diff --git a/doc/doc_ch/angle_class.md b/doc/doc_ch/angle_class.md
index 846be15f834952587e8d3b2533ff147375db7c31..4d7ff0d7aa839591df6e359d4f7295ab2f0cc445 100644
--- a/doc/doc_ch/angle_class.md
+++ b/doc/doc_ch/angle_class.md
@@ -21,9 +21,8 @@ ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/cls/dataset
 
 ```
 " 图像文件名                 图像标注信息 "
-
-train_data/cls/word_001.jpg   0
-train_data/cls/word_002.jpg   180
+train/word_001.jpg   0
+train/word_002.jpg   180
 ```
 
 最终训练集应有如下文件结构：
@@ -55,6 +54,8 @@ train_data/cls/word_002.jpg   180
 
 ### 启动训练
 
+将准备好的txt文件和图片文件夹路径分别写入配置文件的 `Train/Eval.dataset.label_file_list` 和 `Train/Eval.dataset.data_dir` 字段下，`Train/Eval.dataset.data_dir`字段下的路径和文件里记载的图片名构成了图片的绝对路径。
+
 PaddleOCR提供了训练脚本、评估脚本和预测脚本。
 
 开始训练:
diff --git a/doc/doc_en/angle_class_en.md b/doc/doc_en/angle_class_en.md
index e6157d1635431a45b3bc9392d1115dcdd917aeeb..8d9328700f3e638eb4576d132aa32fb93b3ad0c0 100644
--- a/doc/doc_en/angle_class_en.md
+++ b/doc/doc_en/angle_class_en.md
@@ -23,8 +23,8 @@ First put the training images in the same folder (train_images), and use a txt f
 ```
 " Image file name           Image annotation "
 
-train_data/word_001.jpg   0
-train_data/word_002.jpg   180
+train/word_001.jpg   0
+train/word_002.jpg   180
 ```
 
 The final training set should have the following file structure:
@@ -57,6 +57,7 @@ containing all images (test) and a cls_gt_test.txt. The structure of the test se
 ```
 
 ### TRAINING
+Write the prepared txt file and image folder path into the configuration file under the `Train/Eval.dataset.label_file_list` and `Train/Eval.dataset.data_dir` fields, the absolute path of the image consists of the `Train/Eval.dataset.data_dir` field and the image name recorded in the txt file.
 
 PaddleOCR provides training scripts, evaluation scripts, and prediction scripts.