fastNLP

Commit Graph

Author	SHA1	Message	Date
ChenXin	38c2ef7d74	修改 callback 的测试文件	7 years ago
ChenXin	1c9a0b5875	把暂不发布的功能移到 legacy 文件夹	7 years ago
ChenXin	6cb75104b8	修改 tutorials 的测试文件	7 years ago
ChenXin	8a7bf58244	delete an old metric in test	7 years ago
ChenXin	902a3a6bcd	修改了一些注释	7 years ago
yh_cc	349194fe85	删除用于分词的metric，因为有可能引起错误	7 years ago
yh_cc	56ff4ac7a1	统一不同位置的seq_len_to_mask, 现统一到core.utils.seq_len_to_mask	7 years ago
yh_cc	af6a9da78d	Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev	7 years ago
yh_cc	6d36dbe7fb	完善测试	7 years ago
yunfan	702fa1d95c	- update attention - fix tests	7 years ago
yh	25565fe0c9	增加cnn的测试	7 years ago
ChenXin	4926b33df0	core部分的测试和一些小修改	7 years ago
ChenXin	8039f4dd45	讨论并整合了若干模块	7 years ago
yh	b7613cdb7d	conflict solve	7 years ago
yh_cc	b9558e21e6	1. 从安装文件中删除api/automl的安装 2. metric中存在seq_len的bug 3. sampler中存在命名错误，已修改	7 years ago
yunfan	4f65e17d1a	- add model runner for easier test models - add model tests	7 years ago
yh	16388d5698	修改部分注释	7 years ago
yunfan	e864aecb03	- add Const - fix bugs	7 years ago
yunfan	799d4dbc68	- add test - fix jsonloader	7 years ago
yh_cc	ded4228f93	1.增加对Trainer和Tester的多卡支持;	7 years ago
yh_cc	5e9c406761	修改embedding为init_embed初始化	7 years ago
yh_cc	f65c0935f6	Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev	7 years ago
yh_cc	06891cf90a	补充注释，并修改部分代码	7 years ago
xuyige	ee49f4177e	update char level encoder	7 years ago
yh_cc	6e265e5ae9	完善了trainer，callback等的文档; 修改了部分代码的命名以使得代码从文档中隐藏	7 years ago
xuyige	55783314bc	update documents on metrics	7 years ago
yh_cc	7997dce8a7	对DataSet的文档进行更新	7 years ago
yh_cc	66ad7d9bf9	Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev	7 years ago
yh_cc	28ece53df0	本地暂存	7 years ago
yunfan	001586fa3e	- add document	7 years ago
yh	2c202bb151	测试文档	7 years ago
yunfan	abff8d9daa	- fix test_tutorial	7 years ago
yunfan	e025350ea8	Merge branch 'dev' of https://github.com/choosewhatulike/fastNLP-private into pr	7 years ago
yunfan	c344f7a2f9	- add pad sequence for lstm - add csv, conll, json filereader - update dataloader - remove useless dataloader - fix trainer loss print - fix tests	7 years ago
yh_cc	c1ee0b27df	1.DataSet.apply()报错时提供错误的index 2.Vocabulary.from_dataset(), index_dataset()提供报错时的vocab顺序 3.embedloader在embed读取时遇到不规则的数据跳过这一行.	7 years ago
yh_cc	b69f8985c8	1. 在embedding_loader中增加新的读取函数load_with_vocab(), load_without_vocab, 比之前的函数改变主要在(1)不再需要传入embed_dim(2)自动判断当前是word2vec还是glove. 2. vocabulary增加from_dataset(), index_dataset()函数。避免需要多行写index dataset的问题。 3. 在utils中新增一个cache_result()修饰器，用于cache函数的返回值。 4. callback中新增update_every属性	7 years ago
yh_cc	29f81e79ad	准备发布0.4.0版本“	7 years ago
yh	dffd9b96cd	合并冲突	7 years ago
yh	4d1721ffe3	修改部分bug；调整callback	7 years ago
yunfan	f4e64906d4	- fix callback & tests	7 years ago
yunfan	e12041513f	Merge remote-tracking branch 'private/dev' into pr # Conflicts: # fastNLP/core/callback.py # fastNLP/core/trainer.py	7 years ago
yunfan	58f373d371	- fix test	7 years ago
yunfan	70fb4a2284	- add star transformer model - add ConllLoader, for all kinds of conll-format files - add JsonLoader, for json-format files - add SSTLoader, for SST-2 & SST-5 - change Callback interface - fix batch multi-process when killed - add README to list models and their performance	7 years ago
yh	ec90a1f0bb	Merge branch 'dev' of github.com:choosewhatulike/fastNLP-private into dev	7 years ago
yh	e5f68bbd5b	修复CRF为负数的bug	7 years ago
FengZiYjun	6a498bbdf2	* 给vocabulary添加遍历方法	7 years ago
FengZiYjun	f5ab7a5d45	* 将enas相关代码放到automl目录下 * 修复fast_param_mapping的一个bug * Trainer添加自动创建save目录 * Vocabulary的打印，显示内容	7 years ago
FengZiYjun	ef0c6e936d	Changes to Callbacks: * 给callback添加给定几个只读属性 * 通过manager设置这些属性 * 代码优化，减轻@transfer的负担	7 years ago
yh	f2d7d01bb7	修复CRF中可能存在的bug	7 years ago
yunfan	7c7f28f2ac	- add star-transformer	7 years ago

1 2 3 4 5 ...

289 Commits (3624f7dafddc23bfd60faeaeb4e8eefe541fa2eb)