Unpickling error

[manishamukherjee]

Get this error on running the testing part (tried it on two separate systems to get the same error):

Start...

• vocabulary size. source = 50004; target = 31280
• number of XENT training sentences. 1000
• number of PG training sentences. 1000
• maximum batch size. 64 Building model... ('use_critic: ', False) Loading from checkpoint at /media/BACKUP/ghproj_d/code_summarization/github-python/result/model_rf_hybrid_1_29_reinforce.pt Traceback (most recent call last): File "a2c-train.py", line 349, in main() File "a2c-train.py", line 254, in main checkpoint = torch.load(opt.load_from, map_location=lambda storage, loc: storage) File "/usr/local/lib/python2.7/dist-packages/torch/serialization.py", line 231, in load return _load(f, map_location, pickle_module) File "/usr/local/lib/python2.7/dist-packages/torch/serialization.py", line 369, in _load magic_number = pickle_module.load(f) cPickle.UnpicklingError: could not find MARK

Any help would be appreciated.