Skip to content

Add an example for local mode deployment of models #304

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 20, 2018
Merged

Add an example for local mode deployment of models #304

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2540a55
Add an example for local mode deployment of models
Jul 18, 2018
f263abc
Merge branch 'master' into local_model_model_doc_update
laurenyu Jul 20, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions README.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,6 +192,30 @@ instance type.
mxnet_estimator.delete_endpoint()


If you have an existing model and would like to deploy it locally you can do that as well. If you don't
specify a sagemaker_session argument to the MXNetModel constructor, the right session will be generated
when calling model.deploy()
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This still sounds like a choice to me - shouldn't we just instruct the user to not supply a session object? (or would there be a reason for a user to want to construct a local session separately?)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is similar to how the rest of the SDK works. they can provide their own Local Session if they want, with custom config settings.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is a better wording ?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe something like "This requires a Local Session (maybe include a link to documentation?) to run. If you don't specify..." or "If you want to specify a sagemaker session, make sure it's a local session"


Here is an end to end example:

.. code:: python

import numpy
from sagemaker.mxnet import MXNetModel

model_location = 's3://mybucket/my_model.tar.gz'
code_location = 's3://mybucket/sourcedir.tar.gz'
s3_model = MXNetModel(model_data=model_location, role='SageMakerRole',
entry_point='mnist.py', source_dir=code_location)

predictor = s3_model.deploy(initial_instance_count=1, instance_type='local')
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)

# Tear down the endpoint container
predictor.delete_endpoint()


For detailed examples of running docker in local mode, see:

- `TensorFlow local mode example notebook <https://github.com/awslabs/amazon-sagemaker-examples/blob/master/sagemaker-python-sdk/tensorflow_distributed_mnist/tensorflow_local_mode_mnist.ipynb>`__.
Expand Down