aws-samples / sagemaker-yolov3-detection-server

Example of object detection serving with SageMaker
MIT No Attribution
8 stars 8 forks source link

ml.g4dn.xlarge limit issue #1

Open aidamanzano opened 4 years ago

aidamanzano commented 4 years ago

Hi, thank you for your awesome example! Im trying to run it and I get the following error: ResourceLimitExceeded: An error occurred (ResourceLimitExceeded) when calling the CreateEndpoint operation: The account-level service limit 'ml.g4dn.xlarge for endpoint usage' is 0 Instances, with current utilization of 0 Instances and a request delta of 1 Instances. Please contact AWS support to request an increase for this limit. I have seen this thread about the same problem https://github.com/awslabs/amazon-sagemaker-examples/issues/307#issuecomment-545707229 and when I try to request a SageMaker service limit upgrade for the "SageMaker Notebooks" option, ml.g4dn.xlarge is not on the list. I was wondering how you managed to get it to run with ml.g4dn.xlarge? Is there any alternative choice?

vdabravolski commented 4 years ago

@aidamanzano, in this notebook you're deployingYolo model on Sagemaker endpoint. So, you need to request limit increase under "Sagemaker Hosting" category.

aidamanzano commented 4 years ago

Thank you for your response, I've searched under the hosting category and I can't find ml.g4dn.xlarge as one of the options. Which one should I pick so that I don't run into the Resource Limit error?