Home icon

Create custom images for geospatial analysis with Amazon SageMaker Distribution in Amazon SageMaker Studio

Machine Learning Blog

This blog post provides a walkthrough for creating a custom Docker image for geospatial analysis, tailored for use with Amazon SageMaker Studio. It covers extending the SageMaker Distribution by installing specialized geospatial libraries like GDAL, GeoPandas, Leafmap, and Rioxarray.

Specifically, the article covers:

  • Solution overview for building and deploying a custom container image
  • Prerequisites for setting up the required permissions and tools
  • Steps to extend SageMaker Distribution with a Dockerfile
  • Building the custom image and pushing it to Amazon ECR
  • Attaching the custom image to a SageMaker Studio domain
  • Using the custom image for interactive development in Jupyter notebooks
  • Running large-scale geospatial processing jobs with the custom image
  • Cleaning up resources after use
Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jul 8
2024
Generate unique images by fine-tuning Stable Diffusion XL with Amazon SageMaker
Jun 3
2024
Use Amazon SageMaker to perform data analytics in AWS GovCloud (US) Regions
Jul 20
2024
Generate images using Amazon Bedrock with stability diffusion model in .NET
Jun 28
2024
Amazon SageMaker now supports SageMaker Studio Personalization

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.