Amazon SageMaker
Developer Guide

Using TensorFlow with Amazon SageMaker

You can use Amazon SageMaker to train a model using custom TensorFlow code. If you choose to deploy your code using Amazon SageMaker hosting services, you can also provide custom TensorFlow inference code. This section provides guidelines for writing custom TensorFlow code for both model training and inference, and an example that includes sample TensorFlow code and instructions for model training and deployment.

Amazon SageMaker supports using pipe mode in TensorFlow containers. For information, see

For information about TensorFlow supported versions, see The container source code can be found at the GitHub repository at