How to implement a sagemaker ensemble model outside AWS

Question

I would like to know if it is possible to implement an ensemble model trained in Sagemaker for tabular data that targets a binary classification column.

I am very struck by the fact that I have not been able to find examples either on GitHub or in the internal AWS documents, which makes me think that it is not possible to implement these models outside of AWS.

Along with the above, I was able to download the .tar.tz file from the top performance. I was able to implement the 3 models that make up the assembly individually but not the model that groups and implements the predictions called predict.pkl.

I sincerely appreciate any kind of help, link, blog or steps to follow.

Greetings
Alejandro Holguin M

Answer

Thanks for your help, saw the code but did not find a snipet  on how to open and implement an ensemble model with out using any aws endpoint....

As you can see in the images the files downloaded from the best model are in the path but keep geting the same error regarding the version (there are any version different than 0.8.1 available) and the fit issue...

Any help more than apreciated

![Errors](/media/postImages/original/IMulbQ9n2yQS2Mc0rFohYrMw)

Answer

Hi, 
please refer this if it works for your case.
https://github.com/aws-samples/ml-model-serving-on-sagemaker-bring-your-own-ensemble/blob/main/README.md

Thanks.

How to implement a sagemaker ensemble model outside AWS

Relevanter Inhalt