CODEWITHSUNDEEP
amazon-sagemaker
Dao Kieu Vi
Dao Kieu Vi

Reputation: 143

How to run PipelineModel SageMaker at the local

Can we create a PipelineModel and run a batch transform at the local? I don't see any document about this. I tried but get the error

sagemaker_session = LocalSession()
sagemaker_session.config = {'local': {'local_code': True}}
model_1 = PyTorchModel(...)
model_2 = PyTorchModel(...)
model = PipelineModel(models=[model_1, model_2])
transformer = model.transformer(...)
transformer.transform(...)

self.sagemaker_client.create_model(**create_model_request)
TypeError: create_model() missing 1 required positional argument: 'PrimaryContainer'

Upvotes: 0

Views: 477

Answers (1)

Dao Kieu Vi
Dao Kieu Vi

Reputation: 143

It's still a feature request:

https://github.com/aws/sagemaker-python-sdk/issues/1846

Upvotes: 2

Related Questions