Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
DA-southampton committed May 19, 2021
1 parent 80c86fc commit 2a20a76
Show file tree
Hide file tree
Showing 3 changed files with 5 additions and 3 deletions.
Binary file modified .DS_Store
Binary file not shown.
4 changes: 3 additions & 1 deletion Pytorch/README.md
Original file line number Diff line number Diff line change
@@ -1,12 +1,14 @@
主要是积累关于Pytorch实战的一些经验和坑

Pytorch如何加载大数据:https://github.com/pytorch/text/issues/130



| Pytorch技巧 | |
| ----------- | ---- |
|[pytorch对text数据的预处理-综述](https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%AF%B9text%E6%95%B0%E6%8D%AE%E7%9A%84%E9%A2%84%E5%A4%84%E7%90%86-%E7%BB%BC%E8%BF%B0.md) | 已经上传 |
|[pytorch处理文本数据代码版本1-处理文本相似度数据](https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC1-%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%95%B0%E6%8D%AE.md) | 已经上传 |
| [pytorch处理文本数据代码版本2-处理文本相似度数据](https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC2-%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%95%B0%E6%8D%AE.md) | 已经上传你 |
| [pytorch处理文本数据代码版本2-处理文本相似度数据](https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/pytorch%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC2-%E5%A4%84%E7%90%86%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%95%B0%E6%8D%AE.md) | 已经上传 |
|[Pytorch中mask attention是如何实现的代码版本1-阅读文本相似度模型的小总结](https://github.com/DA-southampton/NLP_ability/blob/master/Pytorch/Pytorch%E4%B8%ADmask%E6%98%AF%E5%A6%82%E4%BD%95%E5%AE%9E%E7%8E%B0%E7%9A%84%E4%BB%A3%E7%A0%81%E7%89%88%E6%9C%AC1-%E9%98%85%E8%AF%BB%E6%96%87%E6%9C%AC%E7%9B%B8%E4%BC%BC%E5%BA%A6%E6%A8%A1%E5%9E%8B.md)||


Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -12,15 +12,15 @@

什么是对比损失函数呢?公式如下:

![image-20210114154303377](/Users/zida/Library/Application%20Support/typora-user-images/image-20210114154303377.png)
![image-20210114154303377](https://picsfordablog.oss-cn-beijing.aliyuncs.com/2021-05-19-065215.png)

这个公式需要注意两个细节点,一个是d,代表的是距离度量,一个是margin,代表的是一个超参;

那么我感兴趣的是孪生网路可以不可以使用其他的损失函数?如果可以,又是哪些呢?

首先当然是可以,只要能够优化都可以;

![image-20210114154713043](/Users/zida/Library/Application%20Support/typora-user-images/image-20210114154713043.png)
![image-20210114154713043](https://picsfordablog.oss-cn-beijing.aliyuncs.com/2021-05-19-065221.png)

参考自这里:

Expand Down

0 comments on commit 2a20a76

Please sign in to comment.