def test_async_fit_deploy(sagemaker_session, pytorch_full_version):
training_job_name = ""
# TODO: add tests against local mode when it's ready to be used
instance_type = 'ml.p2.xlarge'
with timeout(minutes=10):
pytorch = _get_pytorch_estimator(sagemaker_session,
pytorch_full_version, instance_type)
pytorch.fit({'training': _upload_training_data(pytorch)}, wait=False)
training_job_name = pytorch.latest_training_job.name
print("Waiting to re-attach to the training job: %s" %
training_job_name)
time.sleep(20)
if not _is_local_mode(instance_type):
endpoint_name = 'test-pytorch-async-fit-attach-deploy-{}'.format(
sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name,
sagemaker_session):
print("Re-attaching now to: %s" % training_job_name)
estimator = PyTorch.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1,
instance_type,
endpoint_name=endpoint_name)
batch_size = 100
data = numpy.random.rand(batch_size, 1, 28,
28).astype(numpy.float32)
output = predictor.predict(data)
assert output.shape == (batch_size, 10)
def test_async_fit_deploy(sagemaker_session, pytorch_full_version):
training_job_name = ""
# TODO: add tests against local mode when it's ready to be used
instance_type = 'ml.p2.xlarge'
with timeout(minutes=10):
pytorch = _get_pytorch_estimator(sagemaker_session, pytorch_full_version, instance_type)
pytorch.fit({'training': _upload_training_data(pytorch)}, wait=False)
training_job_name = pytorch.latest_training_job.name
print("Waiting to re-attach to the training job: %s" % training_job_name)
time.sleep(20)
if not _is_local_mode(instance_type):
endpoint_name = 'test-pytorch-async-fit-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
print("Re-attaching now to: %s" % training_job_name)
estimator = PyTorch.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, instance_type, endpoint_name=endpoint_name)
batch_size = 100
data = numpy.random.rand(batch_size, 1, 28, 28).astype(numpy.float32)
output = predictor.predict(data)
assert output.shape == (batch_size, 10)
def test_sync_fit_deploy(pytorch_training_job, sagemaker_session, cpu_instance_type):
# TODO: add tests against local mode when it's ready to be used
endpoint_name = "test-pytorch-sync-fit-attach-deploy{}".format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = PyTorch.attach(pytorch_training_job, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, cpu_instance_type, endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28), dtype=numpy.float32)
predictor.predict(data)
batch_size = 100
data = numpy.random.rand(batch_size, 1, 28, 28).astype(numpy.float32)
output = predictor.predict(data)
assert output.shape == (batch_size, 10)
def test_sync_fit_deploy(pytorch_training_job, sagemaker_session):
# TODO: add tests against local mode when it's ready to be used
endpoint_name = 'test-pytorch-sync-fit-attach-deploy{}'.format(sagemaker_timestamp())
with timeout(minutes=20):
estimator = PyTorch.attach(pytorch_training_job, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, 'ml.c4.xlarge', endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28), dtype=numpy.float32)
predictor.predict(data)
batch_size = 100
data = numpy.random.rand(batch_size, 1, 28, 28).astype(numpy.float32)
output = predictor.predict(data)
assert output.shape == (batch_size, 10)
