“nll_loss_forward_reduce_cuda_kernel_2d_index“ not implemented for ‘Float‘

Posted 2022-04-09 AI浩

Traceback (most recent call last):
  File "D:\\nlp\\zhinengyunwei\\wh_lstm_pytorch.py", line 213, in <module>
    loss = loss_func(torch.squeeze(output), target)
  File "D:\\ProgramData\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\\ProgramData\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\loss.py", line 1150, in forward
    return F.cross_entropy(input, target, weight=self.weight,
  File "D:\\ProgramData\\Anaconda3\\lib\\site-packages\\torch\\nn\\functional.py", line 2846, in cross_entropy
    return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Float'

发生在loss计算的时候，
将

loss_func(torch.squeeze(output), target)

改为：

loss_func(torch.squeeze(output), target.long())