diff --git a/docs/tutorials/PrepareDataSet.md b/docs/tutorials/PrepareDataSet.md
index 2689ebf089c0847ad2eeb4ca9f587bdbab77f43b..e1d363d844cd056e4a1a3909d9b74f39efd1e560 100644
--- a/docs/tutorials/PrepareDataSet.md
+++ b/docs/tutorials/PrepareDataSet.md
@@ -51,7 +51,7 @@ VOC数据集指的是Pascal VOC比赛使用的数据。用户自定义的VOC数
 
 ##### VOC数据集下载  
 
-- 通过代码自动化下载VOC数据集  
+- 通过代码自动化下载VOC数据集，数据集较大，下载需要较长时间
 
     ```
     # 执行代码自动化下载VOC数据集  
@@ -151,11 +151,11 @@ COCO数据集指的是COCO比赛使用的数据。用户自定义的COCO数据
 
 
 ##### COCO数据下载  
-- 通过代码自动化下载COCO数据集  
+- 通过代码自动化下载COCO数据集，数据集较大，下载需要较长时间
 
     ```
     # 执行代码自动化下载COCO数据集  
-    python dataset/voc/download_coco.py
+    python dataset/coco/download_coco.py
     ```
 
     代码执行完成后COCO数据集文件组织结构为：
diff --git a/docs/tutorials/QUICK_STARTED.md b/docs/tutorials/QUICK_STARTED.md
index a222b592de15918ea3f83ab8ec54a314b01c02e5..9b3e0dced48327c0db645c6236f9f73f66692f4b 100644
--- a/docs/tutorials/QUICK_STARTED.md
+++ b/docs/tutorials/QUICK_STARTED.md
@@ -73,6 +73,8 @@ visualdl --logdir vdl_dir/scalar/ --host <host_IP> --port <port_num>
 python tools/eval.py -c configs/yolov3/yolov3_mobilenet_v1_roadsign.yml -o use_gpu=true
 ```
 
+The final mAP should be around 0.85. The dataset is small so the precision may vary a little after each training.
+
 
 ### 3、Inference
 ```
diff --git a/docs/tutorials/QUICK_STARTED_cn.md b/docs/tutorials/QUICK_STARTED_cn.md
index f081dc2032860863e927293ea7247be21b772d53..4bcb933b4f5f376aaeda9eefb08f411668de3cd4 100644
--- a/docs/tutorials/QUICK_STARTED_cn.md
+++ b/docs/tutorials/QUICK_STARTED_cn.md
@@ -70,6 +70,7 @@ visualdl --logdir vdl_dir/scalar/ --host <host_IP> --port <port_num>
 
 python tools/eval.py -c configs/yolov3/yolov3_mobilenet_v1_roadsign.yml -o use_gpu=true
 ```
+最终模型精度在mAP=0.85左右，由于数据集较小因此每次训练结束后精度会有一定波动
 
 
 ### 3、预测