total_float_ops is 0 by tf.profiler.profile from tensorflow

System information

OS Platform: Linux Ubuntu 16.04
TensorFlow version (use command below): 1.8
Python version: 3.5
CUDA/cuDNN version: CUDA 9 / cuDNN 7
GPU model and memory: GeForce GTX 1080Ti

Exact command to reproduce:

import cv2  
import time  
import tensorflow as tf
from tensorflow.python.framework import graph_util

ModelFile = "OX_Predict_frozen.pb"

def load_pb(pb):
    with tf.gfile.GFile(pb, "rb") as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
    with tf.Graph().as_default() as graph:
        tf.import_graph_def(graph_def, name='')
        return graph

import math
M = math.pow( 10, 6 )
print(M)

def log_FLOP():
    # ***** (3) Load frozen graph *****
    g2 = load_pb(ModelFile)
    with g2.as_default():
        flops = tf.profiler.profile(g2, options = tf.profiler.ProfileOptionBuilder.float_operation())
        print('FLOP after freezing(M): ', flops.total_float_ops/ M)

def main():
    log_FLOP()

if __name__ == "__main__":
    main()

Describe the problem:
I'm trying to log the number of multiply-add operations (MAC) in my network by "tf.profiler.profile". Here is the model(.pb) the model work perfect when predict, but it always return 0 flops with "tf.profiler.profile" any suggestion ?

Source code / logs: the sample code to get .pb is following: https://github.com/ChiFang/TensorFlow_XO_example

it takes only few sec~~~~