Posted On: Jul 15, 2020
Amazon SageMaker Debugger is a new capability of Amazon SageMaker that provides complete insights into the training process of machine learning (ML) models by automating the capture and analysis of data from training runs at real time, with no code changes.
Amazon SageMaker Debugger is now available in the AWS GovCloud (US-West) region, an isolated region designed to address specific regulatory and compliance requirements of US Government agencies, as well as contractors, educational institutions, and other US customers that run sensitive workloads in the cloud.
Amazon SageMaker Debugger makes it much easier to easily analyze and debug model characteristics during training. When anomalies are detected, SageMaker Debugger sends alerts for developers’ to take remedial actions, reducing the time it takes to debug models from days to minutes. The debug data remains in the customer’s AWS account, allowing SageMaker Debugger to be used for most privacy-sensitive applications.
Amazon SageMaker Debugger is available in AWS GovCloud (US-West) starting today. To learn more, read the blog post, refer to the documentation, and try the examples to get started.