def test_attach_wrong_framework(sagemaker_session):
returned_job_description = {'AlgorithmSpecification':
{'TrainingInputMode': 'File',
'TrainingImage': '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0'},
'HyperParameters':
{'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'sagemaker_program': '"iris-dnn-classifier.py"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'training_steps': '100'},
'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)
with pytest.raises(ValueError) as error:
TensorFlow.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):
returned_job_description = {
"AlgorithmSpecification": {
"TrainingInputMode": "File",
"TrainingImage": "1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0",
},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"sagemaker_program": '"iris-dnn-classifier.py"',
"sagemaker_enable_cloudwatch_metrics": "false",
"sagemaker_container_log_level": '"logging.INFO"',
"training_steps": "100",
},
"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
)
with pytest.raises(ValueError) as error:
TensorFlow.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert "didn't use image for requested framework" in str(error)
def test_mnist_async(sagemaker_session):
estimator = TensorFlow(entry_point=SCRIPT,
role=ROLE,
train_instance_count=1,
train_instance_type='ml.c5.4xlarge',
sagemaker_session=sagemaker_session,
py_version='py3',
framework_version=TensorFlow.LATEST_VERSION,
base_job_name=unique_name_from_base('test-tf-sm-mnist'),
tags=TAGS)
inputs = estimator.sagemaker_session.upload_data(
path=os.path.join(RESOURCE_PATH, 'data'),
key_prefix='scriptmode/mnist')
estimator.fit(inputs, wait=False)
training_job_name = estimator.latest_training_job.name
time.sleep(20)
endpoint_name = training_job_name
_assert_training_job_tags_match(sagemaker_session.sagemaker_client, estimator.latest_training_job.name, TAGS)
with timeout.timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = TensorFlow.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge',
endpoint_name=endpoint_name)
result = predictor.predict(np.zeros(784))
print('predict result: {}'.format(result))
_assert_endpoint_tags_match(sagemaker_session.sagemaker_client, predictor.endpoint, TAGS)
_assert_model_tags_match(sagemaker_session.sagemaker_client, estimator.latest_training_job.name, TAGS)
def test_attach_new_repo_name(sagemaker_session, tf_version):
training_image = '520713654638.dkr.ecr.us-west-2.amazonaws.com/sagemaker-tensorflow:{}-cpu-py2'.format(
tf_version)
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"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'evaluation_steps': '10'
},
'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)
estimator = TensorFlow.attach(training_job_name='neo',
sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == 'neo'
assert estimator.py_version == 'py2'
assert estimator.framework_version == tf_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.training_steps == 100
assert estimator.evaluation_steps == 10
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 == 'iris-dnn-classifier.py'
assert estimator.checkpoint_path == 's3://other/1508872349'
assert estimator.train_image() == training_image
def test_attach(sagemaker_session, tf_version):
training_image = "1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-tensorflow-py2-cpu:{}-cpu-py2".format(
tf_version)
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"',
"sagemaker_job_name": '"neo"',
"training_steps": "100",
"evaluation_steps": "10",
},
"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)
estimator = TensorFlow.attach(training_job_name="neo",
sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == "neo"
assert estimator.py_version == "py2"
assert estimator.framework_version == tf_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.training_steps == 100
assert estimator.evaluation_steps == 10
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 == "iris-dnn-classifier.py"
assert estimator.checkpoint_path == "s3://other/1508872349"
def test_attach_custom_image(sagemaker_session):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/tensorflow_with_custom_binary:1.0'
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"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'evaluation_steps': '10'},
'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)
estimator = TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.image_name == training_image
assert estimator.train_image() == training_image
def test_tf_async(sagemaker_session):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')
estimator = TensorFlow(entry_point=script_path,
role='SageMakerRole',
training_steps=1,
evaluation_steps=1,
hyperparameters={'input_tensor_name': 'inputs'},
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session,
base_job_name='test-tf')
inputs = estimator.sagemaker_session.upload_data(
path=DATA_PATH, key_prefix='integ-test-data/tf_iris')
estimator.fit(inputs, wait=False)
training_job_name = estimator.latest_training_job.name
time.sleep(20)
endpoint_name = training_job_name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = TensorFlow.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
json_predictor = estimator.deploy(initial_instance_count=1,
instance_type='ml.c4.xlarge',
endpoint_name=endpoint_name)
result = json_predictor.predict([6.4, 3.2, 4.5, 1.5])
print('predict result: {}'.format(result))
def test_tf_async(sagemaker_session):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')
estimator = TensorFlow(entry_point=script_path,
role='SageMakerRole',
training_steps=1,
evaluation_steps=1,
hyperparameters={'input_tensor_name': 'inputs'},
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session,
base_job_name='test-tf')
inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf_iris')
estimator.fit(inputs, wait=False)
training_job_name = estimator.latest_training_job.name
time.sleep(20)
endpoint_name = training_job_name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = TensorFlow.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
json_predictor = estimator.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge',
endpoint_name=endpoint_name)
result = json_predictor.predict([6.4, 3.2, 4.5, 1.5])
print('predict result: {}'.format(result))
def test_attach_custom_image(sagemaker_session):
training_image = "1.dkr.ecr.us-west-2.amazonaws.com/tensorflow_with_custom_binary:1.0"
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"',
"sagemaker_job_name": '"neo"',
"training_steps": "100",
"evaluation_steps": "10",
},
"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
)
estimator = TensorFlow.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert estimator.image_name == training_image
assert estimator.train_image() == training_image
def test_attach_custom_image(sagemaker_session):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/tensorflow_with_custom_binary:1.0'
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"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'evaluation_steps': '10'},
'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)
estimator = TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.image_name == training_image
assert estimator.train_image() == training_image
def test_attach(sagemaker_session, tensorflow_training_version, tensorflow_training_py_version):
if Version(tensorflow_training_version) > Version("1.12"):
pytest.skip("framework_name_from_image doesn't infer info from DLC image URIs.")
training_image = image_uris.retrieve(
"tensorflow",
region=REGION,
version=tensorflow_training_version,
py_version=tensorflow_training_py_version,
instance_type="ml.c4.xlarge",
image_scope="training",
)
rjd = {
"AlgorithmSpecification": {"TrainingInputMode": "File", "TrainingImage": training_image},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"sagemaker_program": '"iris-dnn-classifier.py"',
"sagemaker_container_log_level": '"logging.INFO"',
"sagemaker_job_name": '"neo"',
},
"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
)
estimator = TensorFlow.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == "neo"
assert estimator.py_version == tensorflow_training_py_version
assert estimator.framework_version == tensorflow_training_version
assert estimator.role == "arn:aws:iam::366:role/SageMakerRole"
assert estimator.instance_count == 1
assert estimator.max_run == 24 * 60 * 60
assert estimator.input_mode == "File"
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() is not None
assert estimator.source_dir == "s3://some/sourcedir.tar.gz"
assert estimator.entry_point == "iris-dnn-classifier.py"
assert estimator.training_image_uri() == training_image
def test_attach_wrong_framework(sagemaker_session):
returned_job_description = {
'AlgorithmSpecification': {
'TrainingInputMode': 'File',
'TrainingImage': '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0'
},
'HyperParameters': {
'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'sagemaker_program': '"iris-dnn-classifier.py"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'training_steps': '100'
},
'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)
with pytest.raises(ValueError) as error:
TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert "didn't use image for requested framework" in str(error)
def test_attach(sagemaker_session, tf_version):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-tensorflow-py2-cpu:{}-cpu-py2'.format(tf_version)
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"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'evaluation_steps': '10'
},
'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)
estimator = TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == 'neo'
assert estimator.py_version == 'py2'
assert estimator.framework_version == tf_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.training_steps == 100
assert estimator.evaluation_steps == 10
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 == 'iris-dnn-classifier.py'
assert estimator.checkpoint_path == 's3://other/1508872349'
def test_mnist_async(sagemaker_session, cpu_instance_type, tf_full_version,
tf_full_py_version):
if tf_full_version == "2.7.0":
tf_full_version = "2.7"
estimator = TensorFlow(
entry_point=SCRIPT,
source_dir=MNIST_RESOURCE_PATH,
role=ROLE,
instance_count=1,
instance_type="ml.c5.4xlarge",
sagemaker_session=sagemaker_session,
framework_version=tf_full_version,
py_version=tf_full_py_version,
tags=TAGS,
)
inputs = estimator.sagemaker_session.upload_data(
path=os.path.join(MNIST_RESOURCE_PATH, "data"),
key_prefix="scriptmode/mnist")
estimator.fit(inputs=inputs,
wait=False,
job_name=unique_name_from_base("test-tf-sm-async"))
training_job_name = estimator.latest_training_job.name
time.sleep(20)
endpoint_name = training_job_name
_assert_training_job_tags_match(sagemaker_session.sagemaker_client,
estimator.latest_training_job.name, TAGS)
with tests.integ.timeout.timeout_and_delete_endpoint_by_name(
endpoint_name, sagemaker_session):
estimator = TensorFlow.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
model_name = "model-mnist-async"
predictor = estimator.deploy(
initial_instance_count=1,
instance_type=cpu_instance_type,
endpoint_name=endpoint_name,
model_name=model_name,
)
result = predictor.predict(np.zeros(784))
print("predict result: {}".format(result))
_assert_endpoint_tags_match(sagemaker_session.sagemaker_client,
predictor.endpoint_name, TAGS)
_assert_model_tags_match(sagemaker_session.sagemaker_client,
model_name, TAGS)
_assert_model_name_match(sagemaker_session.sagemaker_client,
endpoint_name, model_name)
def test_mnist_async(sagemaker_session, cpu_instance_type):
estimator = TensorFlow(
entry_point=SCRIPT,
role=ROLE,
train_instance_count=1,
train_instance_type="ml.c5.4xlarge",
py_version=tests.integ.PYTHON_VERSION,
sagemaker_session=sagemaker_session,
script_mode=True,
# testing py-sdk functionality, no need to run against all TF versions
framework_version=TensorFlow.LATEST_VERSION,
tags=TAGS,
)
inputs = estimator.sagemaker_session.upload_data(
path=os.path.join(MNIST_RESOURCE_PATH, "data"),
key_prefix="scriptmode/mnist")
estimator.fit(inputs=inputs,
wait=False,
job_name=unique_name_from_base("test-tf-sm-async"))
training_job_name = estimator.latest_training_job.name
time.sleep(20)
endpoint_name = training_job_name
_assert_training_job_tags_match(sagemaker_session.sagemaker_client,
estimator.latest_training_job.name, TAGS)
with tests.integ.timeout.timeout_and_delete_endpoint_by_name(
endpoint_name, sagemaker_session):
estimator = TensorFlow.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
model_name = "model-mnist-async"
predictor = estimator.deploy(
initial_instance_count=1,
instance_type=cpu_instance_type,
endpoint_name=endpoint_name,
model_name=model_name,
)
result = predictor.predict(np.zeros(784))
print("predict result: {}".format(result))
_assert_endpoint_tags_match(sagemaker_session.sagemaker_client,
predictor.endpoint, TAGS)
_assert_model_tags_match(sagemaker_session.sagemaker_client,
model_name, TAGS)
_assert_model_name_match(sagemaker_session.sagemaker_client,
endpoint_name, model_name)
