Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Dev0.4.5 #193

Merged
merged 277 commits into from
Jul 12, 2019
Merged

Dev0.4.5 #193

merged 277 commits into from
Jul 12, 2019

Conversation

WillQvQ
Copy link
Member

@WillQvQ WillQvQ commented Jul 12, 2019

Description:Dev0.4.5
Main reason: 将较为成熟的开发版本合并到主分支

violetyao and others added 30 commits June 9, 2019 21:30
2. 重大更新,支持ElmoEmbedding, BertEmbedding
# Conflicts:
#	fastNLP/core/batch.py
2. 删除Trainer的prefetch参数; 在注释中增加num_workers参数
3. Trainer中默认sampler为RandomSampler
[new] 兼容pytorch的DataLoader,替换Batch为DataSetIter
2. 修改embedding.py中的bug
3. ConllReader默认跳过所有的DOCSTART标签
4. 交换bert的heavy lifting到_bert, 将BertEncoder在bert.py中暴露
5. crf中allow_transition的include_end_start修改为false,以与CRF的默认值适配
6. allow_transition与SpanMetric支持BIOES类型的tag
7. datainfo中增加打印格式化输出
xuyige and others added 27 commits July 12, 2019 04:09
修改代码以适配新fastNLP.embeddings模块
2. sequence labeling中增加BiLSTMCRF
3. embedding中修复bug
4. 将之前版本的reproduction移动到legacy文件夹
5. sequence labeling中增加中文NER
6. text classification中loader增强,修改lstm模型,增加train_bert.py
…v0.5.0

# Conflicts:
#	fastNLP/modules/encoder/embedding.py
#	reproduction/seqence_labelling/ner/train_ontonote.py
#	reproduction/text_classification/model/lstm.py
@WillQvQ WillQvQ merged commit d6326de into master Jul 12, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet