Skip to content

Latest commit

 

History

History
145 lines (135 loc) · 3.78 KB

run-tensorflow-experiment.md

File metadata and controls

145 lines (135 loc) · 3.78 KB

Run TensorFlow Experiment Guide

Experiment Spec

The experiment is represented in JSON or YAML format.

YAML Format:

meta:
  name: "tf-mnist-yaml"
  namespace: "default"
  framework: "TensorFlow"
  cmd: "python /var/tf_mnist/mnist_with_summaries.py --log_dir=/train/log --learning_rate=0.01 --batch_size=150"
  envVars:
    ENV_1: "ENV1"
environment:
  image: "gcr.io/kubeflow-ci/tf-mnist-with-summaries:1.0"
spec:
  Ps:
    replicas: 1
    resources: "cpu=1,memory=1024M"
  Worker:
    replicas: 1
    resources: "cpu=1,memory=1024M"

JSON Format:

{
  "meta": {
    "name": "tf-mnist-json",
    "namespace": "default",
    "framework": "TensorFlow",
    "cmd": "python /var/tf_mnist/mnist_with_summaries.py --log_dir=/train/log --learning_rate=0.01 --batch_size=150",
    "envVars": {
      "ENV_1": "ENV1"
    }
  },
  "environment": {
    "image": "gcr.io/kubeflow-ci/tf-mnist-with-summaries:1.0"
  },
  "spec": {
    "Ps": {
      "replicas": 1,
      "resources": "cpu=1,memory=1024M"
    },
    "Worker": {
      "replicas": 1,
      "resources": "cpu=1,memory=1024M"
    }
  }
}

Create Experiment by REST API

POST /api/v1/experiment

Example Request

curl -X POST -H "Content-Type: application/json" -d '
{
  "meta": {
    "name": "tf-mnist-json",
    "namespace": "default",
    "framework": "TensorFlow",
    "cmd": "python /var/tf_mnist/mnist_with_summaries.py --log_dir=/train/log --learning_rate=0.01 --batch_size=150",
    "envVars": {
      "ENV_1": "ENV1"
    }
  },
  "environment": {
    "image": "gcr.io/kubeflow-ci/tf-mnist-with-summaries:1.0"
  },
  "spec": {
    "Ps": {
      "replicas": 1,
      "resources": "cpu=1,memory=1024M"
    },
    "Worker": {
      "replicas": 1,
      "resources": "cpu=1,memory=1024M"
    }
  }
}
' http://127.0.0.1:8080/api/v1/experiment

Example Response:

{
    "status": "OK",
    "code": 200,
    "result": {
        "experimentId": "experiment_1592057447228_0001",
        "name": "tf-mnist-json",
        "uid": "28e39dcd-77d4-11ea-8dbb-0242ac110003",
        "status": "Accepted",
        "acceptedTime": "2020-06-13T22:59:29.000+08:00",
        "spec": {
            "meta": {
                "name": "tf-mnist-json",
                "namespace": "default",
                "framework": "TensorFlow",
                "cmd": "python /var/tf_mnist/mnist_with_summaries.py --log_dir=/train/log --learning_rate=0.01 --batch_size=150",
                "envVars": {
                    "ENV_1": "ENV1"
                }
            },
            "environment": {
                "image": "gcr.io/kubeflow-ci/tf-mnist-with-summaries:1.0"
            },
            "spec": {
                "Ps": {
                    "replicas": 1,
                    "resources": "cpu=1,memory=1024M"
                },
                "Worker": {
                    "replicas": 1,
                    "resources": "cpu=1,memory=1024M"
                }
            }
        }
    }
}

More info see Experiment API Reference.