diff --git a/deploy/cpp/docs/linux_build.md b/deploy/cpp/docs/linux_build.md
index 97311b48e16b7b903a2b1ca99a482179927c65fa..b2873654114ff124dc573ff9c975b1569002f3c8 100755
--- a/deploy/cpp/docs/linux_build.md
+++ b/deploy/cpp/docs/linux_build.md
@@ -5,7 +5,7 @@
 
 ## 前置条件
 * G++ 8.2
-* CUDA 9.0 / CUDA 10.0, cudnn 7+ （仅在使用GPU版本的预测库时需要）
+* CUDA 9.0 / CUDA 10.1, cudnn 7+ （仅在使用GPU版本的预测库时需要）
 * CMake 3.0+
 
 请确保系统已经安装好上述基本软件，**下面所有示例以工作目录为 `/root/projects/`演示**。
@@ -133,7 +133,7 @@ make
 `样例二`:
 ```shell
 #使用 `GPU`预测视频`/root/projects/videos/test.mp4`
-./build/main --model_dir=/root/projects/models/yolov3_darknet --video_path=/root/projects/images/test.mp4 --device=GPU
+./build/main --model_dir=/root/projects/models/yolov3_darknet --video_file=/root/projects/images/test.mp4 --device=GPU
 ```
 视频文件目前支持`.mp4`格式的预测，`可视化预测结果`会保存在当前目录下`output.mp4`文件中。
 
diff --git a/deploy/cpp/scripts/build.sh b/deploy/cpp/scripts/build.sh
index 6c3bbbce674307ce52df9cce487b3153493bc093..cf3ed3981e585348b7e1d865402e761c94236f4f 100644
--- a/deploy/cpp/scripts/build.sh
+++ b/deploy/cpp/scripts/build.sh
@@ -38,11 +38,11 @@ then
   echo "set OPENCV_DIR for x86_64"
   # linux系统通过以下命令下载预编译的opencv
   mkdir -p $(pwd)/deps && cd $(pwd)/deps
-  wget -c https://paddledet.bj.bcebos.com/data/opencv3.4.6gcc8.2ffmpeg.zip
-  unzip opencv3.4.6gcc8.2ffmpeg.zip && cd ..
+  wget -c https://paddledet.bj.bcebos.com/data/opencv-3.4.16_gcc8.2_ffmpeg.tar.gz
+  tar -xvf opencv-3.4.16_gcc8.2_ffmpeg.tar.gz && cd ..
 
   # set OPENCV_DIR
-  OPENCV_DIR=$(pwd)/deps/opencv3.4.6gcc8.2ffmpeg
+  OPENCV_DIR=$(pwd)/deps/opencv-3.4.16_gcc8.2_ffmpeg
 
 elif [ "$MACHINE_TYPE" = "aarch64" ]
 then