Error about output = module(*(input + target), **kwargs)

When I use DataParallelModel and DataParallelCriterion, Wrong Occur, like
`
Traceback (most recent call last):
File "train_SyncBN.py", line 151, in
loss = criterion(outputs, labels)
File "/home/phd-1/.conda/envs/pytorch-0.41/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(input, **kwargs)
File "/home/phd-1/.conda/envs/pytorch-0.41/lib/python3.6/site-packages/encoding/parallel.py", line 134, in forward
outputs = _criterion_parallel_apply(replicas, inputs, targets, kwargs)
File "/home/phd-1/.conda/envs/pytorch-0.41/lib/python3.6/site-packages/encoding/parallel.py", line 188, in _criterion_parallel_apply
raise output
File "/home/phd-1/.conda/envs/pytorch-0.41/lib/python3.6/site-packages/encoding/parallel.py", line 163, in _worker
output = module((input + target), **kwargs)
TypeError: add() received an invalid combination of arguments - got (tuple), but expected one of:

• (Tensor other, Number alpha)
• (Number other, Number alpha)
  `
  my net output just a tensor x, not tuple, how to slove it ?

Reproduce the failure from train_SyncBN.py line 151, then inspect encoding/parallel.py around lines 134, 163, and 188 to trace how outputs and targets are passed to the criterion. Confirm the expected input shape for DataParallelCriterion and document or validate the behavior for a tensor output.