pytorch使用中的一些坑

1.LSTM报错：RuntimeError: Trying to backward through the graph a second time, but the saved intermediate results have already been freed. Specify retain_graph=True when calling backward the first time.

LSTM由于需要保存上一次的隐藏层信息，而backward之后这些信息会丢失，进而出现上述报错。解决方案可参考：https://blog.youkuaiyun.com/a845717607/article/details/104598278/

2.模型开始测试之前，需要model.eval()，防止测试过程中权重发生变化。