Seems a bug in pytorch1.0.1

I run the code Shift-Net(branch random_multi_shift), python train.py can run the code. It goes well when using pytorch 0.4.1, yet does not work using pytorch 1.0.1.
I am not sure whether it is a bug.

/opt/conda/conda-bld/pytorch_1549616138213/work/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference<float>, thrust::device_reference<float>, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [159,0,0] Assertion `input >= 0. && input <= 1.` failed.
Traceback (most recent call last):
  File "train.py", line 40, in <module>
    model.optimize_parameters()
  File "/home/yan/local_run/Shift-Net_pytorch/models/shift_net/shiftnet_model.py", line 312, in optimize_parameters
    self.backward_D()
  File "/home/yan/local_run/Shift-Net_pytorch/models/shift_net/shiftnet_model.py", line 229, in backward_D
    self.loss_D_fake = self.criterionGAN(self.pred_fake, False)
  File "/home/yan/local_run/Shift-Net_pytorch/models/modules/losses.py", line 42, in __call__
    return self.loss(input, target_tensor)
  File "/home/yan/anaconda2/envs/torch1.0_py2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/yan/anaconda2/envs/torch1.0_py2/lib/python2.7/site-packages/torch/nn/modules/loss.py", line 504, in forward
    return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
  File "/home/yan/anaconda2/envs/torch1.0_py2/lib/python2.7/site-packages/torch/nn/functional.py", line 2027, in binary_cross_entropy
    input, target, weight, reduction_enum)
RuntimeError: reduce failed to synchronize: device-side assert triggered