def test_attach_wrong_framework(sagemaker_session):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0.4'
rjd = {'AlgorithmSpecification': {'TrainingInputMode': 'File',
'TrainingImage': training_image},
'HyperParameters':
{'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'checkpoint_path': '"s3://other/1508872349"',
'sagemaker_program': '"iris-dnn-classifier.py"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'training_steps': '100',
'sagemaker_region': '"us-west-2"'},
'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
'ResourceConfig':
{'VolumeSizeInGB': 30,
'InstanceCount': 1,
'InstanceType': 'ml.c4.xlarge'},
'StoppingCondition': {'MaxRuntimeInSeconds': 24 * 60 * 60},
'TrainingJobName': 'neo',
'TrainingJobStatus': 'Completed',
'OutputDataConfig': {'KmsKeyId': '',
'S3OutputPath': 's3://place/output/neo'},
'TrainingJobOutput': {'S3TrainingJobOutput': 's3://here/output.tar.gz'}}
sagemaker_session.sagemaker_client.describe_training_job = Mock(name='describe_training_job',
return_value=rjd)
with pytest.raises(ValueError) as error:
RLEstimator.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert "didn't use image for requested framework" in str(error)
def test_attach_wrong_framework(sagemaker_session):
training_image = "1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0.4"
rjd = {
"AlgorithmSpecification": {"TrainingInputMode": "File", "TrainingImage": training_image},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"checkpoint_path": '"s3://other/1508872349"',
"sagemaker_program": '"iris-dnn-classifier.py"',
"sagemaker_enable_cloudwatch_metrics": "false",
"sagemaker_container_log_level": '"logging.INFO"',
"training_steps": "100",
"sagemaker_region": '"us-west-2"',
},
"RoleArn": "arn:aws:iam::366:role/SageMakerRole",
"ResourceConfig": {
"VolumeSizeInGB": 30,
"InstanceCount": 1,
"InstanceType": "ml.c4.xlarge",
},
"StoppingCondition": {"MaxRuntimeInSeconds": 24 * 60 * 60},
"TrainingJobName": "neo",
"TrainingJobStatus": "Completed",
"TrainingJobArn": "arn:aws:sagemaker:us-west-2:336:training-job/neo",
"OutputDataConfig": {"KmsKeyId": "", "S3OutputPath": "s3://place/output/neo"},
"TrainingJobOutput": {"S3TrainingJobOutput": "s3://here/output.tar.gz"},
}
sagemaker_session.sagemaker_client.describe_training_job = Mock(
name="describe_training_job", return_value=rjd
)
with pytest.raises(ValueError) as error:
RLEstimator.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert "didn't use image for requested framework" in str(error)
def test_coach_mxnet(sagemaker_session, coach_mxnet_latest_version, cpu_instance_type):
estimator = _test_coach(
sagemaker_session, RLFramework.MXNET, coach_mxnet_latest_version, cpu_instance_type
)
job_name = unique_name_from_base("test-coach-mxnet")
with timeout(minutes=15):
estimator.fit(wait="False", job_name=job_name)
estimator = RLEstimator.attach(
estimator.latest_training_job.name, sagemaker_session=sagemaker_session
)
endpoint_name = "test-mxnet-coach-deploy-{}".format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
predictor = estimator.deploy(
1, cpu_instance_type, entry_point="mxnet_deploy.py", endpoint_name=endpoint_name
)
observation = numpy.asarray([0, 0, 0, 0])
action = predictor.predict(observation)
assert 0 < action[0][0] < 1
assert 0 < action[0][1] < 1
def test_attach_custom_image(sagemaker_session):
training_image = 'rl:latest'
returned_job_description = {'AlgorithmSpecification': {'TrainingInputMode': 'File',
'TrainingImage': training_image},
'HyperParameters':
{'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'sagemaker_program': '"iris-dnn-classifier.py"',
'sagemaker_s3_uri_training': '"sagemaker-3/integ-test-data/tf_iris"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'sagemaker_region': '"us-west-2"'},
'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
'ResourceConfig':
{'VolumeSizeInGB': 30,
'InstanceCount': 1,
'InstanceType': 'ml.c4.xlarge'},
'StoppingCondition': {'MaxRuntimeInSeconds': 24 * 60 * 60},
'TrainingJobName': 'neo',
'TrainingJobStatus': 'Completed',
'OutputDataConfig':
{'KmsKeyId': '',
'S3OutputPath': 's3://place/output/neo'},
'TrainingJobOutput':
{'S3TrainingJobOutput': 's3://here/output.tar.gz'}}
sagemaker_session.sagemaker_client.describe_training_job = \
Mock(name='describe_training_job', return_value=returned_job_description)
estimator = RLEstimator.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == 'neo'
assert estimator.image_name == training_image
assert estimator.train_image() == training_image
def test_attach_custom_image(sagemaker_session):
training_image = "rl:latest"
returned_job_description = {
"AlgorithmSpecification": {"TrainingInputMode": "File", "TrainingImage": training_image},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"sagemaker_program": '"iris-dnn-classifier.py"',
"sagemaker_s3_uri_training": '"sagemaker-3/integ-test-data/tf_iris"',
"sagemaker_enable_cloudwatch_metrics": "false",
"sagemaker_container_log_level": '"logging.INFO"',
"sagemaker_job_name": '"neo"',
"training_steps": "100",
"sagemaker_region": '"us-west-2"',
},
"RoleArn": "arn:aws:iam::366:role/SageMakerRole",
"ResourceConfig": {
"VolumeSizeInGB": 30,
"InstanceCount": 1,
"InstanceType": "ml.c4.xlarge",
},
"StoppingCondition": {"MaxRuntimeInSeconds": 24 * 60 * 60},
"TrainingJobName": "neo",
"TrainingJobStatus": "Completed",
"TrainingJobArn": "arn:aws:sagemaker:us-west-2:336:training-job/neo",
"OutputDataConfig": {"KmsKeyId": "", "S3OutputPath": "s3://place/output/neo"},
"TrainingJobOutput": {"S3TrainingJobOutput": "s3://here/output.tar.gz"},
}
sagemaker_session.sagemaker_client.describe_training_job = Mock(
name="describe_training_job", return_value=returned_job_description
)
estimator = RLEstimator.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == "neo"
assert estimator.image_name == training_image
assert estimator.train_image() == training_image
def test_attach(sagemaker_session, rl_coach_mxnet_version):
training_image = "1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-rl-{}:{}{}-cpu-py3".format(
RLFramework.MXNET.value, RLToolkit.COACH.value, rl_coach_mxnet_version
)
supported_versions = TOOLKIT_FRAMEWORK_VERSION_MAP[RLToolkit.COACH.value]
framework_version = supported_versions[rl_coach_mxnet_version][RLFramework.MXNET.value]
returned_job_description = {
"AlgorithmSpecification": {"TrainingInputMode": "File", "TrainingImage": training_image},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"sagemaker_program": '"train_coach.py"',
"sagemaker_enable_cloudwatch_metrics": "false",
"sagemaker_container_log_level": '"logging.INFO"',
"sagemaker_job_name": '"neo"',
"training_steps": "100",
"sagemaker_region": '"us-west-2"',
},
"RoleArn": "arn:aws:iam::366:role/SageMakerRole",
"ResourceConfig": {
"VolumeSizeInGB": 30,
"InstanceCount": 1,
"InstanceType": "ml.c4.xlarge",
},
"StoppingCondition": {"MaxRuntimeInSeconds": 24 * 60 * 60},
"TrainingJobName": "neo",
"TrainingJobStatus": "Completed",
"TrainingJobArn": "arn:aws:sagemaker:us-west-2:336:training-job/neo",
"OutputDataConfig": {"KmsKeyId": "", "S3OutputPath": "s3://place/output/neo"},
"TrainingJobOutput": {"S3TrainingJobOutput": "s3://here/output.tar.gz"},
}
sagemaker_session.sagemaker_client.describe_training_job = Mock(
name="describe_training_job", return_value=returned_job_description
)
estimator = RLEstimator.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == "neo"
assert estimator.framework == RLFramework.MXNET.value
assert estimator.toolkit == RLToolkit.COACH.value
assert estimator.framework_version == framework_version
assert estimator.toolkit_version == rl_coach_mxnet_version
assert estimator.role == "arn:aws:iam::366:role/SageMakerRole"
assert estimator.train_instance_count == 1
assert estimator.train_max_run == 24 * 60 * 60
assert estimator.input_mode == "File"
assert estimator.base_job_name == "neo"
assert estimator.output_path == "s3://place/output/neo"
assert estimator.output_kms_key == ""
assert estimator.hyperparameters()["training_steps"] == "100"
assert estimator.source_dir == "s3://some/sourcedir.tar.gz"
assert estimator.entry_point == "train_coach.py"
assert estimator.metric_definitions == RLEstimator.default_metric_definitions(RLToolkit.COACH)
def test_attach(sagemaker_session, rl_coach_mxnet_version):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-rl-{}:{}{}-cpu-py3'\
.format(RLFramework.MXNET.value, RLToolkit.COACH.value, rl_coach_mxnet_version)
supported_versions = TOOLKIT_FRAMEWORK_VERSION_MAP[RLToolkit.COACH.value]
framework_version = supported_versions[rl_coach_mxnet_version][RLFramework.MXNET.value]
returned_job_description = {'AlgorithmSpecification': {'TrainingInputMode': 'File',
'TrainingImage': training_image},
'HyperParameters':
{'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'sagemaker_program': '"train_coach.py"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'sagemaker_region': '"us-west-2"'},
'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
'ResourceConfig':
{'VolumeSizeInGB': 30,
'InstanceCount': 1,
'InstanceType': 'ml.c4.xlarge'},
'StoppingCondition': {'MaxRuntimeInSeconds': 24 * 60 * 60},
'TrainingJobName': 'neo',
'TrainingJobStatus': 'Completed',
'OutputDataConfig': {'KmsKeyId': '',
'S3OutputPath': 's3://place/output/neo'},
'TrainingJobOutput': {
'S3TrainingJobOutput': 's3://here/output.tar.gz'}}
sagemaker_session.sagemaker_client.describe_training_job = \
Mock(name='describe_training_job', return_value=returned_job_description)
estimator = RLEstimator.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == 'neo'
assert estimator.framework == RLFramework.MXNET.value
assert estimator.toolkit == RLToolkit.COACH.value
assert estimator.framework_version == framework_version
assert estimator.toolkit_version == rl_coach_mxnet_version
assert estimator.role == 'arn:aws:iam::366:role/SageMakerRole'
assert estimator.train_instance_count == 1
assert estimator.train_max_run == 24 * 60 * 60
assert estimator.input_mode == 'File'
assert estimator.base_job_name == 'neo'
assert estimator.output_path == 's3://place/output/neo'
assert estimator.output_kms_key == ''
assert estimator.hyperparameters()['training_steps'] == '100'
assert estimator.source_dir == 's3://some/sourcedir.tar.gz'
assert estimator.entry_point == 'train_coach.py'
assert estimator.metric_definitions == RLEstimator.default_metric_definitions(RLToolkit.COACH)
def test_coach_mxnet(sagemaker_session, rl_coach_full_version):
estimator = _test_coach(sagemaker_session, RLFramework.MXNET, rl_coach_full_version)
with timeout(minutes=15):
estimator.fit(wait='False')
estimator = RLEstimator.attach(estimator.latest_training_job.name,
sagemaker_session=sagemaker_session)
endpoint_name = 'test-mxnet-coach-deploy-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
predictor = estimator.deploy(1, CPU_INSTANCE, entry_point='mxnet_deploy.py',
endpoint_name=endpoint_name)
observation = numpy.asarray([0, 0, 0, 0])
action = predictor.predict(observation)
assert 0 < action[0][0] < 1
assert 0 < action[0][1] < 1
