Model diverged while predicting

[cyberfag]

Hello. After successfull training, I'm trying to predict stages using the command given (python predict.py --data_dir data/eeg_fpz_cz --model_dir output --output_dir output) using my directories of course. But it returns the following error:

Traceback (most recent call last):
  File "predict.py", line 705, in <module>
    tf.compat.v1.app.run()
  File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow_core\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\absl\app.py", line 312, in run
    _run_main(main, args)
  File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\absl\app.py", line 258, in _run_main
    sys.exit(main(argv))
  File "predict.py", line 700, in main
    n_subjects_per_fold=n_subjects_per_fold
  File "predict.py", line 651, in predict
    subject_idx=subject_idx
  File "predict.py", line 561, in custom_run_epoch
    "Model diverged with loss = NaN"
AssertionError: Model diverged with loss = NaN

It seems like your model is trying to perform some more finetuning or something but I just want to use the saved trained model, forward pass and get the predicted labels. Is it possible in this simple way?