in inference/inference.py [0:0]
def output_handler(data, context):
"""Post-process TensorFlow Serving output before it is returned to the client.
Args:
data (obj): the TensorFlow serving response
context (Context): an object containing request and configuration details
Returns:
(bytes, string): data to return to client, response content type
"""
if data.status_code != 200:
raise ValueError(data.content.decode('utf-8'))
response_content_type = context.accept_header
prediction = data.content
return prediction, response_content_type