After you deploy a model into production using Amazon SageMakerhosting services, your client applications use this API to getinferences from the model hosted at the specified endpoint.Show details from next link. https://docs.aws.amazon.com/ja_jp/cli/latest/reference/sagemaker-runtime/invoke-endpoint.html
aws sagemaker-runtime invoke-endpoint -endpoint-url VPC_Endpoint_ID.runtime.sagemaker.Region.vpce.amazonaws.com \ |
| Step 4: Invoke the Endpoint to Get Inferences - Amazon SageMaker : http://docs.aws.amazon.com/sagemaker/latest/dg/interface-vpc-endpoint.html |
| aws sagemaker-runtime invoke-endpoint --endpoint-name DEMO-imageclassification-epc--2018-06-23-02-03-51 --body fileb://tub.jpg --content-type "application/x-image" output.json |
| An error occurred (ValidationError) when calling the InvokeEndpoint 揃 Issue #293 揃 awslabs/amazon-sagemaker-examples 揃 GitHub : http://github.com/awslabs/amazon-sagemaker-examples/issues/293 |
| aws sagemaker-runtime invoke-endpoint \\\n--endpoint-name |
| How to Make Predictions Against a SageMaker Endpoint Using TensorFlow Serving : http://medium.com/ml-bytes/how-to-make-predictions-against-a-sagemaker-endpoint-using-tensorflow-serving-8b423b9b316a |
| aws sagemaker-runtime invoke-endpoint --endpoint-name myendpoint --body |
| amazon web services - Aws Sagemaker invoke-endpoint call and csv - Stack Overflow : http://stackoverflow.com/a/51201634 |