unable to serve tensorflow object detection trained model

I am trying to serve a tensorflow object detection model, trained outside . I am getting below error while deploying

2020-02-05 13:26:36.548229: E tensorflow_serving/util/retrier.cc:37] Loading servable: {name: generic_model version: 1} failed: Not found: Op type not registered 'FusedBatchNormV3' in binary running on model.aws.local. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.

the apis i am using is given below
sagemaker_model = TensorFlowModel(model_data = 's3://traindatavinayak/model/model.tar.gz',
role = role,
#framework_version = '1.12',
entry_point = 'train.py')

predictor = sagemaker_model.deploy(initial_instance_count=1,
instance_type='ml.m4.xlarge')

Start with the TensorFlowModel deployment configuration and the reported TensorFlow Serving log, then compare the trained model's TensorFlow version and ops with the SageMaker framework version shown in the API snippet. Done means the external object-detection model deploys and loads without the missing FusedBatchNormV3 operation error.

Written by the indexing model from the issue text.