hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
1684 Commits
3 Branches
25 MB
521 Download
Tree: 0ca22b6b17
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '0ca22b6b17'
${ noResults }
Commit Graph

405 Commits (0ca22b6b17a6bf84811772b682a57b94de7a0968)

Author SHA1 Message Date
  yh_cc 0ca22b6b17 1.修改部分文档中的typo; 2.支持对transformers embedding 5 years ago
  yh_cc edd3022bde 新增ConstantTokenNumSampler使得每个sample中token数量一致，可以最大化利用GPU的显存 5 years ago
  yh_cc fe7ce8e448 Merge branch 'master' of github.com:fastnlp/fastNLP 5 years ago
  yh_cc ee584e71dc 修复seq2seq_generator的bug 5 years ago
  yunfan 8d08626d67 [update] fix padding masking in viterbi_decode() of CRF 5 years ago
  yh_cc 0d0a6f746a 修复测试失败问题 5 years ago
  ROGERDJQ b6a07be364
[test] fix f1 test (#314) 5 years ago
  yh_cc 40bec21684 修复save_path在dev为空的时候的bug 5 years ago
  roger b9b688d233 f1 fix 5 years ago
  yh_cc c957ed69c1 loader中load先将filename排序保证一致的load顺序, 避免测试不通过 5 years ago
  yh_cc e361b32c3a 在@linzehui 的帮助下seq2seq终于有了第一个版本; 目前实现了Seq2Seq的Transformer和LSTM版本，但metric和loss还没update; 5 years ago
  ROGERDJQ 4e95989e97
[new] add seperator for conll loader (#293) 5 years ago
  linzehui b95aa56afb 基本完成seq2seq基础功能 5 years ago
  linzehui 15360e9724 保存一版旧版 5 years ago
  yh_cc ff8b9a37a7 修复Embedding注释错误与core.utils.py代码错误 5 years ago
  ChenXin 4557202023 更新了 ControlC 的 API 5 years ago
  yh_cc 18747e632e 修复Vocabulary在load的时候可能发生的bug 5 years ago
  yh_cc ab047a2aa3 新增对RobertaEmbedding和GPT2Embedding的支持 6 years ago
  yh_cc 7398f2b0b2 1.增加RobertaEmbedding与GPT2Embedding 6 years ago
  yh_cc 45139ebbff BertEmbedding支持选择是否缩小词表 6 years ago
  yh_cc ace8aafdb2 修复BertEmbedding在include_cls_sep=True时，SEP位置的值不正确的问题 6 years ago
  yh_cc ba645f4483 1.将collect_fn修改为collate_fn使得与pytorch保持一致; 2.增加对BatchSampler的支持 6 years ago
  yh_cc 367edb7ad1 修复move_to_device中device为None时可能出现错误的问题; BERTEmbedding中增加一个可选参数 6 years ago
  yh_cc a8aa1035d3 修复batch转tensor的bug; 新增对TorchLoaderIter的说明 6 years ago
  yh_cc 885c74022c 增加对ConfusionMatrix的测试用例 6 years ago
  yh_cc 7f01971321 调整涉及到多个field取batch的实现方式 6 years ago
  yh_cc dce1a73f53 Merge branch 'master' of github.com:fastnlp/fastNLP 6 years ago
  yh_cc 8fe7a4f191 防止BERTEmbedding在中文场景下被错误使用 6 years ago
  Yige Xu 56bf05adf1 Update test_classification.py 6 years ago
  ChenXin 26ee41f923 DataSet 增加了 apply_more 和 apply_filed_more 两个新方法 6 years ago
  yunfan 54dcc23ad7 [update] collect_fn keep tracks for field 6 years ago
  yunfan 423e8e3746 [update] huge modify on collect_fn 6 years ago
  yunfan 127d6d194b [add] collect_fn for multi field combined inputs 6 years ago
  yh_cc 5ffd46ae8d Merge branch 'master' of github.com:fastnlp/fastNLP 6 years ago
  yh_cc 8acb0f4ad6 1.新增Vocabulary的save与load功能; 2.修复BERTEmbedding drop_word的bug; 3.新增各种Embedding的使用注释 6 years ago
  ChenXin 2d1500651f 三个纬度 check: DataSet Tutorial 6 years ago
  yh_cc 9bed203a35 Merge branch 'master' of github.com:fastnlp/fastNLP 6 years ago
  yh_cc 51e8c3c3b4 update static_embedding to make its property words_to_words is sequential 6 years ago
  ROGERDJQ f3ee16a5f6
[new] add ConfusionMatrix, ConfusionMatrixMetric (#272) 6 years ago
  Yige Xu 58762810ec [update] Re-organize classification loader and pipe 6 years ago
  yh_cc 4518a8fccb [bug fix] test bug fix 6 years ago
  yunfan 1139986b36 [bugfix] fix logger's logging level 6 years ago
  yh_cc 9293a6c1ab 修复一个小bug 6 years ago
  yh_cc 03e9ca2147 修复CWSPipe中无法读取包含<, >的数据的问题https://github.com/fastnlp/fastNLP/issues/258#issue-533768454 6 years ago
  yh_cc faec3245d4 update CMRC2018Metric测试 6 years ago
  yh_cc 38fea0fcfa 1.增强CMRC2018Metric的使用范围; 2. StaticEmbedding支持仅使用来自于pretrain embedding的token 6 years ago
  Yige Xu be432c3b39 fix a bug in ClassifyFPRMetric 6 years ago
  Yige Xu 0547572d58 add ClassifyFPRMetric 6 years ago
  yh f887da12a1 解决CrossEntropyLoss测试因为数值问题无法通过测试的问题 6 years ago
  yh 9c0190fbd8 新增对CrossEntropyLoss中class_in_dim的测试 6 years ago