Python 3 with Tensorflow on Sagemaker

Question

I understand the Sagemaker currently does not support Python 3 with Tensorflow (according to this https://github.com/aws/sagemaker-python-sdk/issues/19)

But is it possible to create your own docker container with Python 3 and Tensorflow as is explained here? https://github.com/awslabs/amazon-sagemaker-examples/blob/master/advanced_functionality/scikit_bring_your_own/scikit_bring_your_own.ipynb

Answer 1

Yes, if you create your own Docker container you can use Tensorflow with Python 3. The default Tensorflow Dockerfiles are available here and you can modify them to suit your needs.

Answer 2

New script mode containers support python 3 with framework version 1.11. AWS support gave me the impression that python 3 won't be supported on the old tf.estimator style containers.