In SAS DLPy, which function is used to instantiate a pre-built convolutional neural network architecture like ResNet-50?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you use dlpy.applications.ResNet50() because SAS DLPy provides pre-built architecture functions in the dlpy.applications module. It instantiates the ResNet-50 architecture against a CAS session. You don't build it with a Keras-style sequential API.
Full Explanation
The correct function is dlpy.applications.ResNet50(), because SAS DLPy provides pre-built architecture functions in the dlpy.applications module, including ResNet50(), which instantiates the ResNet-50 architecture against a CAS session. The dlpy.Sequential().add(ResNet50Layer()) approach is wrong because SAS DLPy does not use a Sequential() API like Keras. The cas.deepLearn.buildResNet50() call is wrong because there is no cas.deepLearn.buildResNet50() CAS action; the action set uses different naming. The PROC HPNEURAL with ARCHITECTURE=RESNET50 approach is wrong because PROC HPNEURAL does not support an ARCHITECTURE= option for pre-built deep learning architectures.