diff --git a/doc/doc_ch/angle_class.md b/doc/doc_ch/angle_class.md
index e884d5ef48801fb595a422ced95ab5e3b15b627c..b2118661290ac0b6f2731a8fd9ba76dadcb21ded 100644
--- a/doc/doc_ch/angle_class.md
+++ b/doc/doc_ch/angle_class.md
@@ -77,7 +77,7 @@ PaddleOCR提供了多种数据增强方式，如果您希望在训练时加入
 默认的扰动方式有：颜色空间转换(cvtColor)、模糊(blur)、抖动(jitter)、噪声(Gasuss noise)、随机切割(random crop)、透视(perspective)、颜色反转(reverse),随机数据增强(RandAugment)。
 
 训练过程中除随机数据增强外每种扰动方式以50%的概率被选择，具体代码实现请参考：
-[randaugment.py.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/cls/randaugment.py)
+[randaugment.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/cls/randaugment.py)
 [img_tools.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/rec/img_tools.py)
 
 *由于OpenCV的兼容性问题，扰动操作暂时只支持linux*
diff --git a/doc/doc_en/angle_class_en.md b/doc/doc_en/angle_class_en.md
index 91af20a4cb34330277d8e770459c452614f9b6e0..c7fff3a1833570cda7687b87efb7c3af2ec49120 100644
--- a/doc/doc_en/angle_class_en.md
+++ b/doc/doc_en/angle_class_en.md
@@ -78,7 +78,7 @@ PaddleOCR provides a variety of data augmentation methods. If you want to add di
 The default perturbation methods are: cvtColor, blur, jitter, Gasuss noise, random crop, perspective, color reverse, RandAugment.
 
 Except for RandAugment, each disturbance method is selected with a 50% probability during the training process. For specific code implementation, please refer to:
-[randaugment.py.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/cls/randaugment.py)
+[randaugment.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/cls/randaugment.py)
 [img_tools.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/rec/img_tools.py)
 
 
diff --git a/ppocr/data/cls/dataset_traversal.py b/ppocr/data/cls/dataset_traversal.py
index c465bf9d3bc22aa794dcea47020b8b851f2dfbf8..01f8c89c839f0c8f6d07ca6ad9676947ce25f6ab 100755
--- a/ppocr/data/cls/dataset_traversal.py
+++ b/ppocr/data/cls/dataset_traversal.py
@@ -122,8 +122,6 @@ class SimpleReader(object):
                         img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
 
                     if self.use_distort:
-                        # if random.randint(1, 100)>= 50:
-                        #     img = random_crop(img)
                         img = warp(img, 10)
                         img = self.randaug(img)
                     norm_img = resize_norm_img(img, self.image_shape)