Data loading error: No persistent_load function

[bowen-upenn]

Nice work! We would like to make a comparison between our VQA algorithm and yours in our ongoing research paper. However, after downloading the dictionary.pkl file and running the test.sh script, I encountered an error message stating "no persistent_load function was specified" when attempting to load the dataset. It seems that a persistent ID is required to load the dataset, but it is not provided. I would appreciate your help. Thank you.

loading dictionary from data/gqa/dictionary.pkl
Traceback (most recent call last):
  File "evaluate.py", line 133, in <module>
    dictionary = Dictionary.load_from_file('data/gqa/dictionary.pkl')
  File "/home/cfr/src/FFOE/dataset.py", line 86, in load_from_file
    word2idx, idx2word = pickle.load(open(path, 'rb'))
_pickle.UnpicklingError: A load persistent id instruction was encountered,
but no persistent_load function was specified.