diff --git a/configs/e2e/e2e_r50_vd_pg.yml b/configs/e2e/e2e_r50_vd_pg.yml
index 3b787f46444a6e9c19f83a928bd2991b68bc4a8b..1c2edad931c3388136a2d24021760a665fbb81ce 100644
--- a/configs/e2e/e2e_r50_vd_pg.yml
+++ b/configs/e2e/e2e_r50_vd_pg.yml
@@ -69,7 +69,7 @@ Metric:
 Train:
   dataset:
     name: PGDataSet
-    label_file_list: [.././train_data/total_text/train/total_text.txt]
+    label_file_list: [.././train_data/total_text/train/]
     ratio_list: [1.0]
     data_format: icdar #two data format: icdar/textnet
     transforms:
@@ -93,7 +93,7 @@ Eval:
   dataset:
     name: PGDataSet
     data_dir: ./train_data/
-    label_file_list: [./train_data/total_text/test/total_text.txt]
+    label_file_list: [./train_data/total_text/test/]
     transforms:
       - DecodeImage: # load image
           img_mode: RGB
@@ -113,4 +113,4 @@ Eval:
     shuffle: False
     drop_last: False
     batch_size_per_card: 1 # must be 1
-    num_workers: 2
\ No newline at end of file
+    num_workers: 2
diff --git a/doc/doc_ch/pgnet.md b/doc/doc_ch/pgnet.md
index 595eedeba4c97589728d0842ebbb3ef6497272ce..5cf017da3969eac8db16c1ba3ff1462ba55b1dea 100644
--- a/doc/doc_ch/pgnet.md
+++ b/doc/doc_ch/pgnet.md
@@ -87,15 +87,15 @@ python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/im
 ```
 /PaddleOCR/train_data/total_text/train/
   |- rgb/            # total_text数据集的训练数据
-      |- img11.jpg
+      |- gt_0.png
       | ...  
-  |- train.txt       # total_text数据集的训练标注
+  |- total_text.txt       # total_text数据集的训练标注
 ```
 
 total_text.txt标注文件格式如下，文件名和标注信息中间用"\t"分隔：
 ```
 " 图像文件名                    json.dumps编码的图像标注信息"
-rgb/img11.jpg    [{"transcription": "ASRAMA", "points": [[214.0, 325.0], [235.0, 308.0], [259.0, 296.0], [286.0, 291.0], [313.0, 295.0], [338.0, 305.0], [362.0, 320.0], [349.0, 347.0], [330.0, 337.0], [310.0, 329.0], [290.0, 324.0], [269.0, 328.0], [249.0, 336.0], [231.0, 346.0]]}, {...}]
+rgb/gt_0.png    [{"transcription": "EST", "points": [[1004.0,689.0],[1019.0,698.0],[1034.0,708.0],[1049.0,718.0],[1064.0,728.0],[1079.0,738.0],[1095.0,748.0],[1094.0,774.0],[1079.0,765.0],[1065.0,756.0],[1050.0,747.0],[1036.0,738.0],[1021.0,729.0],[1007.0,721.0]]}, {...}]
 ```
 json.dumps编码前的图像标注信息是包含多个字典的list，字典中的 `points` 表示文本框的四个点的坐标(x, y)，从左上角的点开始顺时针排列。
 `transcription` 表示当前文本框的文字，**当其内容为“###”时，表示该文本框无效，在训练时会跳过。**
diff --git a/doc/doc_en/pgnet_en.md b/doc/doc_en/pgnet_en.md
index 7e6b61a5fd49bf3df86f2fc2e288669dc6fc87ae..2ab1116ce7085e2e322b4be45ee5628c247040ea 100644
--- a/doc/doc_en/pgnet_en.md
+++ b/doc/doc_en/pgnet_en.md
@@ -80,15 +80,15 @@ Download and unzip [totaltext](https://github.com/cs-chan/Total-Text-Dataset/blo
 ```
 /PaddleOCR/train_data/total_text/train/
   |- rgb/            # total_text training data of dataset
-      |- img11.png
+      |- gt_0.png
       | ...  
-  |- train.txt       # total_text training annotation of dataset
+  |- total_text.txt  # total_text training annotation of dataset
 ```
 
 total_text.txt: the format of dimension file is as follows，the file name and annotation information are separated by "\t"：
 ```
 " Image file name             Image annotation information encoded by json.dumps"
-rgb/img11.jpg    [{"transcription": "ASRAMA", "points": [[214.0, 325.0], [235.0, 308.0], [259.0, 296.0], [286.0, 291.0], [313.0, 295.0], [338.0, 305.0], [362.0, 320.0], [349.0, 347.0], [330.0, 337.0], [310.0, 329.0], [290.0, 324.0], [269.0, 328.0], [249.0, 336.0], [231.0, 346.0]]}, {...}]
+rgb/gt_0.png    [{"transcription": "EST", "points": [[1004.0,689.0],[1019.0,698.0],[1034.0,708.0],[1049.0,718.0],[1064.0,728.0],[1079.0,738.0],[1095.0,748.0],[1094.0,774.0],[1079.0,765.0],[1065.0,756.0],[1050.0,747.0],[1036.0,738.0],[1021.0,729.0],[1007.0,721.0]]}, {...}]
 ```
 The image annotation after **json.dumps()** encoding is a list containing multiple dictionaries.