Skip to content

M
models

PaddlePaddle / models
1 年多 前同步成功

通知 222
Star 6828
Fork 2962
M
models
未验证 提交 0aaa92db 编写于 作者: P peterzhang2029 提交者： GitHub
浏览文件
操作

Merge pull request #554 from peterzhang2029/dssm_doc_refine 

Refine the readme.md of DSSM.
上级 fd1f7af5 dc887dfe
隐藏空白更改
内联 并排
Showing with 32 addition and 32 deletion
dssm/README.cn.md
浏览文件 @ 0aaa92db
...@@ -216,49 +216,49 @@ Pairwise Rank复用上面的DNN结构，同一个source对两个target求相似 ...@@ -216,49 +216,49 @@ Pairwise Rank复用上面的DNN结构，同一个source对两个target求相似
### 回归的数据格式 ### 回归的数据格式
``` ```
# 3 fields each line: # 3 fields each line:
# - source's word ids # - source word list
# - target's word ids # - target word list
# - target # - target
<ids> \t <ids> \t <float> <word list> \t <word list> \t <float>
``` ```
比如： 比如：
``` ```
3 6 10 \t 6 8 33 \t 0.7 苹果 六 袋 苹果 6s 0.1
6 0 \t 6 9 330 \t 0.03 新手 汽车 驾驶 驾校 培训 0.9
``` ```
### 分类的数据格式 ### 分类的数据格式
``` ```
# 3 fields each line: # 3 fields each line:
# - source's word ids # - source word list
# - target's word ids # - target word list
# - target # - target
<ids> \t <ids> \t <label> <word list> \t <word list> \t <label>
``` ```
比如： 比如：
``` ```
3 6 10 \t 6 8 33 \t 0 苹果 六 袋 苹果 6s 0
6 10 \t 8 3 1 \t 1 新手 汽车 驾驶 驾校 培训 1
``` ```
### 排序的数据格式 ### 排序的数据格式
``` ```
# 4 fields each line: # 4 fields each line:
# - source's word ids # - source word list
# - target1's word ids # - target1 word list
# - target2's word ids # - target2 word list
# - label # - label
<ids> \t <ids> \t <ids> \t <label> <word list> \t <word list> \t <word list> \t <label>
``` ```
比如： 比如：
``` ```
7 2 4 \t 2 10 12 \t 9 2 7 10 23 \t 0 苹果 六 袋 苹果 6s 新手 汽车 驾驶 1
7 2 4 \t 10 12 \t 9 2 21 23 \t 1 新手 汽车 驾驶 驾校 培训 苹果 6s 1
``` ```
## 执行训练 ## 执行训练
......
dssm/README.md
浏览文件 @ 0aaa92db
...@@ -190,52 +190,52 @@ Below is a simple example for the data in `./data` ...@@ -190,52 +190,52 @@ Below is a simple example for the data in `./data`
### Regression data format ### Regression data format
``` ```
# 3 fields each line: # 3 fields each line:
# - source's word ids # - source word list
# - target's word ids # - target word list
# - target # - target
<ids> \t <ids> \t <float> <word list> \t <word list> \t <float>
``` ```
The example of this format is as follows. The example of this format is as follows.
``` ```
3 6 10 \t 6 8 33 \t 0.7 Six bags of apples Apple 6s 0.1
6 0 \t 6 9 330 \t 0.03 The new driver The driving school 0.9
``` ```
### Classification data format ### Classification data format
``` ```
# 3 fields each line: # 3 fields each line:
# - source's word ids # - source word list
# - target's word ids # - target word list
# - target # - target
<ids> \t <ids> \t <label> <word list> \t <word list> \t <label>
``` ```
The example of this format is as follows. The example of this format is as follows.
``` ```
3 6 10 \t 6 8 33 \t 0 Six bags of apples Apple 6s 0
6 10 \t 8 3 1 \t 1 The new driver The driving school 1
``` ```
### Ranking data format ### Ranking data format
``` ```
# 4 fields each line: # 4 fields each line:
# - source's word ids # - source word list
# - target1's word ids # - target1 word list
# - target2's word ids # - target2 word list
# - label # - label
<ids> \t <ids> \t <ids> \t <label> <word list> \t <word list> \t <word list> \t <label>
``` ```
The example of this format is as follows. The example of this format is as follows.
``` ```
7 2 4 \t 2 10 12 \t 9 2 7 10 23 \t 0 Six bags of apples Apple 6s The new driver 1
7 2 4 \t 10 12 \t 9 2 21 23 \t 1 The new driver The driving school Apple 6s 1
``` ```
## Training ## Training
......
Markdown is supported
0% 或 .
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 或