The checkpoint models might be corrupted.

[xleslie]

Hi, when I used your pre-training model to test, I encountered a problem
"RuntimeError: unexpected of. The file might be corrupted."

Traceback (most recent call last):
File "test.py", line 20, in
netG.load_state_dict(torch.load('./checkpoint/netG_epoch_'+fold+'.weight'))
File "/home/xuyidan/.conda/envs/cagan/lib/python2.7/site-packages/torch/serialization.py", line 358, in load
return _load(f, map_location, pickle_module)
File "/home/xuyidan/.conda/envs/cagan/lib/python2.7/site-packages/torch/serialization.py", line 549, in _load
deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF. The file might be corrupted.

[aryachiranjeev]

@xleslie did you get the correct weights file. I am also facing same error "Corrupt file".
@fei-hdu