# lstm_example(lstm的实例)
>based on keras(基于keras框架)
## 文件说明
- data_file1(数据文件1):`traindata.xlsx`
用于回归和分类问题的训练
- data_file2(数据文件2):`testdata_for_number.xlsx`
用于回归问题的预测
- code_file1(代码文件1):`number_lstm_keras.py`
predict value: for **regression** question
预测数值:**回归问题**
- code_file2(代码文件2):`label_lstm_keras.py`
predict label: for **classification** question
预测标签:**分类问题**
## 对训练过程可视化
对训练过程可视化
以**分类**问题为例
![](https://img-blog.csdnimg.cn/20190320145213663.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM4NDEyODY4,size_16,color_FFFFFF,t_70)
changes of loss during training(训练中loss的变化)
![](https://img-blog.csdnimg.cn/20190320145317911.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM4NDEyODY4,size_16,color_FFFFFF,t_70)
changes of accuracy during training(训练中acuracy的变化)
## 更多信息
more detailed contents will be in codes or [my blog](https://blog.csdn.net/qq_38412868/article/details/88688581)
更多细节详见代码或者我的博客