test/fastNLP
1
0
Fork 0
mirror of https://gitee.com/fastnlp/fastNLP.git synced 2024-12-05 05:38:31 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
982 Commits 3 Branches 13 Tags 25 MiB
5dc43c6e5a
Commit Graph

982 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
xuyige
4fd49cc333 add sigmoid activate function in MLP 2019-04-11 15:00:10 +08:00
Xipeng Qiu
0f8bed739c Update README.md 2019-04-08 20:14:46 +08:00
Xipeng Qiu
c344f7deac Update README.md 2019-04-08 20:14:12 +08:00
Xipeng Qiu
667b3126a9 Update README.md 2019-04-08 20:11:47 +08:00
Yunfan Shao
90d112c07c
Merge pull request #141 from wlhgtc/master 
Another bug in Star Transformer
 2019-03-31 13:20:20 +08:00
wlhgtc
28d3f500c1
Fix bug in MSA2 (mixed k and v) 
RT, another bug
 2019-03-31 00:00:59 +08:00
xuyige
55f65c3993 add SQuAD metric 2019-03-27 17:04:19 +08:00
yh
ec90a1f0bb Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev 2019-03-23 18:13:35 +08:00
yh
e5f68bbd5b 修复CRF为负数的bug 2019-03-23 18:12:32 +08:00
FengZiYjun
6a498bbdf2 * 给vocabulary添加遍历方法 2019-03-23 15:44:23 +08:00
Yunfan Shao
56410c9e31
Merge pull request #139 from fastnlp/choosewhatulike-patch-1 
fix mask bug in star-transformer
 2019-03-23 13:31:04 +08:00
Yunfan Shao
b7008cba78
fix mask bug in star-transformer 
fix the bug described in #138 . Thank @wlhgtc for bug reporting and pr.
 2019-03-22 17:37:50 +08:00
wlhgtc
8d61cd684e
fix the "masked_fill" bug 
If you use masked_fill according to ex_mask (0 for pad), it will fill not padding position(which value in ex_mask is 1) with 0, this will lead a bad performance.
 2019-03-22 17:05:43 +08:00
FengZiYjun
f5ab7a5d45 * 将enas相关代码放到automl目录下 
* 修复fast_param_mapping的一个bug
* Trainer添加自动创建save目录
* Vocabulary的打印，显示内容
 2019-03-21 15:03:51 +08:00
FengZiYjun
ef0c6e936d Changes to Callbacks: 
* 给callback添加给定几个只读属性
* 通过manager设置这些属性
* 代码优化，减轻@transfer的负担
 2019-03-20 09:49:01 +08:00
FengZiYjun
99d6bb208b change two default init arguments of Trainer into None 2019-03-16 19:54:03 +08:00
yh
f2d7d01bb7 修复CRF中可能存在的bug 2019-03-13 10:16:39 +08:00
yh
22661ea866 修复crf中typo; 以及可能导致数值不稳定的地方 2019-03-12 19:51:28 +08:00
yh
3d7cfb3598 修复fieldarray中padder潜在bug 2019-03-12 19:00:50 +08:00
Xipeng Qiu
88d4de7c90
Merge pull request #135 from choosewhatulike/pr 
Add Star-Transformer
 2019-03-11 21:29:58 +08:00
yunfan
7c7f28f2ac - add star-transformer 2019-03-10 22:20:45 +08:00
FengZiYjun
95a72f06b9 * AutoPadder will not pad when dtype is None 
* add ignore_type in DataSet.apply
 2019-02-25 15:38:38 +08:00
FengZiYjun
3e01b14249 add ignore_type in DataSet.add_field 2019-02-25 10:34:21 +08:00
chenkaiyu1997
251088ac4b Add ENAS (Efficient Neural Architecture Search) 2019-02-25 10:34:21 +08:00
Coet
feb8f63a06 Update README.md 
fix tutorial link
 2019-02-25 10:34:21 +08:00
yunfan
5241e30bdd - update transformer docs 2019-02-20 17:27:36 +08:00
Coet
767e7971e5
Merge pull request #134 from chenkaiyu1997/master 
[new] Add ENAS (Efficient Neural Architecture Search)
 2019-02-18 09:59:14 +08:00
yh
f14d317599 Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev 2019-02-17 14:16:33 +08:00
yh
8d4f26bbd9 增加metric注释；修改trainer save过程中的bug 2019-02-17 14:16:19 +08:00
xuyige
ee677d5d55 update MLP module 2019-02-17 02:12:33 +08:00
chenkaiyu1997
efeac2c427 Add ENAS (Efficient Neural Architecture Search) 2019-02-15 17:31:56 +08:00
yh
3ea7de1673 1.修改ClipGradientCallback的bug；删除LRSchedulerCallback中的print，之后应该传入pbar进行打印;2.增加MLP注释 2019-02-14 13:18:50 +08:00
yh
5eb126dbcd BucketSampler增加一条错误检测 2019-02-09 13:47:13 +08:00
yh
853bea5812 Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev 2019-02-06 22:26:19 +08:00
yh
29eab18b78 1. CRF增加支持bmeso类型的tag 2. vocabulary中增加注释 2019-02-06 22:26:10 +08:00
Coet
13faa2b410
Merge pull request #132 from FengZiYjun/v0.3.1 
fastNLP V0.3.1
 2019-02-06 10:40:53 +08:00
FengZiYjun
b66d7b8f51 update API introduction 2019-02-04 10:07:56 +08:00
FengZiYjun
d1b5adabc4 add codecov fix 2019-02-04 09:56:08 +08:00
FengZiYjun
0c5630bd16 Ready for V0.3.1 
* 升级parser API和模型
* update docs: add new pages for tutorials
* upgrade CWS api download source
* add a new method for dataset field access
* add introduction for bert
* add more unit tests for api/processor
* remove unused test data. Add new test data.
 2019-02-04 09:44:54 +08:00
FengZiYjun
986541139a 整理所有dataset loader，建立单元测试 2019-02-02 16:46:42 +08:00
FengZiYjun
bfaf09df8c add BERT model 
* load pre-trained BERT weights from local binary
* add tests
 2019-01-29 20:35:12 +08:00
FengZiYjun
887fc9281f update callbacks: 
* rename callback methods. Use fastai's notation.
* add a new callback method - on_valid_begin
 2019-01-25 21:43:24 +08:00
xuyige
e0d6a259ae skip training while n_epoch in trainer is not greater than 0 2019-01-23 17:09:28 +08:00
xuyige
d4b4ffa28b add testing tutorial 2019-01-23 14:56:25 +08:00
yunfan
9474ab4b34 remove device in batch 2019-01-21 22:28:31 +08:00
yunfan
c02980e006 Merge branch 'yyff' into dev 2019-01-21 14:55:53 +08:00
yunfan
a37de4344d add batch device 2019-01-21 14:55:32 +08:00
yunfan
e93c6f0053 Merge branch 'dev' of https://github.com/choosewhatulike/fastNLP-private into dev 2019-01-21 14:52:24 +08:00
yh
47ec69ea96 trainer根据syf的多进程batch进行修改 2019-01-21 14:44:31 +08:00
FengZiYjun
f3cb812554 将tesorboardX处理为callback, 从trainer移除tensorboardX相关代码 2019-01-20 16:37:58 +08:00