Merge pull request #2446 from JetHong/pgnet-postpro

fix pgnet.md

doc/doc_ch/pgnet.md

@@ -16,7 +16,7 @@ OCR算法可以分为两阶段算法和端对端的算法。二阶段OCR算法
 - 提出基于图的修正模块（GRM）来进一步提高模型识别性能
 - 精度更高，预测速度更快
 
-PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf)， 算法原理图如下所示：
+PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) ,算法原理图如下所示：
 ![](../pgnet_framework.png)
 输入图像经过特征提取送入四个分支，分别是：文本边缘偏移量预测TBO模块，文本中心线预测TCL模块，文本方向偏移量预测TDO模块，以及文本字符分类图预测TCC模块。
 其中TBO以及TCL的输出经过后处理后可以得到文本的检测结果，TCL、TDO、TCC负责文本识别。
@@ -51,13 +51,13 @@ wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/e2e_server_pgnetA_infer.
 ### 单张图像或者图像集合预测
 ```bash
 # 预测image_dir指定的单张图像
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True
 
 # 预测image_dir指定的图像集合
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True
 
 # 如果想使用CPU进行预测，需设置use_gpu参数为False
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True --use_gpu=False
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True --use_gpu=False
 ```
 ### 可视化结果
 可视化文本检测结果默认保存到./inference_results文件夹里面，结果文件的名称前缀为'e2e_res'。结果示例如下：
@@ -137,12 +137,12 @@ python3 tools/eval.py -c configs/e2e/e2e_r50_vd_pg.yml  -o Global.checkpoints="{
 ### 模型预测
 测试单张图像的端到端识别效果
 ```shell
-python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
+python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/e2e_pgnet/best_accuracy" Global.load_static_weights=false
 ```
 
 测试文件夹下所有图像的端到端识别效果
 ```shell
-python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
+python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/e2e_pgnet/best_accuracy" Global.load_static_weights=false
 ```
 
 ### 预测推理
@@ -150,7 +150,7 @@ python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img=
 首先将PGNet端到端训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，以英文数据集训练的模型为例[模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar) ，可以使用如下命令进行转换：
 ```
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar && tar xf en_server_pgnetA.tar
-python3 tools/export_model.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.pretrained_model=./en_server_pgnetA/iter_epoch_450 Global.load_static_weights=False Global.save_inference_dir=./inference/e2e
+python3 tools/export_model.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.pretrained_model=./en_server_pgnetA/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/e2e
 ```
 **PGNet端到端模型推理，需要设置参数`--e2e_algorithm="PGNet"`**，可以执行如下命令：
 ```
@@ -171,7 +171,9 @@ python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/im
 
 ![](../imgs_results/e2e_res_img623_pgnet.jpg)
 
-#### (3). 精度与FPS
-|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|
-| --- | --- | --- | --- | --- | --- | --- |
-|87.03|82.48|84.69|61.71|58.43|60.03|62.61|
+#### (3). 性能指标
+| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS (size=640)|
+| --- | --- | --- | --- | --- | --- | --- | --- |
+|Ours|87.03|82.48|84.69|61.71|58.43|60.03|62.61|
+|Paper|85.30|86.80|86.1|-|-|61.7|38.20|
+*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*

doc/doc_en/pgnet_en.md

@@ -15,7 +15,7 @@ In recent years, the end-to-end OCR algorithm has been well developed, including
 - A graph based modification module (GRM) is proposed to further improve the performance of model recognition
 - Higher accuracy and faster prediction speed
 
-For details of PGNet algorithm, please refer to [paper](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf), The schematic diagram of the algorithm is as follows:
+For details of PGNet algorithm, please refer to [paper](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) ,The schematic diagram of the algorithm is as follows:
 ![](../pgnet_framework.png)
 After feature extraction, the input image is sent to four branches: TBO module for text edge offset prediction, TCL module for text centerline prediction, TDO module for text direction offset prediction, and TCC module for text character classification graph prediction.
 The output of TBO and TCL can get text detection results after post-processing, and TCL, TDO and TCC are responsible for text recognition.
@@ -49,13 +49,13 @@ After decompression, there should be the following file structure:
 ### Single image or image set prediction
 ```bash
 # Prediction single image specified by image_dir
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True
 
 # Prediction the collection of images specified by image_dir
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True
 
 # If you want to use CPU for prediction, you need to set use_gpu parameter is false
-python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e/" --e2e_pgnet_polygon=True --use_gpu=False
+python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/imgs_en/img623.jpg" --e2e_model_dir="./inference/e2e_server_pgnetA_infer/" --e2e_pgnet_polygon=True --use_gpu=False
 ```
 ### Visualization results
 The visualized end-to-end results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'e2e_res'. Examples of results are as follows:
@@ -141,12 +141,12 @@ python3 tools/eval.py -c configs/e2e/e2e_r50_vd_pg.yml  -o Global.checkpoints="{
 ### Model Test
 Test the end-to-end result on a single image:
 ```shell
-python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
+python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/e2e_pgnet/best_accuracy" Global.load_static_weights=false
 ```
 
 Test the end-to-end result on all images in the folder:
 ```shell
-python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
+python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/e2e_pgnet/best_accuracy" Global.load_static_weights=false
 ```
 
 ### Model inference
@@ -154,7 +154,7 @@ python3 tools/infer_e2e.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.infer_img=
 First, convert the model saved in the PGNet end-to-end training process into an inference model. In the first stage of training based on composite dataset, the model of English data set training is taken as an example[model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar), you can use the following command to convert:
 ```
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar && tar xf en_server_pgnetA.tar
-python3 tools/export_model.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.pretrained_model=./en_server_pgnetA/iter_epoch_450 Global.load_static_weights=False Global.save_inference_dir=./inference/e2e
+python3 tools/export_model.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.pretrained_model=./en_server_pgnetA/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/e2e
 ```
 **For PGNet quadrangle end-to-end model inference, you need to set the parameter `--e2e_algorithm="PGNet"`**, run the following command:
 ```
@@ -173,7 +173,9 @@ python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/im
 The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'e2e_res'. Examples of results are as follows:
 
 ![](../imgs_results/e2e_res_img623_pgnet.jpg)
-#### (3). Metric and FPS
-|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|
-| --- | --- | --- | --- | --- | --- | --- |
-|87.03|82.48|84.69|61.71|58.43|60.03|62.61|
+#### (3). Performance
+| |det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS (size=640)|
+| --- | --- | --- | --- | --- | --- | --- | --- |
+|Ours|87.03|82.48|84.69|61.71|58.43|60.03|62.61|
+|Paper|85.30|86.80|86.1|-|-|61.7|38.20|
+*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*