Tesnorflow iris BYOM error when calling predictor.predict(sample)

**Link to the notebook**

https://github.com/aws/amazon-sagemaker-examples/blob/master/advanced_functionality/tensorflow_iris_byom/tensorflow_BYOM_iris.ipynb

**Describe the bug**

when I run the cell:

sample = [6.4, 3.2, 4.5, 1.5]
predictor.predict(sample)

I get the error:

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from model with message "{ "error": "Failed to process element: 0 of 'instances' list. Error: Invalid argument: JSON Value: 6.4 Type: Number is not of expected type: string" }".

Can you please help me with this?

Open advanced_functionality/tensorflow_iris_byom/tensorflow_BYOM_iris.ipynb and run the cell containing sample and predictor.predict(sample) to reproduce the ModelError. Inspect how the sample is serialized for the endpoint and compare it with the error's expected input type; done means the notebook invocation completes successfully.

Written by the indexing model from the issue text.