test/fastNLP
1
0
Fork 0
mirror of https://gitee.com/fastnlp/fastNLP.git synced 2024-12-04 13:17:51 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
1,174 Commits 3 Branches 13 Tags 25 MiB
216efb446f
Commit Graph

1174 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
wyg
216efb446f [verify] add data source in readme 2019-08-08 14:56:03 +08:00
SrWYG
c1f9d6f330
Merge pull request #8 from fastnlp/dev0.5.0 
Dev0.5.0更新fork
 2019-08-08 14:40:04 +08:00
xuyige
e7d027cdb4 add tqdm bars in tester and fix some import statements 2019-08-07 03:19:32 +08:00
yh_cc
e166c119f5 bert_embedding增加一个auto_truncate的参数，在word pieces长度超过512的情况自动使用0去padding 2019-08-06 02:01:02 +08:00
yh
c3d5128ab5 1. merge conflict 2019-07-30 00:00:58 +08:00
yh
af55db2019 1.修改callback prepare_callbacks, 2.让Dist_Trainer支持find_unused_parameters, 但仅在1.1以上版本有效 2019-07-29 23:56:53 +08:00
yh
71c9e0c30e 从远程下载权重 2019-07-29 23:54:57 +08:00
yh
db8c6a0b8a 解决读取bert权重潜在的bug问题 2019-07-26 19:44:20 +08:00
yunfan
cacf40366c [fix] distributed trainer 2019-07-26 16:26:43 +08:00
yh
d401bd2208 sst loader中增加一列raw_words 2019-07-25 16:56:54 +08:00
yh
cb3cb8bc5c 修复BertEmbedding的weight 2019-07-25 16:51:59 +08:00
yh
a8111087a3 删除getattr的default keyword 2019-07-25 16:36:28 +08:00
yh
210af73c6e 修复callback连续两次加入的bug 2019-07-25 16:01:17 +08:00
yunfan
329a18976f [update] distributed trainer, add evaluation part 2019-07-20 17:12:15 +08:00
yunfan
606d63a5a4 [update] distributed trainer 2019-07-20 16:24:12 +08:00
yunfan
861f5387a4 [add] very first version of distributed trainer 2019-07-19 22:40:26 +08:00
yh
4718804e22 1. 修改内部函数位置; 2.修改BertWordPieceEncoder的部分功能 2019-07-19 17:33:41 +08:00
xuyige
c2d687528e fix bugs and add test codes for: 1. models.snli; 2. core.metrics.extractive_qa; 3. io.data_loader.mnli 2019-07-19 02:05:33 +08:00
yh
22a8702d22 1. Trainer支持使用DistributedDataParallel训练; 但是还没有经过广泛测试，谨慎使用; 2. 修复import os bug; 3.FitlogCallback支持不传入任何DataSet; 4. NullOptimizer的construct_from_optimer返回self; 5. 修复Bert中pooled_cls的bug;“ 2019-07-18 23:43:10 +08:00
yh
c19499e60a 1. 修复DataSet.delete_instance的bug; 2. FieldArray中支持只使用第一个instance推断dimension和type，节省时间 2019-07-18 22:53:30 +08:00
yh
3c2e419059 增加pooled_cls选项，可以是Bert在做分类时可以使用预训练的权重 2019-07-17 20:06:40 +08:00
ChenXin
d9e9f9ca7c delete a todo item 2019-07-12 15:24:18 +08:00
xuyige
ec824376c6 fix embedding tutorials 2019-07-12 14:51:11 +08:00
Yige XU
25421d104d
Merge branch 'master' into dev0.5.0 2019-07-12 14:30:59 +08:00
ChenXin
1fed3650d5 check了 embeddings 的文档 2019-07-12 14:18:04 +08:00
xuyige
98ebc3c0b1 在README.md添加版本说明 2019-07-12 14:12:13 +08:00
yh
f3e19ddd9a erge conflict in bert 2019-07-12 13:29:54 +08:00
yh
39f3accace 增加Embedding的文档 2019-07-12 13:27:29 +08:00
ChenXin
af4fd46273 修改了io 模块内子模块的顺序 2019-07-12 13:16:42 +08:00
ChenXin
90c6454aed 修改了文档首页 2019-07-12 13:13:54 +08:00
yunfan
9f681dcd55 fix tutorial typo 2019-07-12 12:42:31 +08:00
ChenXin
fc0f86aa9e io、data_loader的文档结构和别名 2019-07-12 12:05:04 +08:00
ChenXin
ce72936c0f :maxdepth: 1 2019-07-12 11:38:51 +08:00
ChenXin
dcc6d5d15d models的文档结构和别名 2019-07-12 11:27:35 +08:00
ChenXin
f3a9fc5b79 encoder里面的结构和文档 2019-07-12 11:16:21 +08:00
ChenXin
a09cf518d7 modules入口的介绍和dropout的文档 2019-07-12 11:05:57 +08:00
ChenXin
d6ae241bbb decoder部分的别名 2019-07-12 10:49:18 +08:00
ChenXin
c99f02aa3b API文档入口的介绍 2019-07-12 10:46:29 +08:00
ChenXin
391793a961 最新的docs结构 2019-07-12 10:36:46 +08:00
yh
0a33a32081 Merge branch 'dev0.5.0' of https://github.com/fastnlp/fastNLP into dev0.5.0 
# Conflicts:
#	fastNLP/modules/encoder/embedding.py
#	reproduction/seqence_labelling/ner/train_ontonote.py
#	reproduction/text_classification/model/lstm.py
 2019-07-12 09:56:35 +08:00
yh
807a8f1fb3 1. BucketSampler不需要自己传入batch_size了，由Trainer自动设置 
2. sequence labeling中增加BiLSTMCRF
3. embedding中修复bug
4. 将之前版本的reproduction移动到legacy文件夹
5. sequence labeling中增加中文NER
6. text classification中loader增强，修改lstm模型，增加train_bert.py
 2019-07-12 09:27:11 +08:00
lyhuang18
026925097d
Merge pull request #191 from lyhuang18/lyhuang-reproduction 
修改代码以适配新fastNLP.embeddings模块
 2019-07-12 06:50:10 +08:00
lyhuang18
ffbba0f895 修改代码以适配新embeddings模块 2019-07-12 06:47:04 +08:00
lyhuang18
0d487707d9
Merge pull request #17 from fastnlp/dev0.5.0 
Dev0.5.0
 2019-07-12 06:00:17 +08:00
xuyige
defcaae4bd 将test_embed_loader的almost equal范围稍稍调大一些，以防止偶然的测试不通过 2019-07-12 04:39:17 +08:00
xuyige
bedb792b3c 将test_embed_loader的almost equal范围稍稍调大一些，以防止偶然的测试不通过 2019-07-12 04:33:32 +08:00
lyhuang18
4df322eb2d
Merge pull request #14 from fastnlp/dev0.5.0 
Dev0.5.0
 2019-07-12 04:30:20 +08:00
xuyige
65f92855ba add testing code in stack embedding 2019-07-12 04:24:08 +08:00
xuyige
327833a77f fix bug in test code 2019-07-12 04:11:03 +08:00
xuyige
76198acc5c update README.md: add description in fastNLP.embeddings 2019-07-12 04:09:27 +08:00