opensource/PaddleOCR
3
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2026-09-24 23:33:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

update table metric (#7272)

Browse Source 
* update model size

* update layout dict in whl

* update metric

* update metric
This commit is contained in:
zhoujun
2022-08-21 10:56:07 +08:00
committed by GitHub
parent 8c7c45420f
commit dd063fc98b
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ppstructure/table/README.md
+2 -2
View File
@@ -33,8 +33,8 @@ We evaluated the algorithm on the PubTabNet<sup>[1]</sup> eval dataset, and the
|Method|Acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|Speed|
| --- | --- | --- | ---|
| EDD<sup>[2]</sup> |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.
ppstructure/table/README_ch.md
+2 -2
View File
@@ -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<sup>[2]</sup> |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。