empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType),

完整报错如下：

TypeError: empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:
 * (tuple of ints size, *, tuple of names names, torch.memory_format memory_format, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, torch.memory_format memory_format, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

参考自：https://blog.csdn.net/qq_25105061/article/details/123705011

说是不能是浮点型，所以这里定位到nn.Embedding的位置，feature_fields这个列表确实都是浮点型的，改成int类型即可

feature_fields = data_X.max().values + 1
feature_fields = feature_fields.astype(np.int)
print(feature_fields)
print(sum(feature_fields))

[     2      2      2      2      2      2      2      2      2      2
      2      2      2    869    525 117271  53414    210     13   9476
    407      3  18942   4274 102028   2989     26   6932  82353     10
   3192   1593      4  93248     15     14  21964     60  17029]
536887