提交 e08367c8 编写于 作者: Y Yi Wang

Add few blank lines

上级 837242e7
...@@ -20,6 +20,7 @@ Both examples show that the elements of sequences are usually of the same size. ...@@ -20,6 +20,7 @@ Both examples show that the elements of sequences are usually of the same size.
The real challenge is that in most cases, sentences have variable lengths, and we will need an index data structure to segment the tensor into sequences. Also, sequences might consist of sub-sequences. The real challenge is that in most cases, sentences have variable lengths, and we will need an index data structure to segment the tensor into sequences. Also, sequences might consist of sub-sequences.
## A Solution: The LoD Index ## A Solution: The LoD Index
To understand our solution, it is best to look at some examples. To understand our solution, it is best to look at some examples.
...@@ -75,6 +76,7 @@ In this case, we don't lose any information by ignoring the many 1's in the inde ...@@ -75,6 +76,7 @@ In this case, we don't lose any information by ignoring the many 1's in the inde
A model parameter is just a usual Tensor, which, just like the above example, is a **0-level LoD Tensor**. A model parameter is just a usual Tensor, which, just like the above example, is a **0-level LoD Tensor**.
## The LoD Tensor ## The LoD Tensor
Let us revisit above example of the 2-level LoD Tensor Let us revisit above example of the 2-level LoD Tensor
......
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