hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
989 Commits
3 Branches
25 MB
1 Download
 
 
 
 
 
Tree: 372496ca32
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '372496ca32'
${ noResults }
fastNLP/fastNLP/core
xuyige 089009f9f2 大幅度更新： 6 years ago
..
__init__.py [unstable] change Batch to torch's DataLoader 6 years ago
_parallel_utils.py Tester中predict function的DataParallel并行 6 years ago
batch.py 1.修复BertEmbedding中的bug; 2. 修复Batch, Field在进行类型转换时的bug 6 years ago
callback.py 修复GradientClip在update_every的场景下会更新错误的问题 6 years ago
const.py Dev0.4.0 (#149) 6 years ago
dataset.py 1.修复trainer中潜在多步更新bug; 2. LSTM的数据并行修改；3. embed_loader中bug修复, 且允许手动初始化； 6 years ago
field.py 1.修复BertEmbedding中的bug; 2. 修复Batch, Field在进行类型转换时的bug 6 years ago
instance.py 修改了最新的文档 6 years ago
losses.py 大幅度更新： 6 years ago
metrics.py 新增NER的数据加载与模型代码; 修改metric中的typo; 修改LSTM中的默认初始化将forget gate设置为1. 6 years ago
optimizer.py 1.增加AdamW的optimizer;2.修复Trainer中metric_key的bug;3.静态embedding初始化修改;4.CrossEntropyLoss增加对reduction的支持' 6 years ago
predictor.py update documents in predictor 6 years ago
sampler.py Dev0.4.0 (#149) 6 years ago
tester.py Tester中predict function的DataParallel并行 6 years ago
trainer.py 1.增加AdamW的optimizer;2.修复Trainer中metric_key的bug;3.静态embedding初始化修改;4.CrossEntropyLoss增加对reduction的支持' 6 years ago
utils.py Tester中predict function的DataParallel并行 6 years ago
vocabulary.py 1. 在vocabulary的from_dataset中增加no_create_entry_dataset选项，用于传递dev和test 6 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

一款轻量级的自然语言处理（NLP）工具包，目标是减少用户项目中的工程型代码，例如数据处理循环、训练循环、多卡运行等

Python Jupyter Notebook Text CSV Markdown