问RuntimeError:应为后端CUDA的对象，但获得了参数#3的后端CPU 'index‘

EN

    LSTM(
      (embed): Embedding(139948, 12, padding_idx=0)
      (lstm): LSTM(12, 12, num_layers=2, batch_first=True, bidirectional=True)
      (lin): Linear(in_features=240, out_features=6, bias=True)
    )
    Train epoch : 1,  loss : 771.319284286499,  accuracy :0.590
    =================================================================================================
    Traceback (most recent call last):enter code here
      File "C:/Users/Administrator/PycharmProjects/untitled/example.py", line 297, in <module>
        scores = model(x_test, x_test_seq_length)
      File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 493, in __call__
        result = self.forward(*input, **kwargs)
      File "C:/Users/Administrator/PycharmProjects/untitled/example.py", line 141, in forward
        x = self.embed(x)  # sequence_length(max_len), batch_size, embed_size
      File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 493, in __call__
        result = self.forward(*input, **kwargs)
      File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\sparse.py", line 117, in forward
        self.norm_type, self.scale_grad_by_freq, self.sparse)
      File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\functional.py", line 1506, in embedding
        return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
    RuntimeError: Expected object of backend CUDA but got backend CPU for argument #3 'index'