-cpu: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
  • restartPolicy: Never
  • 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=cpu
  • - --data_format=NHWC
  • image: /kubeflow/tf-benchmarks-cpu:v20171202-bdab599-dirty-284af3
  • name: tensorflow
  • ports:
  • - containerPort: 2222
  • name: tfjob-port
  • resources: {}
  • workingDir: /opt/tf-benchmarks/scripts/tf_cnn_benchmarks
  • restartPolicy: OnFailure
  • status:
  • completionTime: 2018-09-26T15:33:58Z
  • conditions:
  • - lastTransitionTime: 2018-09-26T15:33:07Z
  • lastUpdateTime: 2018-09-26T15:33:07Z
  • message: TFJob mycnnjob is created.
  • reason: TFJobCreated
  • status: "True"
  • type: Created
  • - lastTransitionTime: 2018-09-26T15:33:07Z
  • lastUpdateTime: 2018-09-26T15:33:10Z
  • message: TFJob mycnnjob is running.
  • reason: TFJobRunning
  • status: "False"
  • type: Running
  • - lastTransitionTime: 2018-09-26T15:33:07Z
  • lastUpdateTime: 2018-09-26T15:33:58Z
  • message: TFJob mycnnjob is failed.
  • reason: TFJobFailed
  • status: "True"
  • type: Failed
  • startTime: 2018-09-26T15:33:10Z
  • tfReplicaStatuses:
  • Chief: {}
  • Master: {}
  • PS: {}
  • Worker: {}