Commit Graph

54 Commits

Author SHA1 Message Date
yh_cc
e8b6298fb1 完善SpanFPreRecMetric即测试 2022-04-10 23:56:55 +08:00
MorningForest
9c62e300a7 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-10 23:10:44 +08:00
MorningForest
0cab4dc526 修改F1RecPreMetric测试用例 2022-04-10 23:10:35 +08:00
yh_cc
817f6d6ad6 修改fastnlp_torch_all_gather函数,使得它gather后的tensor都在当前device 2022-04-10 22:28:48 +08:00
yh_cc
12d3e08568 增加BucketedBatchSampler的测试 2022-04-10 20:42:37 +08:00
yh_cc
983c587cba Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-10 14:36:52 +08:00
yh_cc
20b8ca9a92 实现了BucketedBatchSampler; 创建了reproducible_batch_sampler.py 2022-04-10 14:36:47 +08:00
YWMditto
a376eea776 重新修改了断点重训的逻辑,主要修改了 trainer.save/load 和 driver.save 和 load 函数 2022-04-10 12:56:49 +08:00
YWMditto
770b2eaf4b Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-10 11:47:01 +08:00
yh_cc
0e7961cd9f Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-10 00:08:24 +08:00
yh_cc
8e4abf2aa5 删除了driver的replace_sampler替换为set_dist_repro_dataloader; 同时修改 driver.load/driver.save 函数 2022-04-10 00:08:19 +08:00
x54-729
680421fe86 paddle分布式训练 2022-04-09 12:52:19 +00:00
YWMditto
a8597602d0 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-09 15:28:19 +08:00
YWMditto
929abc3953 加入了 test_logger.py 2022-04-09 15:28:13 +08:00
x54-729
6ef912675b 新的paddle测试数据集 2022-04-09 14:37:55 +08:00
x54-729
fd3b82c5b0 Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-08 15:28:34 +00:00
yh_cc
4781178a5a 修复测试 2022-04-08 22:36:52 +08:00
x54-729
2d68c952d3 调整paddle_backend 2022-04-08 22:34:17 +08:00
yh_cc
40c0a712dd 移动env的位置为顶级目录 2022-04-08 22:29:22 +08:00
YWMditto
e3ce87271e Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0 2022-04-08 21:48:46 +08:00
YWMditto
fe270ef619 更新 callbacks, controllers, drivers, samplers 以及 tests 中的部分内容 2022-04-08 21:48:29 +08:00
MorningForest
8cf855ab47 添加了metric测试用例 2022-04-08 21:37:12 +08:00
MorningForest
6960eb56b6 添加了dataset测试用例 2022-04-08 21:36:41 +08:00
MorningForest
9ed4df6f86 添加了dataloaders测试用例 2022-04-08 21:36:12 +08:00
MorningForest
65c621db78 添加了collators测试用例 2022-04-08 21:35:39 +08:00
x54-729
3a580edb99 提交tests/core/utils/ 2022-04-08 12:16:05 +00:00
x54-729
05ca80bb6f 提交tests/modules/ 2022-04-08 12:15:33 +00:00
x54-729
6170976b7f 提交tests/core/drivers/torch_paddle_driver 2022-04-08 12:14:33 +00:00
x54-729
23502a0753 提交tests/core/drivers/paddle_driver 2022-04-08 12:14:20 +00:00
x54-729
96a565c763 提交tests/core/drivers/jittor_driver 2022-04-08 12:14:03 +00:00
x54-729
d8ce9a7915 提交/tests/core/drivers/ 2022-04-08 12:13:11 +00:00
yh_cc
259cbf80db 提交log/envs 2022-04-08 19:23:08 +08:00
yh_cc
916a2d2c30 init dev0.8.0 2022-04-08 01:21:26 +08:00
hw
c0aa5bd932
增加Mr, R8, R52, Ohsumed, 20ng数据集的loader ,pipe (#382)
* 增加Mr, R8, R52, Ohsumed, 20ng数据集的loader ,pipe

* "更改_20ng为NG20"
2021-09-23 14:40:07 +08:00
yh_cc
c72bc070a9 1.修复yxg同学发现的DataSet copy Field导致的bug; 2. 修改DistTrainer中update_every的bug; 3.Trainer和DistTrainer修改pin_memory默认值为True 2021-09-18 00:00:38 +08:00
WillQvQ
d9e0450ae7 Merge branch 'master' of github.com:fastnlp/fastNLP into dev 2021-04-12 10:30:28 +08:00
yh_cc
3e9330d250 解决https://github.com/fastnlp/fastNLP/issues/355 的问题 2021-03-30 11:12:26 +08:00
sleepy-owl
2b91830c26
Flaky test fix (#352) 2021-02-23 19:04:05 +08:00
yh_cc
04ad8e604e DataSet apply的时候可以传入use_tqdm和tqdm_desc 2021-01-05 23:45:15 +08:00
yh_cc
dc280fa1cb 删除对spacy的依赖 2020-12-11 14:03:10 +08:00
yh_cc
7ca8d045e7 update for basemodel bug 2020-12-11 13:42:18 +08:00
yh_cc
50d7cfdd7a 在dataset中添加concat函数,支持将两个dataset concat起来 2020-12-09 19:45:55 +08:00
yunfan
f711d3070a dist_trainer for fp16 2020-12-06 03:48:08 +00:00
yh_cc
2e8350cd16 Trainer支持fp16 2020-12-05 22:30:23 +08:00
willqvq
350772f518 修改读取测试数据的位置 2020-11-23 13:34:05 +08:00
willqvq
fc8f8f6913 把测试文件夹 test 改名为 tests 2020-11-23 13:00:31 +08:00
FengZiYjun
32652407df restructure files & add "modules" directory & add CRF.py 2018-07-01 10:39:36 +08:00
FengZiYjun
3e1d995b3c update file structures 2018-06-25 14:16:47 +08:00
FengZiYjun
58127d3c4e start building word seg (generally seq2seq) model 2018-05-30 22:28:22 +08:00
FengZiYjun
52b1337e8b READY TO GO: test_charlm tested 2018-05-25 17:40:28 +08:00