yujunjun/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-11-13 08:33:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

add indicator explain

Browse Source
This commit is contained in:
WenmuZhou 2022-08-17 03:16:38 +00:00
parent b63088b9a5
commit 015cb7f08e
2 changed files with 19 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
ppstructure/table/README.md
View File

@ -30,12 +30,16 @@ The table recognition flow chart is as follows
## 2. Performance ## 2. Performance
We evaluated the algorithm on the PubTabNet<sup>[1]</sup> eval dataset, and the performance is as follows: We evaluated the algorithm on the PubTabNet<sup>[1]</sup> eval dataset, and the performance is as follows:
|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%| 93.32 |1180ms|
| SLANet(ours) | 76.2%| 94.98 |590ms|
|Method|acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)| The performance indicators are explained as follows:
| --- | --- | --- | - Acc: The accuracy of the table structure in each image, a wrong token is considered an error.
| EDD<sup>[2]</sup> |x| 88.3 | - TEDS: The accuracy of the model's restoration of table information. This indicator evaluates not only the table structure, but also the text content in the table.
| TableRec-RARE(ours) |73.8%| 93.32 | - Speed: The inference speed of a single image when the model runs on the CPU machine and MKL is enabled.
| SLANet(ours) | 76.2%| 94.98 |SLANet |
## 3. Result ## 3. Result

15
ppstructure/table/README_ch.md
View File

@ -36,11 +36,16 @@
我们在 PubTabNet<sup>[1]</sup> 评估数据集上对算法进行了评估，性能如下 我们在 PubTabNet<sup>[1]</sup> 评估数据集上对算法进行了评估，性能如下
|算法|acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)| |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 | | EDD<sup>[2]</sup> |x| 88.3 |x|
| TableRec-RARE(ours) |73.8%| 93.32 | | TableRec-RARE(ours) |73.8%| 93.32 |1180ms|
| SLANet(ours) | 76.2%| 94.98 | | SLANet(ours) | 76.2%| 94.98 |590ms|
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。
- TEDS: 模型对表格信息还原的准确度，此指标评价内容不仅包含表格结构，还包含表格内的文字内容。
- Speed: 模型在CPU机器上，开启MKL的情况下，单张图片的推理速度。
## 3. 效果演示 ## 3. 效果演示