salesforce / cove

BSD 3-Clause "New" or "Revised" License
473 stars 93 forks source link

RuntimeError: torch.LongTensor constructor doesn't accept any keyword arguments #15

Closed tuvuumass closed 6 years ago

tuvuumass commented 6 years ago

Hi,

I got the following error when running test/example.py. Any ideas?

No handlers could be found for logger "torchtext.data.iterator"
Traceback (most recent call last):
  File "example.py", line 28, in <module>
    for batch_idx, batch in enumerate(train_iter):
  File "python2/lib/python2.7/site-packages/torchtext/data/iterator.py", line 157, in __iter__
    yield Batch(minibatch, self.dataset, self.device)
  File "python2/lib/python2.7/site-packages/torchtext/data/batch.py", line 27, in __init__
    setattr(self, name, field.process(batch, device=device))
  File "python2/lib/python2.7/site-packages/torchtext/data/field.py", line 188, in process
    tensor = self.numericalize(padded, device=device)
  File "python2/lib/python2.7/site-packages/torchtext/data/field.py", line 283, in numericalize
    lengths = torch.LongTensor(lengths, device=device)
**RuntimeError: torch.LongTensor constructor doesn't accept any keyword arguments**