Merge pull request #4 from fastnlp/master

update
This commit is contained in:
lyhuang18 2018-09-15 17:01:11 +08:00 committed by GitHub
commit 1ebb514aa3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
15 changed files with 12 additions and 9 deletions

View File

@ -43,6 +43,7 @@ extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.viewcode',
'sphinx.ext.autosummary',
'sphinx.ext.mathjax',
]

View File

@ -1,6 +1,12 @@
fastNLP.saver
==============
fastNLP.saver.config\_saver
----------------------------
.. automodule:: fastNLP.saver.config_saver
:members:
fastNLP.saver.logger
---------------------

Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 50 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 29 KiB

View File

@ -12,13 +12,15 @@ fastNLP是一个基于PyTorch的模块化自然语言处理系统用于快速
而每个类别包含不同的实现模块。
大多数当前的NLP模型可以构建在这些模块上这极大地简化了开发NLP模型的过程。
fastNLP的架构如下左图所示:
fastNLP的架构如图所示
.. image:: figures/procedures_and_sequence_labeling.png
.. image:: figures/procedures.PNG
在constructing model部分以序列标注(上右图)和文本分类(下图)为例进行说明:
在constructing model部分以序列标注和文本分类为例进行说明
.. image:: figures/text_classification.png
.. image:: figures/sequence_labeling.PNG
:width: 400
* encoder module将输入编码为一些抽象表示输入的是单词序列输出向量序列。
* interaction module使表示中的信息相互交互输入的是向量序列输出的也是向量序列。

View File

@ -1,6 +0,0 @@
def test_trainer():
pass
if __name__ == "__main__":
test_trainer()