What is the correct way to write the predict request?

You trained a text classification model.

You have the following SignatureDefs:

What is the correct way to write the predict request?
A . data = json.dumps({"signature_name": "serving_default’ "instances": [fab’, ‘be1, ‘cd’]]})
B . data = json dumps({"signature_name": "serving_default"! "instances": [[‘a’, ‘b’, "c", ‘d’, ‘e’, ‘f’]]})
C . data = json.dumps({"signature_name": "serving_default, "instances": [[‘a’, ‘b ‘c’1, [d ‘e T]]})
D . data = json dumps({"signature_name": f,serving_default", "instances": [[‘a’, ‘b’], [c ‘d’], [‘e T]]})

View Answer

Answer: D

Explanation:

https://stackoverflow.com/questions/37956197/what-is-the-negative-index-in-shape-arrays-used-for-tensorflow