Creating a multi-container Transform Job without creating an Endpoint?

[andremoeller]

Please fill out the form below.

System Information

• Framework (e.g. TensorFlow) / Algorithm (e.g. KMeans): N/A: BYO
• Framework Version: N/A: BYO
• Python Version: 3.5
• CPU or GPU: CPU
• Python SDK Version: 1.18.3
• Are you using a custom image: Yes.

Describe the problem

Is there an easy way to create a multi-container Transform Job from a PipelineModel without first creating an Endpoint?

PipelineModel itself doesn't have a transform method that returns a transformer:
https://github.com/aws/sagemaker-python-sdk/blob/master/src/sagemaker/pipeline.py

And the example notebooks both just use the model created by deploying the endpoint to create a transform job:

https://github.com/awslabs/amazon-sagemaker-examples/blob/master/advanced_functionality/inference_pipeline_sparkml_xgboost_abalone/inference_pipeline_sparkml_xgboost_abalone.ipynb

https://github.com/awslabs/amazon-sagemaker-examples/blob/master/advanced_functionality/inference_pipeline_sparkml_blazingtext_dbpedia/inference_pipeline_sparkml_blazingtext_dbpedia.ipynb

Thanks!

[andremoeller]

Closing since this was merged in.