A data scientist uses SAS DLPy to train a CNN on an image dataset stored in CAS. After training, they want to apply the model to score new images. Which method is used in SAS DLPy to score new data?
Select an answer to reveal the explanation.
Short Explanation
You use model.predict() with the new image table because SAS DLPy applies the trained CNN to CAS data and returns predicted labels and probabilities. The fit method trains the model, so it doesn't score new images.
Full Explanation
The correct method is model.predict() with the new image table because the SAS DLPy Model class provides a predict() method that applies the trained model to a new image table in CAS and returns predicted labels and probabilities. The option using model.fit() with the test dataset is wrong because fit() is used for training, not scoring. The option saying model.score() returns predictions is wrong because model.score() exists in DLPy but is used to compute accuracy metrics, not to return predictions on new data. The option naming cas.deepLearn.dlScore() with the model weights table is wrong because it names a valid underlying CAS action, but the DLPy API exposes this through predict(), not direct CAS action calls.