Build-in Object Detection Algorithm and Sagemaker Neo

Hi AlexLe,

Thanks for your interest in SageMaker Object Detection and SageMaker Neo.
SageMaker Neo does not support models trained with built-in SageMaker Object Detection algorithm. Please check https://docs.aws.amazon.com/sagemaker/latest/dg/neo.html for details.

Best Regards,
AWS SageMaker Team.

Can you give me a recommendation which pre-trained models can be used with Neo? I was trying some from the Gluon MXNet Model Zoo but had no luck either ...

Edited by: AlexLe on Aug 15, 2019 11:58 AM

Hi,

I am trying the inbuilt object detection algorithm available on AWS for a computer vision problem. The training job ran successfully and I have received the model artifacts in the .tar.gz format in an S3 bucket.

To reduce the model footprint, we need to use Sagemaker Neo - a compilation job on the available model artifacts. The compilation job fails with the error - "ClientError: OperatorNotImplemented:('One or more operators are not supported in frontend MXNet:\n_contrib_MultiBoxTarget: 1\nMakeLoss: 3"

How can this be resolved? Around August 2019, Sagemaker Neo did not support models trained with built-in Sagemaker Object Detection Algorithm. Is there any change in this status today ?

Thanks

I built a Object Detection model using the build in Object Detection Algorithm of Sagemaker [1]. After training I would like to optimize the model for my AWS PANORAMA using Sagemaker Neo but the compiling job fails with the error message "ClientError: OperatorNotImplemented:('Operator _contrib_MultiBoxTarget is not supported in frontend MXNet.". Is built-in object algorithm supported by sagemaker neo or not ?