提交 8b05bc8d 编写于 作者: S Superjom

add more description for arguments

上级 4012e62c
...@@ -438,6 +438,16 @@ optional arguments: ...@@ -438,6 +438,16 @@ optional arguments:
number of batches to output model, (default: 400) number of batches to output model, (default: 400)
``` ```
重要的参数描述如下
- `train_data_path` 训练数据路径
- `test_data_path` 测试数据路局,可以不设置
- `source_dic_path` 源字典字典路径
- `target_dic_path` 目标字典路径
- `model_type` 模型的损失函数的类型,分类0,排序1,回归2
- `model_arch` 模型结构,FC 0, CNN 1, RNN 2
- `dnn_dims` 模型各层的维度设置,默认为 `256,128,64,32`,即模型有4层,各层维度如上设置
## 用训练好的模型预测 ## 用训练好的模型预测
```python ```python
usage: infer.py [-h] --model_path MODEL_PATH -i DATA_PATH -o usage: infer.py [-h] --model_path MODEL_PATH -i DATA_PATH -o
...@@ -480,6 +490,11 @@ optional arguments: ...@@ -480,6 +490,11 @@ optional arguments:
number of categories for classification task. number of categories for classification task.
``` ```
部分参数可以参考 `train.py`,重要参数解释如下
- `data_path` 需要预测的数据路径
- `prediction_output_path` 预测的输出路径
## 参考文献 ## 参考文献
1. Huang P S, He X, Gao J, et al. Learning deep structured semantic models for web search using clickthrough data[C]//Proceedings of the 22nd ACM international conference on Conference on information & knowledge management. ACM, 2013: 2333-2338. 1. Huang P S, He X, Gao J, et al. Learning deep structured semantic models for web search using clickthrough data[C]//Proceedings of the 22nd ACM international conference on Conference on information & knowledge management. ACM, 2013: 2333-2338.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册