def output_handler()

in code/inference.py [0:0]


def output_handler(response, context):
    """Post-process TensorFlow Serving output before it is returned to the client.

    Args:
        response (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 response.status_code != 200:
        _return_error(response.status_code, response.content.decode('utf-8'))
    response_content_type = context.accept_header
    prediction = response.content
    return prediction, response_content_type