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
1,263 Commits 3 Branches 13 Tags 25 MiB
9f3336f167
Commit Graph

248 Commits

Author SHA1 Message Date
yh
e2232ac39f 1.修复Embedding中潜在的寻找路径失败; 2.reproduction中增加分词模型; 3.修改ner模型为最新的pipe版本 2019-08-20 21:35:12 +08:00
yunfan
4e59d88724 [update] move logger to fastNLP.core, update logging format 2019-08-20 15:28:21 +08:00
yh
61a133aef5 merge 2019-08-19 23:37:57 +08:00
yh
3624f7dafd 增加conll2003Pipe 2019-08-19 23:35:47 +08:00
xuyige
ea0f2f7e00 update reproduction/matching to adapt version 0.5.0: 1) move loader codes from DataLoader to PiPe; 2) fix some bugs in matching pipe; 3) delete some expire codes. 2019-08-19 20:48:08 +08:00
yunfan
3b8bc469ba [update] logger, support straightly import logger to use 2019-08-19 14:24:12 +08:00
yh
511f41dda1 1. 增加中文NER相关的loader和pipe; 2. 对应修改sequence_labeling的代码; 3.增加部分测试代码 2019-08-19 10:52:12 +08:00
yunfan
007c047ae7 [update] logger in trainer & tester 2019-08-18 13:39:56 +08:00
yunfan
287019450e [add] logger in trainer 2019-08-17 18:16:12 +08:00
ChenXin
de17c9a7d3 rename base_loader file as data_bundle 2019-08-16 17:40:43 +08:00
yh
cf64412dad merge docs 2019-08-14 23:16:11 +08:00
yh
7a21c2a587 1. 增强BertEmbedding使其可以自动判断token_type_ids; 2.增加CrossEntropyLoss中对label dimension的报错处理 2019-08-14 23:14:59 +08:00
ChenXin
a8a21b169a fix a serial bugs on importing 2019-08-14 20:18:54 +08:00
wyg
216efb446f [verify] add data source in readme 2019-08-08 14:56:03 +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
ffbba0f895 修改代码以适配新embeddings模块 2019-07-12 06:47:04 +08:00
xuyige
570b214dfb 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 2019-07-12 04:07:47 +08:00
Yige XU
2c1a830b34
Merge pull request #190 from brxx122/master 
[new] Update Readme.md and repair bugs with the modification of fastnlp 0.4.5
 2019-07-11 22:25:01 +08:00
Danqing Wang
ec08564c1c add rouge in readme 2019-07-11 21:14:53 +08:00
Danqing Wang
897ed8a8d0 modify readme and update trainer.py 2019-07-11 21:11:49 +08:00
Yige XU
1dd8db7632
Merge pull request #188 from SrWYG/dev0.5.0 
[verify] train_char_cnn optimization
 2019-07-11 20:49:27 +08:00
yunfan
ca145d2050 fix import bug 2019-07-11 14:44:23 +08:00
wyg
efea6ceaf5 [verify] train_char_cnn optimization 2019-07-11 14:04:32 +08:00
xuyige
7d07b38e0a fix bug in matching DataLoader 2019-07-11 00:17:38 +08:00
xuyige
83f9cb193f update README.md 2019-07-11 00:03:24 +08:00
yh
5c80c6f4f5 将DataInfo修改为DataBundle 2019-07-10 20:14:00 +08:00
FFTYYY
97c7ba313d 添加了mwan模型，并稍微修改了matching dataloader 2019-07-10 16:56:58 +08:00
Yige XU
000deb2788
Merge pull request #184 from choosewhatulike/master 
[bug fix] fix test case for sstloader & update some train scripts
 2019-07-09 19:55:36 +08:00
yunfan
14778ee071 [bug fix] sst loader, star-transformer 
[update] train script
 2019-07-09 14:00:40 +08:00
xuyige
488ce6bbec Update test_dataLoader.py 2019-07-09 13:56:01 +08:00
yh_cc
9ec1570a20 sequence labeling 的dataloader 2019-07-09 11:30:36 +08:00
yh_cc
e876082567 修复Embedding中的bug 2019-07-09 11:28:35 +08:00
xuyige
a83cee0fbb fix bug in load dataset test code 2019-07-09 02:18:11 +08:00
xuyige
a39dafac6b fix bug in tests 2019-07-09 01:17:40 +08:00
xuyige
d70aa96e4c 大幅度更新：1、更新requirements；2、将modules.aggregator的内容移至modules.encoder；3、将SQuADMetric重命名为ExtractiveQAMetric；4、更新reproduction的README；5、将reproduction/text_classification的dataloader移动到fastNLP.io.data_loader并做适配性修改 2019-07-09 01:01:47 +08:00
Danqing Wang
5bb6c22b48 Delete removed files 2019-07-08 23:35:28 +08:00
Danqing Wang
c588ba7820 Merge BertSum and reorganize Summarization Task 2019-07-08 23:30:07 +08:00
Danqing Wang
9fe06df4fe
Merge pull request #5 from fastnlp/dev0.5.0 
Dev0.5.0 delete dataset_loader and pull again
 2019-07-08 23:19:04 +08:00
Danqing Wang
bb373fd78d delete my fastnlp/io/dataset_loader.py and add test file 2019-07-08 23:13:22 +08:00
SrWYG
e38777b014
Merge pull request #5 from lyhuang18/lyhuang-reproduction 
Yelp_f的结果
 2019-07-08 21:24:22 +08:00
lyhuang18
124edb59e3 Yelp_f的结果 2019-07-08 19:51:03 +08:00
wyg
8cd9ea178d [verify] sst2loader 2019-07-08 19:46:46 +08:00
lyhuang18
0476b2898d
Delete SSTLoader.py 2019-07-08 19:45:41 +08:00
wyg
ba47fb851a [verify] sst2loader 2019-07-08 19:45:39 +08:00
SrWYG
9130929145
[remove] 过期的SSTloader 2019-07-08 19:38:15 +08:00
xuyige
b445ea6955 删除过期的reproduction内容 2019-07-08 16:01:57 +08:00
Yige XU
e05ccb8c9c
Merge pull request #179 from maszhongming/dev0.5.0 
[add] BertSum model (Liu et al. 2019)
 2019-07-08 15:45:13 +08:00
Yige XU
1f4cd0c8b6
Merge pull request #178 from SrWYG/dev0.5.0 
[bugfix] IMDB/SST/YELP dataloader char_level无空格 [add]IMDB/SST use spacy tokenizer
 2019-07-08 15:44:24 +08:00
maszhongming
248eefe9eb add BertSum 2019-07-08 16:10:01 +09:00