关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
yanhui
/
PaddleNLP
Not watched
1
0
Fork 0
Code
Releases 0 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.
3299 Commits
1 Branch
84 MiB
48 Download
 
 
 
 
 
 
Branch: optim_uie_for_npu
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'optim_uie_for_npu'
${ noResults }
PaddleNLP/paddlenlp/metrics
westfish 520cb0913b
update spanevaluator (#4195) 		1 year ago
..
README.md first commit without legacy files 3 years ago
__init__.py Add UIE (#1986) 2 years ago
bleu.py black format all (#4014) 1 year ago
chunk.py black format all (#4014) 1 year ago
distinct.py black format all (#4014) 1 year ago
dureader.py black format all (#4014) 1 year ago
glue.py black format all (#4014) 1 year ago
perplexity.py black format all (#4014) 1 year ago
rouge.py black format all (#4014) 1 year ago
sighan.py black format all (#4014) 1 year ago
span.py update spanevaluator (#4195) 1 year ago
squad.py black format all (#4014) 1 year ago
utils.py fix bleu trans_func error, vae dataloader error and distillation arg bug 3 years ago

README.md

paddlenlp.metrics

目前paddlenlp提供以下评价指标：

Metric 简介 API
Perplexity 困惑度，常用来衡量语言模型优劣，也可用于机器翻译、文本生成等任务。 paddlenlp.metrics.Perplexity
BLEU(bilingual evaluation understudy) 机器翻译常用评价指标 paddlenlp.metrics.BLEU
Rouge(Recall-Oriented Understudy for Gisting Evaluation) 评估自动文摘以及机器翻译的指标 paddlenlp.metrics.RougeL, paddlenlp.metrics.RougeN
AccuracyAndF1 准确率及F1-score，可用于GLUE中的MRPC 和QQP任务 paddlenlp.metrics.AccuracyAndF1
PearsonAndSpearman 皮尔森相关性系数和斯皮尔曼相关系数。可用于GLUE中的STS-B任务 paddlenlp.metrics.PearsonAndSpearman
Mcc(Matthews correlation coefficient) 马修斯相关系数，用以测量二分类的分类性能的指标。可用于GLUE中的CoLA任务 paddlenlp.metrics.Mcc
ChunkEvaluator 计算了块检测的精确率、召回率和F1-score。常用于序列标记任务，如命名实体识别（NER） paddlenlp.metrics.ChunkEvaluator
Squad 用于SQuAD和DuReader-robust的评价指标 paddlenlp.metrics.compute_predictions, paddlenlp.metrics.squad_evaluate
Delete task

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

cancel
confirm

No Description

Python C++ Cuda Text Markdown other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit