Merge branch 'dygraph' into drgraph/fix_infer_post

doc/doc_ch/pgnet.md

@@ -27,13 +27,17 @@ PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.Wang
 ![](../imgs_results/e2e_res_img295_pgnet.png)
 
 ### 性能指标
-| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS (size=640)|下载链接|
+####测试集: Total Text
+####测试环境: NVIDIA Tesla V100-SXM2-16GB
+| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|下载|
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-|Paper|85.30|86.80|86.1|-|-|61.7|38.20|-|
-|Ours|87.03|82.48|84.69|61.71|58.43|60.03|62.61|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar)|
+|Paper|85.30|86.80|86.1|-|-|61.7|38.20 (size=640)|-|
+|Ours|87.03|82.48|84.69|61.71|58.43|60.03|48.73 (size=768)|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar)|
 
 *note：PaddleOCR里的PGNet实现针对预测速度做了优化，在精度下降可接受范围内，可以显著提升端对端预测速度*
 
+
+
 <a name="环境配置"></a>
 ## 二、环境配置
 请先参考[快速安装](./installation.md)配置PaddleOCR运行环境。

doc/doc_en/pgnet_en.md

@@ -24,10 +24,12 @@ The results of detection and recognition are as follows:
 ![](../imgs_results/e2e_res_img293_pgnet.png)
 ![](../imgs_results/e2e_res_img295_pgnet.png)
 ### Performance
-| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS (size=640)|download|
+####Test set: Total Text
+####Test environment: NVIDIA Tesla V100-SXM2-16GB
+| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|download|
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-|Paper|85.30|86.80|86.1|-|-|61.7|38.20|-|
-|Ours|87.03|82.48|84.69|61.71|58.43|60.03|62.61|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar)|
+|Paper|85.30|86.80|86.1|-|-|61.7|38.20 (size=640)|-|
+|Ours|87.03|82.48|84.69|61.71|58.43|60.03|48.73 (size=768)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar)|
 
 *note：PGNet in PaddleOCR optimizes the prediction speed, and can significantly improve the end-to-end prediction speed within the acceptable range of accuracy reduction*