hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain

Commit Graph

  • *
  • *
  • *
  • *
  • *
  • *
  • *
  • *
  • |\
  • | *
  • |/
  • *
  • |\
  • * \
  • |\ \
  • | | *
  • | |/
  • |/|
  • | *
  • * |
  • |\ \
  • | | *
  • | | |\
  • | | |/
  • | |/|
  • * | |
  • |\ \ \
  • | | * |
  • * | | |
  • * | | |
  • | * | |
  • |/ / /
  • | * /
  • | |/
  • * |
  • |\|
  • | *
  • | |\
  • | | *
  • | | *
  • | |/
  • * |
  • |\ \
  • | | *
  • | | *
  • | | |\
  • | |_|/
  • |/| |
  • | * |
  • |/ /
  • * |
  • * |
  • |\ \
  • | | *
  • | | |\
  • | |_|/
  • |/| |
  • * | |
  • * | |
  • * | |
  • |\ \ \
  • | | | *
  • | | | |\
  • | |_|_|/
  • |/| | |
  • | | * |
  • | |/ /
  • |/| |
  • | | *
  • * | |
  • * | |
  • | * |
  • |/ /
  • * |
  • * |
  • * |
  • |\ \
  • | |/
  • |/|
  • * |
  • |\ \
  • | * |
  • |/ /
  • * |
  • |\ \
  • | | *
  • | |/
  • | *
  • * |
  • |\ \
  • | | *
  • | |/
  • | *
  • | *
  • * |
  • |\ \
  • * \ \
  • |\ \ \
  • | | | *
  • | | | *
  • | |_|/
  • |/| |
  • * | |
  • * | |
  • | | *
  • | | |\
  • | | * \
  • | | |\ \
  • | |_|/ /
  • |/| | |
  • | | | *
  • | | |/|
  • | |_|/
  • |/| |
  • | | *
  • * | |
  • |\ \ \
  • | * \ \
  • | |\ \ \
  • | * | | |
  • | | * | |
  • | |/ / /
  • | * | |
  • | * | |
  • | * | |
  • | |\ \ \
  • | * | | |
  • | | * | |
  • | |/ / /
  • | | * /
  • | |/ /
  • |/| |
  • | | *
  • | * |
  • | | *
  • | | |\
  • | |_|/
  • |/| |
  • | | *
  • | * |
  • | | *
  • | * |
  • | |\ \
  • | |/ /
  • |/| |
  • * | |
  • |\ \ \
  • | * \ \
  • | |\ \ \
  • | * | | |
  • | | | * |
  • | |_|/ /
  • |/| | |
  • | | * |
  • | | |/
  • | | *
  • | |/
  • | *
  • |/
  • *
  • *
  • *
  • |\
  • | *
  • | |\
  • | |/
  • |/|
  • | *
  • * |
  • * |
  • |/
  • *
  • *
  • |\
  • * |
  • * |
  • |\ \
  • | * \
  • | |\ \
  • | | * |
  • 7a54a209 add codes testing utils by xuyige 2018-08-28 17:18:36 +0800
  • 246908bf find a bug that bilinear must have bias by xuyige 2018-08-28 17:18:09 +0800
  • 08e924b5 add test code for testing preprocess.py by xuyige 2018-08-28 17:17:07 +0800
  • 81216049 add test code for testing trainer by xuyige 2018-08-28 17:16:19 +0800
  • e58295d6 add test code for testing other modules by xuyige 2018-08-28 13:40:12 +0800
  • ff37b036 add test code for testing loader by xuyige 2018-08-28 13:39:46 +0800
  • d6d92010 add test code for testing action.py by xuyige 2018-08-28 13:39:28 +0800
  • 96391d6a Merge pull request #46 from fastnlp/modify-readme-example by Coet 2018-08-24 19:15:16 +0800
  • 47ddb24d modify readme example by Xipeng Qiu 2018-08-24 11:52:13 +0800
  • 9b7ad276 Merge pull request #44 from choosewhatulike/master by Coet 2018-08-24 09:48:39 +0800
  • aea53c18 Merge pull request #43 from FengZiYjun/master by Coet 2018-08-24 09:47:40 +0800
  • b54713d2 add MLP decoder by choosewhatulike 2018-08-23 23:28:45 +0800
  • 2df8eb74 Updates to core, loader: - add Loss, Optimizer - change Trainer & Tester initialization interface: two styles of definition provided - handle Optimizer construction and loss function definition in a hard manner - add argparse in task-specific scripts. (seq_labeling.py & text_classify.py) - seq_labeling.py & text_classify.py work by FengZiYjun 2018-08-22 19:10:12 +0800
  • ceac3f2e Merge pull request #38 from FengZiYjun/new_updates by Coet 2018-08-22 10:18:46 +0800
  • edb3b134 Merge pull request #2 from FengZiYjun/new_updates by Coet 2018-08-21 13:46:58 +0800
  • c871d66e Merge pull request #37 from keezen/master by Coet 2018-08-21 10:12:45 +0800
  • fac830e1 fix bugs and clean up by FengZiYjun 2018-08-20 19:25:19 +0800
  • 6fe43183 docs/requirements by lyhuang 2018-08-20 17:46:14 +0800
  • f2676d89 docs更新 by lyhuang 2018-08-20 17:22:26 +0800
  • 3ab8950d Update metrics and figure in readme. by Ke Zhen 2018-08-20 14:51:10 +0800
  • 4c8c2dfd updates to core, loader, test: - move preprocess.py from loader/ to core/ - changes to interface of preprocess: 1. add run method, to run the main processing 2. add cross validation split 3. add return value 4. merge subclasses - Trainer supports cross validation - add data as arguments in Trainer.train & Tester.test - add readme.example.py, to run the example program shown in README.md - other corresponding changes by FengZiYjun 2018-08-19 16:21:14 +0800
  • fc7dd7ec Merge pull request #33 from FengZiYjun/master by Coet 2018-08-18 16:50:45 +0800
  • 836f05a8 Merge pull request #1 from FengZiYjun/FengZiYjun-patch-1 by Coet 2018-08-17 19:34:05 +0800
  • 1d000d3e Update .travis.yml by Coet 2018-08-17 19:28:38 +0800
  • dfe09458 Update .travis.yml by Coet 2018-08-17 19:14:01 +0800
  • 2f83010d Merge pull request #32 from choosewhatulike/master by Xipeng Qiu 2018-08-17 17:20:03 +0800
  • 80baf357 add logging in Trainer & Tester - see fastNLp/saver/logger.py to know how to create and use a logger - a log file named "train_test.log" will be created in the same dir as the main file where the program starts - this file records all important events happened in Trainer & Tester's methods by FengZiYjun 2018-08-17 11:16:13 +0800
  • 9e29fb22 Merge branch 'master' of https://github.com/fastnlp/fastNLP by Ziyuan Feng 2018-08-17 09:22:49 +0800
  • fb20e873 add chinese word segmentation model by choosewhatulike 2018-08-17 00:02:01 +0800
  • ad3b59b1 Update README.md by Xipeng Qiu 2018-08-17 00:05:33 +0800
  • 9bc30f17 Merge pull request #29 from keezen/master by Coet 2018-08-16 22:10:13 +0800
  • ffe7c263 Merge branch 'master' into more_code_comments by Coet 2018-08-16 21:46:36 +0800
  • abbe423d Update README.md by Xipeng Qiu 2018-08-16 15:42:27 +0800
  • 1146ef08 fix test_metrics by choosewhatulike 2018-08-15 20:41:49 +0800
  • 964cc2dc Merge pull request #25 from fastnlp/create_issue_templates by Coet 2018-08-15 21:30:45 +0800
  • 929a595c Merge branch 'master' of https://github.com/fastNLP/fastNLP into to_merge by FengZiYjun 2018-08-15 21:07:55 +0800
  • 7f23b40a Update readme, conv and max_pool by Ke Zhen 2018-08-15 20:27:05 +0800
  • 4bbeaebe Updates to cores, action, loader: - rename Inference to Predictor - rename Trainer.prepare_input to Trainer.load_train_data, load data_train.pkl only - add __contains__ method to config Section class - more code comments - more elegant make_batch & data_iterator: Samplers return batch samples instead of batch indices by FengZiYjun 2018-08-15 20:12:20 +0800
  • 8a878072 set no_grad() for test & inference, reduce memory usage by choosewhatulike 2018-08-14 00:35:48 +0800
  • 762a559f fix bug in SeqLabelTester by Yunfan Shao 2018-08-14 00:10:44 +0800
  • 4bc123dc Update issue templates by Coet 2018-08-13 20:26:16 +0800
  • d6ef1322 fix test_metrics bug by choosewhatulike 2018-08-12 20:04:38 +0800
  • 2961afd3 remove unused file by choosewhatulike 2018-08-12 19:55:19 +0800
  • 0b2e2ff5 Merge pull request #23 from fastnlp/dev/ci_test by Coet 2018-08-12 18:30:45 +0800
  • 8a697646 Merge pull request #24 from fastnlp/add-code-of-conduct-1 by Coet 2018-08-12 18:16:00 +0800
  • 1cd73253 Create CODE_OF_CONDUCT.md by Coet 2018-08-11 21:50:54 +0800
  • 3560fb1f Merge pull request #22 from fastnlp/dev/ner by Coet 2018-08-11 21:29:24 +0800
  • 380fc251 add code coverage by FengZiYjun 2018-08-11 10:11:09 +0800
  • 77b3a0c6 fastNLP high-level interface: - fastNLP interface for sequence labeling works - fastNLP interface for text classification works by FengZiYjun 2018-08-11 09:20:09 +0800
  • 20756932 Merge pull request #21 from fastnlp/dev/classify by Coet 2018-08-10 19:45:37 +0800
  • 80a127cb merge jianghao's code by FengZiYjun 2018-08-09 21:57:53 +0800
  • 8e6db053 changes to Trainer, Tester & Inference: - rename "POSTrainer", "POSTester" to "SeqLabelTrainer", "SeqLabelTester" - Trainer & Tester have NO relation with Action - Inference owns independent "make_batch" & "data_forward" - Conversion to Tensor & go into cuda are done in "make_batch" - "make_batch" support maximum/minimum length by FengZiYjun 2018-08-08 20:40:44 +0800
  • c1d7c5d7 changes to action, trainer and tester: - rename "POSTrainer" to "SeqLabelTrainer" - add text classification test data - update make_batch in Trainer and Tester by FengZiYjun 2018-08-07 19:18:56 +0800
  • cd5c1f41 Merge pull request #19 from choosewhatulike/master by Yunfan Shao 2018-08-06 22:00:10 +0800
  • defdfaad Merge pull request #20 from choosewhatulike/fix_optim by Yunfan Shao 2018-08-06 21:58:57 +0800
  • 83f69b0e Combine make_batch for Trainer and Tester - change parameter <seq_length-->mask> in loss function defined in seq model - Trainer & Tester have Action as default parameter, shared static methods like make_batch - add seq_len in make_batch of Inference - add SeqLabelInfer, a subclass of Inference - seq_labeling.py works by FengZiYjun 2018-08-06 20:15:31 +0800
  • 2c0079f3 changes to action, trainer and tester: - Action collects shared operations: data_forward, mode, pad, make_batch - Trainer and Tester receives Action as a parameter - seq_labeling works in such setting by FengZiYjun 2018-08-03 21:29:07 +0800
  • 8f2d5f71 Create __init__.py by Coet 2018-08-01 20:47:46 +0800
  • 743a6d75 fix bugs in preprocessor by FengZiYjun 2018-08-01 10:10:55 +0800
  • c90e7b01 Merge branch 'master' of https://github.com/choosewhatulike/fastNLP by choosewhatulike 2018-08-01 00:31:29 +0800
  • c42487f9 merge master by choosewhatulike 2018-08-01 00:20:14 +0800
  • a077703c merge master by choosewhatulike 2018-08-01 00:20:14 +0800
  • 1548ee7c add recall, f1-score by choosewhatulike 2018-08-01 00:09:09 +0800
  • 2c0e9317 Merge pull request #18 from fastnlp/dev/inference by Coet 2018-07-31 19:54:46 +0800
  • 8e3e6d45 changes to batch methods - [action] add k-means bucketing, partition sequences into buckets of nearly the same length - [trainer] print train loss every 10 steps - [loader] cws pku loader split sequence longer than max_seq_len into several shorter sequences by FengZiYjun 2018-07-31 10:11:44 +0800
  • 9aad8dff update by FengZiYjun 2018-07-30 18:08:29 +0800
  • 58120998 update by FengZiYjun 2018-07-30 18:08:29 +0800
  • ef8ec3b9 add cws train script and corresponding config file by FengZiYjun 2018-07-30 09:52:46 +0800
  • 233e8328 changes to seq label model, - [model] optimize cuda support in seq labeling model - [test] add test data "pku" for chinese word seg - test_tester.py and test_cws.py is OK to run! by FengZiYjun 2018-07-28 20:18:40 +0800
  • e531908f Merge branch 'dev/inference' of https://github.com/fastnlp/fastNLP by FengZiYjun 2018-07-28 12:06:12 +0800
  • 242e576a changes to trainer, tester, preprocessor, etc. - [tester][trainer] add cuda support - [preprocess] fix label2index for padding label seq - update README.md - [test] add test_tester.py - rename "action" to "core" by FengZiYjun 2018-07-28 11:57:25 +0800
  • aaac041f Update config_loader.py by Yige XU 2018-07-27 17:06:49 +0800
  • 215a67e7 fix optimizer by choosewhatulike 2018-07-26 22:45:25 +0800
  • 2e96f730 fix optimizer by choosewhatulike 2018-07-26 22:38:54 +0800
  • c83008ad fastnlp.py works, see test/test_fastNLP.py for high-level API by FengZiYjun 2018-07-26 22:19:30 +0800
  • febe27b5 Merge remote-tracking branch 'origin/master' by choosewhatulike 2018-07-25 23:41:45 +0800
  • e5353147 add recall metrics by choosewhatulike 2018-07-25 23:37:25 +0800
  • fe17f611 changes to preprocessor, trainer, inference & seq modeling - [trainer]rename "batchify" to "make_batch" in trainer - [trainer]pack (batch_x_pad, seq_len) into batch_x in make_batch for seq labeling, because seq length before pad is needed to make masks - [trainer]unpack it in data_forward - [model]shorten model definition - [inference]build inference class. test_POS_pipeline.py is OK to infer - [preprocessor]handle pickles in a nicer manner - [FastNLP] add fastNLP.py as high-level API, not finished yet by FengZiYjun 2018-07-25 22:01:57 +0800
  • 9701ab28 add accuracy_score; fix optimizer by choosewhatulike 2018-07-25 00:14:16 +0800
  • 22d900b7 Merge remote-tracking branch 'origin/master' by FengZiYjun 2018-07-24 21:14:23 +0800
  • 7c2f260a Merge pull request #16 from fastnlp/feature/preprocess by Coet 2018-07-24 21:09:54 +0800
  • eab9473b Merge branch 'feature/preprocess' of https://github.com/fastnlp/fastNLP by FengZiYjun 2018-07-24 08:40:27 +0800
  • 647c6c63 edit dataset loaders to follow edited preprocessor; add unit tests for dataset loader by FengZiYjun 2018-07-24 08:40:14 +0800
  • 1c0eac4c optimize model definition of seq modeling; test_POS_pipeline ready to run by FengZiYjun 2018-07-23 22:26:19 +0800
  • a422a4e2 Update preprocess.py by Yige XU 2018-07-23 00:14:50 +0800
  • 7f4e57a1 Update metrics.py by Coet 2018-07-22 19:17:57 +0800
  • 92be0722 add init parameters in modules; optimizer Preprocessor; add metrics.py by FengZiYjun 2018-07-22 17:20:30 +0800
  • 875fdc46 add optimizor construct function by choosewhatulike 2018-07-22 12:21:05 +0800
  • 7557e2d0 fix bugs: 1. action batchify 2. Trainer optimizer position 3. Trainer.pad by FengZiYjun 2018-07-21 18:21:19 +0800
  • 66d38054 Merge pull request #14 from keezen/master by Coet 2018-07-21 17:15:54 +0800
  • 45690d33 merge by Ke Zhen 2018-07-21 15:25:43 +0800
  • 4a25bdba classification by Ke Zhen 2018-07-21 14:21:57 +0800
  • 843b7c0e To Do (save commit) by FengZiYjun 2018-07-20 20:21:40 +0800
  • 3d234bf5 add model selection (best dev) in Trainer: save the best model during validation; add Inference. by FengZiYjun 2018-07-17 20:16:17 +0800
  • 174ce35f delete unnecessary files by FengZiYjun 2018-07-16 21:20:51 +0800
  • 301bbdcd add accuracy in POS Tester; optimize evaluation output in Trainer; keep POS pipeline (loader + trainer + tester + saver) OK; add codes borrowed from FudanParser. by FengZiYjun 2018-07-16 21:12:46 +0800
  • 621b79ee update configLoader to load hyper-parameters from file by FengZiYjun 2018-07-16 19:53:36 +0800
  • 08b0edae Merge remote-tracking branch 'origin/master' by FengZiYjun 2018-07-16 18:56:20 +0800
  • b3388684 Merge pull request #13 from xuyige/master by Coet 2018-07-16 18:55:51 +0800
  • 91e02a50 update config loader by Yige XU 2018-07-16 18:14:51 +0800