Testing always creates same results across 600 test points

[hiyamgh]

Hello

Great work thank you very much!!

I am running the testing and I always get the same results after setting NUM_TEST_POINTS = 600

This is a sample of the results:

Restoring model weights from just_testing//cls_2.mbs_8.ubs_16.numstep4.updatelr0.001batchnorm\model999
WARNING:tensorflow:From C:\Users\96171\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\training\saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
Mean validation accuracy/loss, stddev, and confidence intervals
(array([0.875  , 0.6875 , 0.8125 , 0.78125, 0.6875 , 0.6875 , 0.71875,
       0.78125, 0.6875 , 0.78125, 0.71875]), array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]), array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]))

Process finished with exit code 0

The stddev and the confidence intervals are always 0