From dd063fc98b7b8e711e967d5b59fbb055a72751ac Mon Sep 17 00:00:00 2001 From: zhoujun Date: Sun, 21 Aug 2022 10:56:07 +0800 Subject: [PATCH] update table metric (#7272) * update model size * update layout dict in whl * update metric * update metric --- ppstructure/table/README.md | 4 ++-- ppstructure/table/README_ch.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/ppstructure/table/README.md b/ppstructure/table/README.md index 3732a89c..a5d0da3c 100644 --- a/ppstructure/table/README.md +++ b/ppstructure/table/README.md @@ -33,8 +33,8 @@ We evaluated the algorithm on the PubTabNet[1] eval dataset, and the |Method|Acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|Speed| | --- | --- | --- | ---| | EDD[2] |x| 88.3 |x| -| TableRec-RARE(ours) |73.8%| 95.3% |1550ms| -| SLANet(ours) | 76.2%| 95.85% |766ms| +| TableRec-RARE(ours) | 71.73%| 93.88% |779ms| +| SLANet(ours) | 76.31%| 95.89%|766ms| The performance indicators are explained as follows: - Acc: The accuracy of the table structure in each image, a wrong token is considered an error. diff --git a/ppstructure/table/README_ch.md b/ppstructure/table/README_ch.md index cc73f8bc..e83c81be 100644 --- a/ppstructure/table/README_ch.md +++ b/ppstructure/table/README_ch.md @@ -39,8 +39,8 @@ |算法|Acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|Speed| | --- | --- | --- | ---| | EDD[2] |x| 88.3% |x| -| TableRec-RARE(ours) |73.8%| 95.3% |1550ms| -| SLANet(ours) | 76.2%| 95.85% |766ms| +| TableRec-RARE(ours) | 71.73%| 93.88% |779ms| +| SLANet(ours) |76.31%| 95.89%|766ms| 性能指标解释如下： - Acc: 模型对每张图像里表格结构的识别准确率，错一个token就算错误。 -- GitLab