SAP-C02 · Question #424
A manufacturing company is building an inspection solution for its factory. The company has IP cameras at the end of each assembly line. The company has used Amazon SageMaker to train a machine…
The correct answer is B. Deploy AWS IoT Greengrass on the local server. Deploy the ML model to the Greengrass server. AWS IoT Greengrass enables ML inference locally using models that are created, trained, and optimized in the cloud using Amazon SageMaker, AWS Deep Learning AMI, or AWS Deep Learning Containers, and deployed on the edge devices…
Question
A manufacturing company is building an inspection solution for its factory. The company has IP cameras at the end of each assembly line. The company has used Amazon SageMaker to train a machine learning (ML) model to identify common defects from still images. The company wants to provide local feedback to factory workers when a defect is detected. The company must be able to provide this feedback even if the factory's internet connectivity is down. The company has a local Linux server that hosts an API that provides local feedback to the workers. How should the company deploy the ML model to meet these requirements?
Options
- ASet up an Amazon Kinesis video stream from each IP camera to AWS. Use Amazon EC2
- BDeploy AWS IoT Greengrass on the local server. Deploy the ML model to the Greengrass server.
- COrder an AWS Snowball device. Deploy a SageMaker endpoint the ML model and an Amazon
- DDeploy Amazon Monitron devices on each IP camera. Deploy an Amazon Monitron Gateway on
How the community answered
(21 responses)- A10% (2)
- B81% (17)
- C5% (1)
- D5% (1)
Explanation
AWS IoT Greengrass enables ML inference locally using models that are created, trained, and optimized in the cloud using Amazon SageMaker, AWS Deep Learning AMI, or AWS Deep Learning Containers, and deployed on the edge devices. https://aws.amazon.com/blogs/machine-learning/anomaly-detection-with-amazon-sagemaker- edge-manager-using-aws-iot-greengrass-v2/
Community Discussion
No community discussion yet for this question.