In SAS DLPy, a data scientist trains a deep learning model and uses the model.get_feature_maps() method. What does this method return?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you use model.get_feature_maps() to run input images through the model and grab the activation outputs at chosen intermediate layers. That lets you see what patterns the network detected for those images.
Full Explanation
The option saying it returns intermediate activation outputs at specified layers for given input images is correct because model.get_feature_maps() in SAS DLPy applies the model to input images and returns activation outputs, or feature maps, at specified intermediate layers, letting you visualize what patterns each convolutional layer detected for specific inputs. The learned weight matrices option is wrong because those are kernel weights accessed through different DLPy methods. The gradient values option is wrong because that is gradient inspection, a different debugging capability. The learnable parameters summary option is wrong because parameter counts are typically shown by model.print_summary().