RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 ‘self‘ in

RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _thnn_conv2d_forward  怎么解决呢？

Traceback (most recent call last):
  File "train_heart.py", line 101, in <module>
    train()
  File "train_heart.py", line 99, in train
    trainer.train()
  File "/home/dluser/code/CL-Cardiac-segmentation-master/base/base_trainer.py", line 117, in train
    self._train_epoch(epoch)
  File "/home/dluser/code/CL-Cardiac-segmentation-master/trainer_heart.py", line 105, in _train_epoch
    curr_iter=batch_idx, target_ul=target_ul, epoch=epoch - 1, **kargs)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 705, in forward
    output = self.module(*inputs[0], **kwargs[0])
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/code/CL-Cardiac-segmentation-master/models/model.py", line 122, in forward
    enc = self.encoder(x_l)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/code/CL-Cardiac-segmentation-master/models/modeling/unet_model.py", line 34, in forward
    x1 = self.inc(x)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/code/CL-Cardiac-segmentation-master/models/modeling/unet_parts.py", line 39, in forward
    x= self.double_conv(x)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/container.py", line 119, in forward
    input = module(input)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torchstat/model_hook.py", line 50, in wrap_call
    output = self._origin_call[module.__class__](module, *input, **kwargs)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 399, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/dluser/anaconda3/envs/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 396, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _thnn_conv2d_forward