mirror of
https://github.com/hanzo-ml/katib.git
synced 2026-09-24 00:31:27 +00:00
Ayush GuptaandGitHub
1c19d3a6eb
* Fix Istio sidecar injection by moving from annotations to labels Signed-off-by: madmecodes <[email protected]> * Update Istio sidecar injection from annotations to labels across the codebase Replace annotations with labels for Istio sidecar injection according to Istio recommendations. Update conformance tests, examples, constants, composers, and utilities to use the new label-based approach consistently. Signed-off-by: madmecodes <[email protected]> * fix: Update SuggestionLabels function and composer implementation for Istio label injection Signed-off-by: madmecodes <[email protected]> * Fix linting issues in mpi-job-horovod.py Signed-off-by: madmecodes <[email protected]> * update: function moved from annotations to labels Signed-off-by: madmecodes <[email protected]> --------- Signed-off-by: madmecodes <[email protected]>
38 KiB
38 KiB
In [1]:
# Install required package (Katib SDK).
# TODO (andreyvelich): Update this example with the latest SDK.
!pip install kubeflow-katib==0.13.0Requirement already satisfied: kubeflow-katib==0.13.0 in /opt/conda/lib/python3.8/site-packages (0.13.0) Requirement already satisfied: kubernetes>=12.0.0 in /opt/conda/lib/python3.8/site-packages (from kubeflow-katib==0.13.0) (12.0.1) Requirement already satisfied: six>=1.10 in /opt/conda/lib/python3.8/site-packages (from kubeflow-katib==0.13.0) (1.16.0) Requirement already satisfied: certifi>=14.05.14 in /opt/conda/lib/python3.8/site-packages (from kubeflow-katib==0.13.0) (2021.5.30) Requirement already satisfied: urllib3>=1.15.1 in /opt/conda/lib/python3.8/site-packages (from kubeflow-katib==0.13.0) (1.26.5) Requirement already satisfied: setuptools>=21.0.0 in /opt/conda/lib/python3.8/site-packages (from kubeflow-katib==0.13.0) (49.6.0.post20210108) Requirement already satisfied: pyyaml>=3.12 in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (5.4.1) Requirement already satisfied: requests in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (2.25.1) Requirement already satisfied: google-auth>=1.0.1 in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (1.35.0) Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (1.0.1) Requirement already satisfied: requests-oauthlib in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (1.3.1) Requirement already satisfied: python-dateutil>=2.5.3 in /opt/conda/lib/python3.8/site-packages (from kubernetes>=12.0.0->kubeflow-katib==0.13.0) (2.8.1) Requirement already satisfied: rsa<5,>=3.1.4 in /opt/conda/lib/python3.8/site-packages (from google-auth>=1.0.1->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (4.8) Requirement already satisfied: pyasn1-modules>=0.2.1 in /opt/conda/lib/python3.8/site-packages (from google-auth>=1.0.1->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (0.2.8) Requirement already satisfied: cachetools<5.0,>=2.0.0 in /opt/conda/lib/python3.8/site-packages (from google-auth>=1.0.1->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (4.2.4) Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /opt/conda/lib/python3.8/site-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (0.4.8) Requirement already satisfied: chardet<5,>=3.0.2 in /opt/conda/lib/python3.8/site-packages (from requests->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (4.0.0) Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.8/site-packages (from requests->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (2.10) Requirement already satisfied: oauthlib>=3.0.0 in /opt/conda/lib/python3.8/site-packages (from requests-oauthlib->kubernetes>=12.0.0->kubeflow-katib==0.13.0) (3.2.0)
In [2]:
from kubeflow.katib import KatibClient
from kubernetes.client import V1ObjectMeta
from kubeflow.katib import V1beta1Experiment
from kubeflow.katib import V1beta1AlgorithmSpec
from kubeflow.katib import V1beta1AlgorithmSetting
from kubeflow.katib import V1beta1ObjectiveSpec
from kubeflow.katib import V1beta1MetricsCollectorSpec
from kubeflow.katib import V1beta1CollectorSpec
from kubeflow.katib import V1beta1SourceSpec
from kubeflow.katib import V1beta1FilterSpec
from kubeflow.katib import V1beta1FeasibleSpace
from kubeflow.katib import V1beta1ExperimentSpec
from kubeflow.katib import V1beta1NasConfig
from kubeflow.katib import V1beta1GraphConfig
from kubeflow.katib import V1beta1Operation
from kubeflow.katib import V1beta1ParameterSpec
from kubeflow.katib import V1beta1TrialTemplate
from kubeflow.katib import V1beta1TrialParameterSpecIn [3]:
# Experiment name and namespace.
namespace = "kubeflow-user-example-com"
experiment_name = "darts-example"
metadata = V1ObjectMeta(
name=experiment_name,
namespace=namespace
)
# Algorithm specification.
algorithm_spec=V1beta1AlgorithmSpec(
algorithm_name="darts",
algorithm_settings=[
V1beta1AlgorithmSetting(
name="num_epochs",
value="2"
),
V1beta1AlgorithmSetting(
name="stem_multiplier",
value="1"
),
V1beta1AlgorithmSetting(
name="init_channels",
value="4"
),
V1beta1AlgorithmSetting(
name="num_nodes",
value="3"
),
]
)
# Objective specification. For DARTS Goal is omitted.
objective_spec=V1beta1ObjectiveSpec(
type="maximize",
objective_metric_name="Best-Genotype",
)
# Metrics collector specification.
# We should specify metrics format to get Genotype from training container.
metrics_collector_spec=V1beta1MetricsCollectorSpec(
collector=V1beta1CollectorSpec(
kind="StdOut"
),
source=V1beta1SourceSpec(
filter=V1beta1FilterSpec(
metrics_format=[
"([\\w-]+)=(Genotype.*)"
]
)
)
)
# Configuration for the Neural Network (NN).
# This NN contains 2 number of layers and 5 various operations with different parameters.
nas_config=V1beta1NasConfig(
graph_config=V1beta1GraphConfig(
num_layers=2
),
operations=[
V1beta1Operation(
operation_type="separable_convolution",
parameters=[
V1beta1ParameterSpec(
name="filter_size",
parameter_type="categorical",
feasible_space=V1beta1FeasibleSpace(
list=["3"]
),
)
]
),
V1beta1Operation(
operation_type="dilated_convolution",
parameters=[
V1beta1ParameterSpec(
name="filter_size",
parameter_type="categorical",
feasible_space=V1beta1FeasibleSpace(
list=["3", "5"]
),
)
]
),
V1beta1Operation(
operation_type="avg_pooling",
parameters=[
V1beta1ParameterSpec(
name="filter_size",
parameter_type="categorical",
feasible_space=V1beta1FeasibleSpace(
list=["3"]
),
)
]
),
V1beta1Operation(
operation_type="max_pooling",
parameters=[
V1beta1ParameterSpec(
name="filter_size",
parameter_type="categorical",
feasible_space=V1beta1FeasibleSpace(
list=["3"]
),
)
]
),
V1beta1Operation(
operation_type="skip_connection",
),
]
)
# JSON template specification for the Trial's Worker Kubernetes Job.
trial_spec={
"apiVersion": "batch/v1",
"kind": "Job",
"spec": {
"template": {
"metadata": {
"labels": {
"sidecar.istio.io/inject": "false"
}
},
"spec": {
"containers": [
{
"name": "training-container",
"image": "docker.io/kubeflowkatib/darts-cnn-cifar10:v0.13.0",
"command": [
'python3',
'run_trial.py',
'--algorithm-settings="${trialParameters.algorithmSettings}"',
'--search-space="${trialParameters.searchSpace}"',
'--num-layers="${trialParameters.numberLayers}"'
],
# Training container requires 1 GPU.
"resources": {
"limits": {
"nvidia.com/gpu": 1
}
}
}
],
"restartPolicy": "Never"
}
}
}
}
# Template with Trial parameters and Trial spec.
# Set retain to True to save trial resources after completion.
trial_template=V1beta1TrialTemplate(
retain=True,
primary_container_name="training-container",
trial_parameters=[
V1beta1TrialParameterSpec(
name="algorithmSettings",
description=" Algorithm settings of DARTS Experiment",
reference="algorithm-settings"
),
V1beta1TrialParameterSpec(
name="searchSpace",
description="Search Space of DARTS Experiment",
reference="search-space"
),
V1beta1TrialParameterSpec(
name="numberLayers",
description="Number of Neural Network layers",
reference="num-layers"
),
],
trial_spec=trial_spec
)
# Experiment object.
experiment = V1beta1Experiment(
api_version="kubeflow.org/v1beta1",
kind="Experiment",
metadata=metadata,
spec=V1beta1ExperimentSpec(
max_trial_count=1,
parallel_trial_count=1,
max_failed_trial_count=1,
algorithm=algorithm_spec,
objective=objective_spec,
metrics_collector_spec=metrics_collector_spec,
nas_config=nas_config,
trial_template=trial_template,
)
)In [4]:
# Print the Trial template container info.
print(experiment.spec.trial_template.trial_spec["spec"]["template"]["spec"]["containers"][0]){'name': 'training-container', 'image': 'docker.io/kubeflowkatib/darts-cnn-cifar10:v0.13.0', 'command': ['python3', 'run_trial.py', '--algorithm-settings="${trialParameters.algorithmSettings}"', '--search-space="${trialParameters.searchSpace}"', '--num-layers="${trialParameters.numberLayers}"'], 'resources': {'limits': {'nvidia.com/gpu': 1}}}
In [5]:
# Create client.
kclient = KatibClient()
# Create your Experiment.
kclient.create_experiment(experiment,namespace=namespace)Out [5]:
Katib Experiment darts-example link here
{'apiVersion': 'kubeflow.org/v1beta1',
'kind': 'Experiment',
'metadata': {'creationTimestamp': '2021-10-05T23:49:49Z',
'generation': 1,
'managedFields': [{'apiVersion': 'kubeflow.org/v1beta1',
'fieldsType': 'FieldsV1',
'fieldsV1': {'f:spec': {'.': {},
'f:algorithm': {'.': {},
'f:algorithmName': {},
'f:algorithmSettings': {}},
'f:maxFailedTrialCount': {},
'f:maxTrialCount': {},
'f:metricsCollectorSpec': {'.': {},
'f:collector': {'.': {}, 'f:kind': {}},
'f:source': {'.': {}, 'f:filter': {'.': {}, 'f:metricsFormat': {}}}},
'f:nasConfig': {'.': {},
'f:graphConfig': {'.': {}, 'f:numLayers': {}},
'f:operations': {}},
'f:objective': {'.': {}, 'f:objectiveMetricName': {}, 'f:type': {}},
'f:parallelTrialCount': {},
'f:trialTemplate': {'.': {},
'f:primaryContainerName': {},
'f:retain': {},
'f:trialParameters': {},
'f:trialSpec': {'.': {},
'f:apiVersion': {},
'f:kind': {},
'f:spec': {'.': {},
'f:template': {'.': {},
'f:metadata': {'.': {},
'f:annotations': {'.': {}, 'f:sidecar.istio.io/inject': {}}},
'f:spec': {'.': {}, 'f:containers': {}, 'f:restartPolicy': {}}}}}}}},
'manager': 'OpenAPI-Generator',
'operation': 'Update',
'time': '2021-10-05T23:49:49Z'}],
'name': 'darts-example',
'namespace': 'kubeflow-user-example-com',
'resourceVersion': '393947521',
'uid': '3fbda962-64c0-4474-b1de-03b390f96369'},
'spec': {'algorithm': {'algorithmName': 'darts',
'algorithmSettings': [{'name': 'num_epochs', 'value': '2'},
{'name': 'stem_multiplier', 'value': '1'},
{'name': 'init_channels', 'value': '4'},
{'name': 'num_nodes', 'value': '3'}]},
'maxFailedTrialCount': 1,
'maxTrialCount': 1,
'metricsCollectorSpec': {'collector': {'kind': 'StdOut'},
'source': {'filter': {'metricsFormat': ['([\\w-]+)=(Genotype.*)']}}},
'nasConfig': {'graphConfig': {'numLayers': 2},
'operations': [{'operationType': 'separable_convolution',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'dilated_convolution',
'parameters': [{'feasibleSpace': {'list': ['3', '5']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'avg_pooling',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'max_pooling',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'skip_connection'}]},
'objective': {'metricStrategies': [{'name': 'Best-Genotype',
'value': 'max'}],
'objectiveMetricName': 'Best-Genotype',
'type': 'maximize'},
'parallelTrialCount': 1,
'resumePolicy': 'Never',
'trialTemplate': {'failureCondition': 'status.conditions.#(type=="Failed")#|#(status=="True")#',
'primaryContainerName': 'training-container',
'retain': True,
'successCondition': 'status.conditions.#(type=="Complete")#|#(status=="True")#',
'trialParameters': [{'description': ' Algorithm settings of DARTS Experiment',
'name': 'algorithmSettings',
'reference': 'algorithm-settings'},
{'description': 'Search Space of DARTS Experiment',
'name': 'searchSpace',
'reference': 'search-space'},
{'description': 'Number of Neural Network layers',
'name': 'numberLayers',
'reference': 'num-layers'}],
'trialSpec': {'apiVersion': 'batch/v1',
'kind': 'Job',
'spec': {'template': {'metadata': {'annotations': {'sidecar.istio.io/inject': 'false'}},
'spec': {'containers': [{'command': ['python3',
'run_trial.py',
'--algorithm-settings="${trialParameters.algorithmSettings}"',
'--search-space="${trialParameters.searchSpace}"',
'--num-layers="${trialParameters.numberLayers}"'],
'image': 'docker.io/kubeflowkatib/darts-cnn-cifar10:v0.13.0',
'name': 'training-container',
'resources': {'limits': {'nvidia.com/gpu': 1}}}],
'restartPolicy': 'Never'}}}}}}}In [6]:
exp = kclient.get_experiment(name=experiment_name, namespace=namespace)
print(exp)
print("-----------------\n")
# Get the latest status.
print(exp["status"]["conditions"][-1]){'apiVersion': 'kubeflow.org/v1beta1', 'kind': 'Experiment', 'metadata': {'creationTimestamp': '2021-10-05T23:49:49Z', 'finalizers': ['update-prometheus-metrics'], 'generation': 1, 'managedFields': [{'apiVersion': 'kubeflow.org/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:spec': {'.': {}, 'f:algorithm': {'.': {}, 'f:algorithmName': {}, 'f:algorithmSettings': {}}, 'f:maxFailedTrialCount': {}, 'f:maxTrialCount': {}, 'f:metricsCollectorSpec': {'.': {}, 'f:collector': {'.': {}, 'f:kind': {}}, 'f:source': {'.': {}, 'f:filter': {'.': {}, 'f:metricsFormat': {}}}}, 'f:nasConfig': {'.': {}, 'f:graphConfig': {'.': {}, 'f:numLayers': {}}, 'f:operations': {}}, 'f:objective': {'.': {}, 'f:objectiveMetricName': {}, 'f:type': {}}, 'f:parallelTrialCount': {}, 'f:trialTemplate': {'.': {}, 'f:primaryContainerName': {}, 'f:retain': {}, 'f:trialParameters': {}, 'f:trialSpec': {'.': {}, 'f:apiVersion': {}, 'f:kind': {}, 'f:spec': {'.': {}, 'f:template': {'.': {}, 'f:metadata': {'.': {}, 'f:annotations': {'.': {}, 'f:sidecar.istio.io/inject': {}}}, 'f:spec': {'.': {}, 'f:containers': {}, 'f:restartPolicy': {}}}}}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2021-10-05T23:49:49Z'}, {'apiVersion': 'kubeflow.org/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"update-prometheus-metrics"': {}}}, 'f:status': {'.': {}, 'f:conditions': {}, 'f:currentOptimalTrial': {'.': {}, 'f:bestTrialName': {}, 'f:observation': {'.': {}, 'f:metrics': {}}, 'f:parameterAssignments': {}}, 'f:runningTrialList': {}, 'f:startTime': {}, 'f:trials': {}, 'f:trialsRunning': {}}}, 'manager': 'katib-controller', 'operation': 'Update', 'time': '2021-10-05T23:50:31Z'}], 'name': 'darts-example', 'namespace': 'kubeflow-user-example-com', 'resourceVersion': '393948698', 'uid': '3fbda962-64c0-4474-b1de-03b390f96369'}, 'spec': {'algorithm': {'algorithmName': 'darts', 'algorithmSettings': [{'name': 'num_epochs', 'value': '2'}, {'name': 'stem_multiplier', 'value': '1'}, {'name': 'init_channels', 'value': '4'}, {'name': 'num_nodes', 'value': '3'}]}, 'maxFailedTrialCount': 1, 'maxTrialCount': 1, 'metricsCollectorSpec': {'collector': {'kind': 'StdOut'}, 'source': {'filter': {'metricsFormat': ['([\\w-]+)=(Genotype.*)']}}}, 'nasConfig': {'graphConfig': {'numLayers': 2}, 'operations': [{'operationType': 'separable_convolution', 'parameters': [{'feasibleSpace': {'list': ['3']}, 'name': 'filter_size', 'parameterType': 'categorical'}]}, {'operationType': 'dilated_convolution', 'parameters': [{'feasibleSpace': {'list': ['3', '5']}, 'name': 'filter_size', 'parameterType': 'categorical'}]}, {'operationType': 'avg_pooling', 'parameters': [{'feasibleSpace': {'list': ['3']}, 'name': 'filter_size', 'parameterType': 'categorical'}]}, {'operationType': 'max_pooling', 'parameters': [{'feasibleSpace': {'list': ['3']}, 'name': 'filter_size', 'parameterType': 'categorical'}]}, {'operationType': 'skip_connection'}]}, 'objective': {'metricStrategies': [{'name': 'Best-Genotype', 'value': 'max'}], 'objectiveMetricName': 'Best-Genotype', 'type': 'maximize'}, 'parallelTrialCount': 1, 'resumePolicy': 'Never', 'trialTemplate': {'failureCondition': 'status.conditions.#(type=="Failed")#|#(status=="True")#', 'primaryContainerName': 'training-container', 'retain': True, 'successCondition': 'status.conditions.#(type=="Complete")#|#(status=="True")#', 'trialParameters': [{'description': ' Algorithm settings of DARTS Experiment', 'name': 'algorithmSettings', 'reference': 'algorithm-settings'}, {'description': 'Search Space of DARTS Experiment', 'name': 'searchSpace', 'reference': 'search-space'}, {'description': 'Number of Neural Network layers', 'name': 'numberLayers', 'reference': 'num-layers'}], 'trialSpec': {'apiVersion': 'batch/v1', 'kind': 'Job', 'spec': {'template': {'metadata': {'annotations': {'sidecar.istio.io/inject': 'false'}}, 'spec': {'containers': [{'command': ['python3', 'run_trial.py', '--algorithm-settings="${trialParameters.algorithmSettings}"', '--search-space="${trialParameters.searchSpace}"', '--num-layers="${trialParameters.numberLayers}"'], 'image': 'docker.io/kubeflowkatib/darts-cnn-cifar10:v0.13.0', 'name': 'training-container', 'resources': {'limits': {'nvidia.com/gpu': 1}}}], 'restartPolicy': 'Never'}}}}}}, 'status': {'conditions': [{'lastTransitionTime': '2021-10-05T23:49:49Z', 'lastUpdateTime': '2021-10-05T23:49:49Z', 'message': 'Experiment is created', 'reason': 'ExperimentCreated', 'status': 'True', 'type': 'Created'}, {'lastTransitionTime': '2021-10-05T23:50:30Z', 'lastUpdateTime': '2021-10-05T23:50:30Z', 'message': 'Experiment is running', 'reason': 'ExperimentRunning', 'status': 'True', 'type': 'Running'}], 'currentOptimalTrial': {'bestTrialName': '', 'observation': {'metrics': None}, 'parameterAssignments': None}, 'runningTrialList': ['darts-example-n4fpnxlm'], 'startTime': '2021-10-05T23:49:49Z', 'trials': 1, 'trialsRunning': 1}}
-----------------
{'lastTransitionTime': '2021-10-05T23:50:30Z', 'lastUpdateTime': '2021-10-05T23:50:30Z', 'message': 'Experiment is running', 'reason': 'ExperimentRunning', 'status': 'True', 'type': 'Running'}
In [7]:
kclient.get_experiment_status(name=experiment_name, namespace=namespace)Out [7]:
'Succeeded'
In [8]:
kclient.is_experiment_succeeded(name=experiment_name, namespace=namespace)Out [8]:
True
In [9]:
opt_trial = kclient.get_optimal_hyperparameters(name=experiment_name, namespace=namespace)
best_genotype = opt_trial["currentOptimalTrial"]["observation"]["metrics"][0]["latest"]
print(best_genotype)Genotype(normal=[[('separable_convolution_3x3',0),('dilated_convolution_3x3',1)],[('dilated_convolution_3x3',2),('dilated_convolution_5x5',1)],[('dilated_convolution_5x5',2),('separable_convolution_3x3',3)]],normal_concat=range(2,5),reduce=[[('separable_convolution_3x3',1),('separable_convolution_3x3',0)],[('max_pooling_3x3',2),('max_pooling_3x3',1)],[('max_pooling_3x3',2),('max_pooling_3x3',3)]],reduce_concat=range(2,5))
In [10]:
kclient.delete_experiment(name=experiment_name, namespace=namespace)Out [10]:
{'apiVersion': 'kubeflow.org/v1beta1',
'kind': 'Experiment',
'metadata': {'creationTimestamp': '2021-10-05T23:49:49Z',
'deletionGracePeriodSeconds': 0,
'deletionTimestamp': '2021-10-05T23:58:39Z',
'finalizers': ['update-prometheus-metrics'],
'generation': 2,
'managedFields': [{'apiVersion': 'kubeflow.org/v1beta1',
'fieldsType': 'FieldsV1',
'fieldsV1': {'f:spec': {'.': {},
'f:algorithm': {'.': {},
'f:algorithmName': {},
'f:algorithmSettings': {}},
'f:maxFailedTrialCount': {},
'f:maxTrialCount': {},
'f:metricsCollectorSpec': {'.': {},
'f:collector': {'.': {}, 'f:kind': {}},
'f:source': {'.': {}, 'f:filter': {'.': {}, 'f:metricsFormat': {}}}},
'f:nasConfig': {'.': {},
'f:graphConfig': {'.': {}, 'f:numLayers': {}},
'f:operations': {}},
'f:objective': {'.': {}, 'f:objectiveMetricName': {}, 'f:type': {}},
'f:parallelTrialCount': {},
'f:trialTemplate': {'.': {},
'f:primaryContainerName': {},
'f:retain': {},
'f:trialParameters': {},
'f:trialSpec': {'.': {},
'f:apiVersion': {},
'f:kind': {},
'f:spec': {'.': {},
'f:template': {'.': {},
'f:metadata': {'.': {},
'f:annotations': {'.': {}, 'f:sidecar.istio.io/inject': {}}},
'f:spec': {'.': {}, 'f:containers': {}, 'f:restartPolicy': {}}}}}}}},
'manager': 'OpenAPI-Generator',
'operation': 'Update',
'time': '2021-10-05T23:49:49Z'},
{'apiVersion': 'kubeflow.org/v1beta1',
'fieldsType': 'FieldsV1',
'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {},
'v:"update-prometheus-metrics"': {}}},
'f:status': {'.': {},
'f:completionTime': {},
'f:conditions': {},
'f:currentOptimalTrial': {'.': {},
'f:bestTrialName': {},
'f:observation': {'.': {}, 'f:metrics': {}},
'f:parameterAssignments': {}},
'f:startTime': {},
'f:succeededTrialList': {},
'f:trials': {},
'f:trialsSucceeded': {}}},
'manager': 'katib-controller',
'operation': 'Update',
'time': '2021-10-05T23:54:31Z'}],
'name': 'darts-example',
'namespace': 'kubeflow-user-example-com',
'resourceVersion': '393962398',
'uid': '3fbda962-64c0-4474-b1de-03b390f96369'},
'spec': {'algorithm': {'algorithmName': 'darts',
'algorithmSettings': [{'name': 'num_epochs', 'value': '2'},
{'name': 'stem_multiplier', 'value': '1'},
{'name': 'init_channels', 'value': '4'},
{'name': 'num_nodes', 'value': '3'}]},
'maxFailedTrialCount': 1,
'maxTrialCount': 1,
'metricsCollectorSpec': {'collector': {'kind': 'StdOut'},
'source': {'filter': {'metricsFormat': ['([\\w-]+)=(Genotype.*)']}}},
'nasConfig': {'graphConfig': {'numLayers': 2},
'operations': [{'operationType': 'separable_convolution',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'dilated_convolution',
'parameters': [{'feasibleSpace': {'list': ['3', '5']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'avg_pooling',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'max_pooling',
'parameters': [{'feasibleSpace': {'list': ['3']},
'name': 'filter_size',
'parameterType': 'categorical'}]},
{'operationType': 'skip_connection'}]},
'objective': {'metricStrategies': [{'name': 'Best-Genotype',
'value': 'max'}],
'objectiveMetricName': 'Best-Genotype',
'type': 'maximize'},
'parallelTrialCount': 1,
'resumePolicy': 'Never',
'trialTemplate': {'failureCondition': 'status.conditions.#(type=="Failed")#|#(status=="True")#',
'primaryContainerName': 'training-container',
'retain': True,
'successCondition': 'status.conditions.#(type=="Complete")#|#(status=="True")#',
'trialParameters': [{'description': ' Algorithm settings of DARTS Experiment',
'name': 'algorithmSettings',
'reference': 'algorithm-settings'},
{'description': 'Search Space of DARTS Experiment',
'name': 'searchSpace',
'reference': 'search-space'},
{'description': 'Number of Neural Network layers',
'name': 'numberLayers',
'reference': 'num-layers'}],
'trialSpec': {'apiVersion': 'batch/v1',
'kind': 'Job',
'spec': {'template': {'metadata': {'annotations': {'sidecar.istio.io/inject': 'false'}},
'spec': {'containers': [{'command': ['python3',
'run_trial.py',
'--algorithm-settings="${trialParameters.algorithmSettings}"',
'--search-space="${trialParameters.searchSpace}"',
'--num-layers="${trialParameters.numberLayers}"'],
'image': 'docker.io/kubeflowkatib/darts-cnn-cifar10:v0.13.0',
'name': 'training-container',
'resources': {'limits': {'nvidia.com/gpu': 1}}}],
'restartPolicy': 'Never'}}}}}},
'status': {'completionTime': '2021-10-05T23:54:31Z',
'conditions': [{'lastTransitionTime': '2021-10-05T23:49:49Z',
'lastUpdateTime': '2021-10-05T23:49:49Z',
'message': 'Experiment is created',
'reason': 'ExperimentCreated',
'status': 'True',
'type': 'Created'},
{'lastTransitionTime': '2021-10-05T23:54:31Z',
'lastUpdateTime': '2021-10-05T23:54:31Z',
'message': 'Experiment is running',
'reason': 'ExperimentRunning',
'status': 'False',
'type': 'Running'},
{'lastTransitionTime': '2021-10-05T23:54:31Z',
'lastUpdateTime': '2021-10-05T23:54:31Z',
'message': 'Experiment has succeeded because max trial count has reached',
'reason': 'ExperimentMaxTrialsReached',
'status': 'True',
'type': 'Succeeded'}],
'currentOptimalTrial': {'bestTrialName': 'darts-example-n4fpnxlm',
'observation': {'metrics': [{'latest': "Genotype(normal=[[('separable_convolution_3x3',0),('dilated_convolution_3x3',1)],[('dilated_convolution_3x3',2),('dilated_convolution_5x5',1)],[('dilated_convolution_5x5',2),('separable_convolution_3x3',3)]],normal_concat=range(2,5),reduce=[[('separable_convolution_3x3',1),('separable_convolution_3x3',0)],[('max_pooling_3x3',2),('max_pooling_3x3',1)],[('max_pooling_3x3',2),('max_pooling_3x3',3)]],reduce_concat=range(2,5))",
'max': 'unavailable',
'min': 'unavailable',
'name': 'Best-Genotype'}]},
'parameterAssignments': [{'name': 'algorithm-settings',
'value': "{'num_epochs': '2', 'w_lr': 0.025, 'w_lr_min': 0.001, 'w_momentum': 0.9, 'w_weight_decay': 0.0003, 'w_grad_clip': 5.0, 'alpha_lr': 0.0003, 'alpha_weight_decay': 0.001, 'batch_size': 128, 'num_workers': 4, 'init_channels': '4', 'print_step': 50, 'num_nodes': '3', 'stem_multiplier': '1'}"},
{'name': 'search-space',
'value': "['separable_convolution_3x3', 'dilated_convolution_3x3', 'dilated_convolution_5x5', 'avg_pooling_3x3', 'max_pooling_3x3', 'skip_connection']"},
{'name': 'num-layers', 'value': '2'}]},
'startTime': '2021-10-05T23:49:49Z',
'succeededTrialList': ['darts-example-n4fpnxlm'],
'trials': 1,
'trialsSucceeded': 1}}In [ ]: