[bug] amazonei_tensorflow_model_server does not report any errors

[mostafafarzaneh]

I am using 763104351884.dkr.ecr.us-west-2.amazonaws.com/tensorflow-inference-eia:2.3.0-cpu-py37-ubuntu18.04 docker image which run amazonei_tensorflow_model_server and serves models. When I run the server with https://s3-us-west-2.amazonaws.com/aws-tf-serving-ei-example/ssd_resnet.zip model, I can see the Elastic Inference Cloud Watch metrics changes. But when I run the server with my own TensorFlow model, despite that the server response properly, but the Elastic Inference Cloud Watch metrics do not change and it seems that my model does not run on Elastic Inference. I do not know what is the problem because amazonei_tensorflow_model_server does not report any errors.