RuntimeError: Boolean value of Tensor with more than one value is ambiguous

这个bug怎么解决？

```python
Traceback (most recent call last):
  File "/home/sues/CMY/Kaggle-predict/House-price-predict.py", line 115, in <module>
    train_and_pred(train_features, test_features, train_label, test_data, num_epochs, learning_rate, weight_decay, batch_size)
  File "/home/sues/CMY/Kaggle-predict/House-price-predict.py", line 106, in train_and_pred
    train_loss, _ = train(net, train_features, train_label, None, None, num_epochs, lr, weight_decay, batch_size)
  File "/home/sues/CMY/Kaggle-predict/House-price-predict.py", line 59, in train
    l = loss(net(X), y)
  File "/home/sues/miniconda3/envs/reza/lib/python3.9/site-packages/torch/nn/modules/loss.py", line 517, in __init__
    super(MSELoss, self).__init__(size_average, reduce, reduction)
  File "/home/sues/miniconda3/envs/reza/lib/python3.9/site-packages/torch/nn/modules/loss.py", line 18, in __init__
    self.reduction: str = _Reduction.legacy_get_string(size_average, reduce)
  File "/home/sues/miniconda3/envs/reza/lib/python3.9/site-packages/torch/nn/_reduction.py", line 35, in legacy_get_string
    if size_average and reduce:
RuntimeError: Boolean value of Tensor with more than one value is ambiguous

```

参考一下这个链接的原因说明：
https://blog.csdn.net/weixin_43818631/article/details/122255929