CODEWITHSUNDEEP
amazon-web-servicesamazon-sagemaker
user10031054
user10031054

Reputation: 11

Get weights after training from Sagemaker Estimator

Tensorflow's Estimator provides a method to get desired variable values after training/testing using get_variable_value. Does there exist similar functionality in Sagemaker's Estimator, so that I am able to obtain weights after my model is trained.

Upvotes: 1

Views: 781

Answers (1)

Leopd
Leopd

Reputation: 42769

For the Estimator object in the SageMaker Python SDK, after you call fit() you can call get the S3 URL of your model artifacts with

model_artifacts_url = estimator.create_model().model_data

The model itself is saved into your S3 bucket as a tarball at this location. So from here you can get the model parameters out of S3.

Upvotes: 1

Related Questions