What is the procedure to save the tensorflow model and load it for batch transform

Hi Need *Documentation*

I am looking for AWS Sagemaker example to save the tensorflow model and load it in different sagemaker environment for batchtransform

i dont want to re-train again or use estimater, just load the model and do the batch transform
@andremoeller
@aaronmarkham
@j3ffreyjohn
Thanks in advance
error faced
1)
~/anaconda3/envs/tensorflow_p36/lib/python3.6/json/encoder.py in default(self, o)
178 """
179 raise TypeError("Object of type '%s' is not JSON serializable" %
--> 180 o.__class__.__name__)
181
182 def encode(self, o):

TypeError: Object of type 'module' is not JSON serializable

2)
ClientError: An error occurred (ValidationException) when calling the CreateModel operation: 1 validation error detected: Value 'my_model/saved_model.pb' at 'primaryContainer.modelDataUrl' failed to satisfy constraint: Member must satisfy regular expression pattern: ^(https|s3)://([^/]+)/?(.*)$

No repository file, test, or entry point is named. Start from the requested SageMaker TensorFlow model save/load workflow and the two reported serialization and modelDataUrl errors; done means an example or documentation clearly explains loading the saved model for batch transform without retraining.

Written by the indexing model from the issue text.