Which SAS DLPy architecture is most appropriate for detecting and localizing multiple objects within a single image?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you want object detection, so you need an architecture that finds and localizes multiple objects in one image. A YOLO or similar object detection model in SAS DLPy does that by predicting classes and bounding boxes together.
Full Explanation
The correct choice is the YOLO or similar object detection architecture in DLPy built-in models because object detection requires identifying and localizing multiple objects with bounding boxes. YOLO, Faster R-CNN, and SSD predict class labels and bounding coordinates simultaneously, and SAS DLPy includes YOLO variants. The standard sequential CNN with a single Dense output layer classifying the whole image performs image-level classification, not localization. The LSTM network processing image pixels as time-series sequences is suited to sequential data. The PCA pipeline reducing image dimensions before k-means clustering of object regions is unsupervised and unsuitable for detection.