diff --git a/deploy/serving/README.md b/deploy/serving/README.md
index 38393bf36102a862e829dda345c94a4a57d44895..0d0122b9f3a238f24cab51096b1aa723920e4cb8 100644
--- a/deploy/serving/README.md
+++ b/deploy/serving/README.md
@@ -2,11 +2,11 @@
 
 `PaddleDetection`训练出来的模型可以使用[Serving](https://github.com/PaddlePaddle/Serving) 部署在服务端。  
 本教程以在COCO数据集上用`configs/yolov3/yolov3_darknet53_270e_coco.yml`算法训练的模型进行部署。  
-预训练模型权重文件为[yolov3_darknet53_270e_coco.pdparams](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) 。
+预训练模型权重文件为[yolov3_darknet53_270e_coco.pdparams](https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams) 。
 
 ## 1. 首先验证模型
 ```
-python tools/infer.py -c  --infer_img=demo/000000014439.jpg -o use_gpu=True weights=https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams --infer_img=demo/000000014439.jpg
+python tools/infer.py -c configs/yolov3/yolov3_darknet53_270e_coco.yml --infer_img=demo/000000014439.jpg -o use_gpu=True weights=https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams --infer_img=demo/000000014439.jpg
 ```
 
 ## 2. 安装 paddle serving
diff --git a/docs/tutorials/INSTALL.md b/docs/tutorials/INSTALL.md
index db09adaadf1482fd0413644e9e2bbb1ee43a2559..ee0646d08e32ffc3d1dc88e08edf2a802f3ba594 100644
--- a/docs/tutorials/INSTALL.md
+++ b/docs/tutorials/INSTALL.md
@@ -122,7 +122,7 @@ OK
 ```
 # Predict an image by GPU
 export CUDA_VISIBLE_DEVICES=0
-python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams --infer_img=demo/000000014439.jpg
+python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg
 ```
 
 An image of the same name with the predicted result will be generated under the `output` folder.
diff --git a/docs/tutorials/INSTALL_cn.md b/docs/tutorials/INSTALL_cn.md
index e51a1091d63a1ce66092bb90e7cf8a5dfa1941a2..50d847367fc23d6d8a180fc66ca66769147f9bef 100644
--- a/docs/tutorials/INSTALL_cn.md
+++ b/docs/tutorials/INSTALL_cn.md
@@ -118,7 +118,7 @@ OK
 ```
 # 在GPU上预测一张图片
 export CUDA_VISIBLE_DEVICES=0
-python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams --infer_img=demo/000000014439.jpg
+python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg
 ```
 
 会在`output`文件夹下生成一个画有预测结果的同名图像。
diff --git a/docs/tutorials/QUICK_STARTED.md b/docs/tutorials/QUICK_STARTED.md
index 9b3e0dced48327c0db645c6236f9f73f66692f4b..b4e7ae9491d38ca07154b67e9523b7ae8d77ca7a 100644
--- a/docs/tutorials/QUICK_STARTED.md
+++ b/docs/tutorials/QUICK_STARTED.md
@@ -14,7 +14,7 @@ export CUDA_VISIBLE_DEVICES=0
 
 ```
 # predict an image using PP-YOLO
-python tools/infer.py -c configs/ppyolo/ppyolo.yml -o use_gpu=true weights=https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams --infer_img=demo/000000014439.jpg
+python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg
 ```
 
 the result：
diff --git a/docs/tutorials/QUICK_STARTED_cn.md b/docs/tutorials/QUICK_STARTED_cn.md
index 2b5212af15b855759d9455037b83800d5e1d7603..d201e7fc901c2aef8b1ce95ebc9ba087ed3a1d9e 100644
--- a/docs/tutorials/QUICK_STARTED_cn.md
+++ b/docs/tutorials/QUICK_STARTED_cn.md
@@ -11,7 +11,7 @@ export CUDA_VISIBLE_DEVICES=0
 ## 一、快速体验
 ```
 # 用PP-YOLO算法在COCO数据集上预训练模型预测一张图片
-python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg
+python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg
 ```
 
 结果如下图：