2

I need to reproduce results with AutoKeras for the same input and configurations: I tried the following at the beginning of my notebook but still didn't got the same results.

I am using Tensorflow 2.0.4 and AutoKeras 1.0.12

seed_value= 0

import os
os.environ['PYTHONHASHSEED']=str(seed_value)
os.environ['TF_CUDNN_DETERMINISTIC'] = str(seed_value)


import tensorflow as tf
tf.random.set_seed(seed_value)

from keras import backend as K
import autokeras as ak


import random
random.seed(seed_value)


import numpy as np
np.random.seed(seed_value)

Note: I want to reproduce results at different times; i.e. to get the same result after closing the notebook, and run the code again .. not during the same session.

userInThisWorld
  • 1,361
  • 4
  • 18
  • 35

1 Answers1

2

I guess, you need to seed the generators before each call you want to be reproducable. The best option is to make such a decorator (or a context manager):

import contextlib

@contextlib.contextmanager
def reproducable(seed_value=0):
    import os
    os.environ['PYTHONHASHSEED']=str(seed_value)
    os.environ['TF_CUDNN_DETERMINISTIC'] = str(seed_value)

    import tensorflow as tf
    tf.random.set_seed(seed_value)

    from keras import backend as K
    import autokeras as ak

    import random
    random.seed(seed_value)

    import numpy as np
    np.random.seed(seed_value)

    yield 


@reproducable()
def main():
    # ...put your code here...

UPD

Note: I want to reproduce results at different times; i.e. to get the same result after closing the notebook, and run the code again .. not during the same session.

and?

enter image description here

madbird
  • 1,326
  • 7
  • 11
  • 1
    @madbrd thanks for the answer, but I want to reproduce results at different times; i.e. to get the same result after closing the notebook, and run the code again .. not during the same session. – userInThisWorld Feb 08 '21 at 08:35
  • @userInThisWorld, and how this differ? (unless `random` is not the only culprit) – madbird Feb 08 '21 at 10:08