Coet
49ad966c5f
Merge pull request #60 from KuNyaa/master
...
add tensorboardX for loss visualization
2018-09-06 09:56:14 +08:00
Coet
ee2f98fce1
Merge pull request #62 from fastnlp/text_classify_interface
...
Text Classification Interface
2018-09-06 09:54:03 +08:00
FengZiYjun
5309c98846
Text classification interface is ready.
...
- fix issue #58 , use path.join instead of +
- modify description and version in setup.py
- docstring in core/ follows RestructureText format
2018-09-05 10:00:57 +08:00
KuNya
68b63fb071
add graph summary in _train_step
2018-09-04 20:47:43 +08:00
Coet
63c687d906
Merge pull request #54 from fastnlp/pos_tag_service
...
CWS+POS tag interface
2018-09-04 11:51:33 +08:00
Zhen Ke
a665ddf909
Merge pull request #56 from keezen/master
...
Rewrite classification model and add initialization for conv_maxpool module
2018-09-04 11:27:02 +08:00
Coet
a13b8e5c82
Merge branch 'master' into pos_tag_service
2018-09-04 09:25:46 +08:00
KuNya
baf17892a7
add tensorboardX for loss visualization
2018-09-03 19:37:44 +08:00
Xipeng Qiu
4f371446c2
Merge pull request #59 from lyhuang18/test2
...
update docs
2018-09-02 21:52:07 +08:00
lyhuang
34c78cb9de
update docs
...
move example to docs
2018-09-02 20:08:17 +08:00
lyhuang
292853c84a
Merge branch 'master' into test2
2018-09-02 17:50:16 +08:00
lyhuang18
c80ae39fb3
Merge pull request #1 from fastnlp/master
...
update
2018-09-02 17:48:56 +08:00
Xipeng Qiu
961a321712
Merge pull request #55 from fastnlp/add-more-badges
...
add more badges in README
2018-09-02 16:45:31 +08:00
Ke Zhen
de89674436
Merge remote-tracking branch 'upstream/master'
2018-09-02 16:42:00 +08:00
Ke Zhen
d910ae3c77
Rewrite classification model, add intialization for conv_maxpool
2018-09-02 16:39:36 +08:00
Coet
e82ec43b37
Update README.md
2018-09-02 15:23:13 +08:00
FengZiYjun
31eac4a795
fix bug in preprocessor: reported in issue 47
2018-09-02 14:33:23 +08:00
FengZiYjun
6f59384d6c
pass CI
2018-09-02 14:18:04 +08:00
FengZiYjun
57911f771a
- clean up unused codes
...
- improve code comments
- BaseLoader & its subclasses does not need a data name any more
- update file tree
- add setup.py
2018-09-02 13:32:57 +08:00
FengZiYjun
32a036e8e6
[fix] drop "data" in Tester.make_batch; correct spelling of "show_metrics"
...
[add] PeopleDailyCorpusLoader, to parse PeopleDaily Corpus
[update] add CWS + POS_tag interface at FastNLP, see example in test_fastNLP.py
[update] modify README.md and readme_example.py to the latest version.
2018-09-01 21:33:28 +08:00
Coet
3a9b5d17e3
Merge pull request #52 from fastnlp/cws_service
...
Chinese word segmentation interface
2018-09-01 17:54:16 +08:00
FengZiYjun
0430067faf
update
2018-08-31 11:51:56 +08:00
FengZiYjun
501ffb26c5
optimize CWS example
...
- see test_fastNLP.py
- update interpret_word_seg_results in fastnlp.py
- delete useless data to increase git clone speed
2018-08-31 11:23:40 +08:00
FengZiYjun
ab55f25e20
Updates to Trainer/Tester/fastnlp
...
1. Tester has a parameter "print_every_step" to control printing. print_every_step == 0 means NO print.
2. Tester's evaluate return (list of) floats, rather than torch.cuda.tensor
3. Trainer also has a parameter "print_every_step". The same usage.
4. In training, validation steps are not shown.
5. Updates to code comments.
6. fastnlp.py is ready for CWS. test_fastNLP.py works.
2018-08-31 10:46:56 +08:00
Yige XU
9dc32f68a7
Merge pull request #50 from h00Jiang/master
...
fix a bug (when restore the pickle_file , cannot restore dev.pkl)
2018-08-30 14:56:59 +08:00
FengZiYjun
9d6b0daa99
Prepare for CWS service:
...
- specify the name of the config file and the name of corresponding section where model init params store.
- fastnlp.py needs load_pickle to get dictionary size and the number of labels
- other minor adjustments
2018-08-30 11:45:47 +08:00
FengZiYjun
625b72691b
edit fastnlp run method, get ready for CWS
...
- change inputs of fastnlp from string to list of strings
- adopt flexible outputs according to diff tasks
2018-08-29 23:26:32 +08:00
Coet
b76d3d0827
Merge pull request #51 from xuyige/test_code
...
Test code
2018-08-29 17:05:18 +08:00
Coet
50b5345539
check if data_dev.pkl exists
...
In line 100, add a if statement to check whether there exists a file named "data_dev.pkl" in the pickle path. If not, the file won't be loaded.
2018-08-29 17:03:26 +08:00
xuyige
beee885689
add test code for testing variational rnn
2018-08-29 15:28:22 +08:00
xuyige
2bc54c6d17
add test code for testing masked rnn
2018-08-29 15:27:59 +08:00
xuyige
b362a810e0
fix a bug in testing code
2018-08-29 15:26:50 +08:00
xuyige
c77621292b
fix a bug in char_language_model.py
2018-08-29 15:26:18 +08:00
xuyige
650838d118
fix a bug in step() of MaskedRNNBase
2018-08-29 15:10:43 +08:00
h00Jiang
18586c9c6d
fix a bug (when init_emb is not None , get an error)
2018-08-29 14:08:29 +08:00
h00Jiang
5a70d65591
fix a bug (when restore the pickle_file , cannot restore dev.pkl)
2018-08-29 14:02:24 +08:00
lyhuang
3fde835638
docs/requirements.txt
2018-08-29 00:18:15 +08:00
lyhuang
96cf033689
docs/
2018-08-29 00:11:33 +08:00
lyhuang
41c7524d4f
docs/requirements.txt
2018-08-28 21:23:28 +08:00
xuyige
8899b44add
fix a bug
2018-08-28 17:19:10 +08:00
xuyige
7a54a20908
add codes testing utils
2018-08-28 17:18:36 +08:00
xuyige
246908bf45
find a bug that bilinear must have bias
2018-08-28 17:18:09 +08:00
xuyige
08e924b54f
add test code for testing preprocess.py
2018-08-28 17:17:07 +08:00
xuyige
812160493e
add test code for testing trainer
2018-08-28 17:16:19 +08:00
xuyige
e58295d657
add test code for testing other modules
2018-08-28 13:40:12 +08:00
xuyige
ff37b03670
add test code for testing loader
2018-08-28 13:39:46 +08:00
xuyige
d6d92010e0
add test code for testing action.py
2018-08-28 13:39:28 +08:00
Coet
96391d6ab3
Merge pull request #46 from fastnlp/modify-readme-example
...
modify readme example
2018-08-24 19:15:16 +08:00
Xipeng Qiu
47ddb24d1d
modify readme example
2018-08-24 11:52:13 +08:00
Coet
9b7ad27616
Merge pull request #44 from choosewhatulike/master
...
add MLP decoder
2018-08-24 09:48:39 +08:00
