diff --git a/PaddleCV/yolov3/README.md b/PaddleCV/yolov3/README.md
index 0464ae33a95d843e46bed0db6e9da7155ddfc22d..a079257e575307b3d67fdbe08a59b9982c6a1db4 100644
--- a/PaddleCV/yolov3/README.md
+++ b/PaddleCV/yolov3/README.md
@@ -47,7 +47,7 @@ Train the model on [MS-COCO dataset](http://cocodataset.org/#download), download
 The data catalog structure is as follows:
 
 ```
-  data/coco/
+  dataset/coco/
   ├── annotations
   │   ├── instances_train2014.json
   │   ├── instances_train2017.json
@@ -101,8 +101,6 @@ Please make sure that pre-trained model is downloaded and loaded correctly, othe
 
     python train.py --help
 
-
-
 **data reader introduction:**
 
 * Data reader is defined in `reader.py` .
diff --git a/PaddleCV/yolov3/README_cn.md b/PaddleCV/yolov3/README_cn.md
index 2141e36927f71aefd8418f670bc28ec27b70ed04..79d627452a3d02dddbf6dccaf62bd3b798d46c69 100644
--- a/PaddleCV/yolov3/README_cn.md
+++ b/PaddleCV/yolov3/README_cn.md
@@ -49,7 +49,7 @@ YOLOv3 的网络结构由基础特征提取网络、multi-scale特征融合层
 数据目录结构如下：
 
 ```
-data/coco/
+dataset/coco/
 ├── annotations
 │   ├── instances_train2014.json
 │   ├── instances_train2017.json
@@ -102,8 +102,6 @@ data/coco/
 
     python train.py --help
 
-
-
 **数据读取器说明：**
 
 * 数据读取器定义在reader.py中。