Question 234 of 280
Choose 2You have deployed a scikit-team model to a Vertex AI endpoint using a custom model server. You enabled autoscaling: however, the deployed model fails to scale beyond one replica, which led to dropped requests. You notice that CPU utilization remains low even during periods of high load. What should you do?
AAttach a GPU to the prediction nodes
✓BIncrease the number of workers in your model server
CSchedule scaling of the nodes to match expected demand
DIncrease the minReplicaCount in your DeployedModel configuration
✓ASend user-submitted images to the Cloud Vision API. Use object localization to identify all objects in the image and compare the results against a list of animals.
BDownload an object detection model from TensorFlow Hub. Deploy the model to a Vertex AI endpoint. Send new user-submitted images to the model endpoint to classify whether each photo has an animal.
CManually label previously submitted images with bounding boxes around any animals. Build an AutoML object detection model by using Vertex AI. Deploy the model to a Vertex AI endpoint Send new user-submitted images to your model endpoint to detect whether each photo has an animal.
DManually label previously submitted images as having animals or not. Create an image dataset on Vertex AI. Train a classification model by using Vertex AutoML to distinguish the two classes. Deploy the model to a Vertex AI endpoint. Send new user-submitted images to your model endpoint to classify whether each photo has an animal.
✓
Correct Answer: B, A
Increase the number of workers in your model server
▥
Explanation
The correct answer is highlighted above. Review the wording carefully, then use the next question to continue building your understanding of Google certification topics.