Customising model in AWS sagemaker

Question

I have a python script which I wrote using tensorflow python 3.6 AWS sagemaker jupyter notebook inside AWS sagemaker instance. I have to use sagemaker debugger for my Deep Learning model. I can see many links suggesting that first dockerise the algorithm image and then use it over sagemaker. Can anyone please suggest that is there any available alternative such that Tensorflow-1 docker image is available and I can include some other packages via pip in this image and then run my model on sagemaker ? I am using keras 2.3.0 with tensorflow 1.15 .Please guide and share necessary references.

Answer 1

You don't have to dockerize your code yourself, you can use an existing SageMaker TensorFlow image, and with the SageMaker Python SDK you can let SageMaker manipulate docker images for you - no docker knowledge needed ! This documentation explains how to launch your own TF code on SageMaker Training or SageMaker Hosting. You can add a requirements.txt file to bring extra dependencies