TypeError: can‘t convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to

错误：
File “D:\Anaconda\envs\pytorch3.8\lib\site-packages\torch_tensor.py”, line 972, in array
return self.numpy().astype(dtype, copy=False)
TypeError: can’t convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
改错方法：
_tensor.py文件中

  def __array__(self, dtype=None):
    if has_torch_function_unary(self):
            return handle_torch_function(Tensor.__array__, (self,), self, dtype=dtype)
        if dtype is None:
            return self.numpy()
        else:
            return self.numpy().astype(dtype, copy=False)

改为

 def __array__(self, dtype=None):
        if has_torch_function_unary(self):
            return handle_torch_function(Tensor.__array__, (self,), self, dtype=dtype)
        if dtype is None:
            return self.cpu().numpy()
        else:
            return self.cpu().numpy().astype(dtype, copy=False)