def test_transform_byo_estimator(sagemaker_session, cpu_instance_type):
data_path = os.path.join(DATA_DIR, "one_p_mnist")
pickle_args = {} if sys.version_info.major == 2 else {"encoding": "latin1"}
tags = [{"Key": "some-tag", "Value": "value-for-tag"}]
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, "mnist.pkl.gz")
with gzip.open(train_set_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(
role="SageMakerRole",
train_instance_count=1,
train_instance_type=cpu_instance_type,
k=10,
sagemaker_session=sagemaker_session,
output_path="s3://{}/".format(sagemaker_session.default_bucket()),
)
# set kmeans specific hp
kmeans.init_method = "random"
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = "kmeans++"
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
job_name = unique_name_from_base("test-kmeans-attach")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
estimator = Estimator.attach(training_job_name=job_name, sagemaker_session=sagemaker_session)
estimator._enable_network_isolation = True
transform_input_path = os.path.join(data_path, "transform_input.csv")
transform_input_key_prefix = "integ-test-data/one_p_mnist/transform"
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix
)
transformer = estimator.transformer(1, cpu_instance_type, tags=tags)
transformer.transform(transform_input, content_type="text/csv")
with timeout_and_delete_model_with_transformer(
transformer, sagemaker_session, minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES
):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name
)
assert model_desc["EnableNetworkIsolation"]
model_tags = sagemaker_session.sagemaker_client.list_tags(
ResourceArn=model_desc["ModelArn"]
)["Tags"]
assert tags == model_tags
def test_async_byo_estimator(sagemaker_session, region):
image_name = registry(region) + "/factorization-machines:1"
endpoint_name = unique_name_from_base('byo')
training_data_path = os.path.join(DATA_DIR, 'dummy_tensor')
training_job_name = ""
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {
'encoding': 'latin1'
}
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
prefix = 'test_byo_estimator'
key = 'recordio-pb-data'
s3_train_data = sagemaker_session.upload_data(path=training_data_path,
key_prefix=os.path.join(
prefix, 'train',
key))
estimator = Estimator(image_name=image_name,
role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session,
base_job_name='test-byo')
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type='binary_classifier')
# training labels must be 'float32'
estimator.fit({'train': s3_train_data}, wait=False)
training_job_name = estimator.latest_training_job.name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(1,
'ml.m4.xlarge',
endpoint_name=endpoint_name)
predictor.serializer = fm_serializer
predictor.content_type = 'application/json'
predictor.deserializer = sagemaker.predictor.json_deserializer
result = predictor.predict(train_set[0][:10])
assert len(result['predictions']) == 10
for prediction in result['predictions']:
assert prediction['score'] is not None
assert estimator.train_image() == image_name
def test_async_byo_estimator(sagemaker_session, region):
image_name = registry(region) + "/factorization-machines:1"
endpoint_name = unique_name_from_base("byo")
training_data_path = os.path.join(DATA_DIR, "dummy_tensor")
job_name = unique_name_from_base("byo")
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, "one_p_mnist", "mnist.pkl.gz")
pickle_args = {} if sys.version_info.major == 2 else {
"encoding": "latin1"
}
with gzip.open(data_path, "rb") as f:
train_set, _, _ = pickle.load(f, **pickle_args)
prefix = "test_byo_estimator"
key = "recordio-pb-data"
s3_train_data = sagemaker_session.upload_data(path=training_data_path,
key_prefix=os.path.join(
prefix, "train",
key))
estimator = Estimator(
image_name=image_name,
role="SageMakerRole",
train_instance_count=1,
train_instance_type="ml.c4.xlarge",
sagemaker_session=sagemaker_session,
)
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type="binary_classifier")
# training labels must be 'float32'
estimator.fit({"train": s3_train_data}, wait=False, job_name=job_name)
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(1,
"ml.m4.xlarge",
endpoint_name=endpoint_name)
predictor.serializer = fm_serializer
predictor.content_type = "application/json"
predictor.deserializer = sagemaker.predictor.json_deserializer
result = predictor.predict(train_set[0][:10])
assert len(result["predictions"]) == 10
for prediction in result["predictions"]:
assert prediction["score"] is not None
assert estimator.train_image() == image_name
def load_model(self, model_name: str = "") -> None:
"""
Load the already trained model to not have to train again.
Arguments:
model_name: The name of the training job, as provided by AWS
"""
LOGGER.info(f"Loading already trained model {model_name}")
self._model = Estimator.attach(training_job_name=model_name,
sagemaker_session=self.executor.session)
def test_async_byo_estimator(sagemaker_session, region):
image_name = registry(region) + "/factorization-machines:1"
endpoint_name = name_from_base('byo')
training_job_name = ""
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
# take 100 examples for faster execution
vectors = np.array([t.tolist() for t in train_set[0][:100]]).astype('float32')
labels = np.where(np.array([t.tolist() for t in train_set[1][:100]]) == 0, 1.0, 0.0).astype('float32')
buf = io.BytesIO()
write_numpy_to_dense_tensor(buf, vectors, labels)
buf.seek(0)
bucket = sagemaker_session.default_bucket()
prefix = 'test_byo_estimator'
key = 'recordio-pb-data'
boto3.resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train', key)).upload_fileobj(buf)
s3_train_data = 's3://{}/{}/train/{}'.format(bucket, prefix, key)
estimator = Estimator(image_name=image_name,
role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session, base_job_name='test-byo')
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type='binary_classifier')
# training labels must be 'float32'
estimator.fit({'train': s3_train_data}, wait=False)
training_job_name = estimator.latest_training_job.name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
predictor.serializer = fm_serializer
predictor.content_type = 'application/json'
predictor.deserializer = sagemaker.predictor.json_deserializer
result = predictor.predict(train_set[0][:10])
assert len(result['predictions']) == 10
for prediction in result['predictions']:
assert prediction['score'] is not None
assert estimator.train_image() == image_name
def test_transform_byo_estimator(sagemaker_session):
data_path = os.path.join(DATA_DIR, 'one_p_mnist')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
tags = [{'Key': 'some-tag', 'Value': 'value-for-tag'}]
# Load the data into memory as numpy arrays
train_set_path = os.path.join(data_path, 'mnist.pkl.gz')
with gzip.open(train_set_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
kmeans = KMeans(role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
k=10,
sagemaker_session=sagemaker_session,
output_path='s3://{}/'.format(
sagemaker_session.default_bucket()))
# set kmeans specific hp
kmeans.init_method = 'random'
kmeans.max_iterators = 1
kmeans.tol = 1
kmeans.num_trials = 1
kmeans.local_init_method = 'kmeans++'
kmeans.half_life_time_size = 1
kmeans.epochs = 1
records = kmeans.record_set(train_set[0][:100])
job_name = unique_name_from_base('test-kmeans-attach')
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
kmeans.fit(records, job_name=job_name)
transform_input_path = os.path.join(data_path, 'transform_input.csv')
transform_input_key_prefix = 'integ-test-data/one_p_mnist/transform'
transform_input = kmeans.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
estimator = Estimator.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
transformer = estimator.transformer(1, 'ml.m4.xlarge', tags=tags)
transformer.transform(transform_input, content_type='text/csv')
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name)
model_tags = sagemaker_session.sagemaker_client.list_tags(
ResourceArn=model_desc['ModelArn'])['Tags']
assert tags == model_tags
def test_async_byo_estimator(sagemaker_session, region):
image_name = registry(region) + "/factorization-machines:1"
endpoint_name = name_from_base('byo')
training_job_name = ""
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
# take 100 examples for faster execution
vectors = np.array([t.tolist() for t in train_set[0][:100]]).astype('float32')
labels = np.where(np.array([t.tolist() for t in train_set[1][:100]]) == 0, 1.0, 0.0).astype('float32')
buf = io.BytesIO()
write_numpy_to_dense_tensor(buf, vectors, labels)
buf.seek(0)
bucket = sagemaker_session.default_bucket()
prefix = 'test_byo_estimator'
key = 'recordio-pb-data'
boto3.resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train', key)).upload_fileobj(buf)
s3_train_data = 's3://{}/{}/train/{}'.format(bucket, prefix, key)
estimator = Estimator(image_name=image_name,
role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session, base_job_name='test-byo')
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type='binary_classifier')
# training labels must be 'float32'
estimator.fit({'train': s3_train_data}, wait=False)
training_job_name = estimator.latest_training_job.name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
predictor.serializer = fm_serializer
predictor.content_type = 'application/json'
predictor.deserializer = sagemaker.predictor.json_deserializer
result = predictor.predict(train_set[0][:10])
assert len(result['predictions']) == 10
for prediction in result['predictions']:
assert prediction['score'] is not None
assert estimator.train_image() == image_name
def test_async_byo_estimator(sagemaker_session, region, cpu_instance_type,
training_set):
image_uri = image_uris.retrieve("factorization-machines", region)
endpoint_name = unique_name_from_base("byo")
training_data_path = os.path.join(DATA_DIR, "dummy_tensor")
job_name = unique_name_from_base("byo")
with timeout(minutes=5):
prefix = "test_byo_estimator"
key = "recordio-pb-data"
s3_train_data = sagemaker_session.upload_data(path=training_data_path,
key_prefix=os.path.join(
prefix, "train",
key))
estimator = Estimator(
image_uri=image_uri,
role="SageMakerRole",
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
)
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type="binary_classifier")
# training labels must be 'float32'
estimator.fit({"train": s3_train_data}, wait=False, job_name=job_name)
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=job_name,
sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(
1,
cpu_instance_type,
endpoint_name=endpoint_name,
serializer=_FactorizationMachineSerializer(),
deserializer=sagemaker.deserializers.JSONDeserializer(),
)
result = predictor.predict(training_set[0][:10])
assert len(result["predictions"]) == 10
for prediction in result["predictions"]:
assert prediction["score"] is not None
assert estimator.training_image_uri() == image_uri
def test_async_byo_estimator(sagemaker_session, region):
image_name = registry(region) + "/factorization-machines:1"
endpoint_name = name_from_base('byo')
training_data_path = os.path.join(DATA_DIR, 'dummy_tensor')
training_job_name = ""
with timeout(minutes=5):
data_path = os.path.join(DATA_DIR, 'one_p_mnist', 'mnist.pkl.gz')
pickle_args = {} if sys.version_info.major == 2 else {'encoding': 'latin1'}
with gzip.open(data_path, 'rb') as f:
train_set, _, _ = pickle.load(f, **pickle_args)
prefix = 'test_byo_estimator'
key = 'recordio-pb-data'
s3_train_data = sagemaker_session.upload_data(path=training_data_path,
key_prefix=os.path.join(prefix, 'train', key))
estimator = Estimator(image_name=image_name,
role='SageMakerRole', train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session, base_job_name='test-byo')
estimator.set_hyperparameters(num_factors=10,
feature_dim=784,
mini_batch_size=100,
predictor_type='binary_classifier')
# training labels must be 'float32'
estimator.fit({'train': s3_train_data}, wait=False)
training_job_name = estimator.latest_training_job.name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = Estimator.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
model = estimator.create_model()
predictor = model.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
predictor.serializer = fm_serializer
predictor.content_type = 'application/json'
predictor.deserializer = sagemaker.predictor.json_deserializer
result = predictor.predict(train_set[0][:10])
assert len(result['predictions']) == 10
for prediction in result['predictions']:
assert prediction['score'] is not None
assert estimator.train_image() == image_name
