A DLPy sequential model is saved using model.save_to_astore(path='models/', name='fraud_dlpy_v1'). What is the purpose of saving to ASTORE format?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because the ASTORE (Analytic Store) format encapsulates the model in a SAS-native binary format that can be scored using PROC ASTORE, deployed via SAS Micro Analytic Service for real-time REST API scoring, or registered in SAS Model Manager — all without requiring Python or an active CAS session. This is the primary SAS deployment format for DLPy models.
Full explanation below image
Full Explanation
B is correct because the ASTORE (Analytic Store) format encapsulates the model in a SAS-native binary format that can be scored using PROC ASTORE, deployed via SAS Micro Analytic Service for real-time REST API scoring, or registered in SAS Model Manager — all without requiring Python or an active CAS session. This is the primary SAS deployment format for DLPy models. A is wrong; compression is not the purpose. C is wrong; ASTORE saves the full model, not just convolutional layers. D is wrong; ONNX export uses a different workflow.