1.下载docker镜像
在官方网址可以选择合适的版本:
/metropolis/deepstream/dev-guide/text/DS_docker_containers.html#a-docker-container-for-dgpu
docker pull /nvidia/deepstream:6.1-triton
2.启动容器
参数根据自己机器配置进行设置
docker run --gpus=all --shm-size=12g --ulimit memlock=-1 --ulimit stack=67108864 -it --name ds6 /nvidia/deepstream:6.1-triton
3.安装库
apt-get update
apt install python3-gi python3-dev python3-gst-1.0 python-gi-dev git python-dev \
python3 python3-pip python3.8-dev cmake g++ build-essential libglib2.0-dev \
libglib2.0-dev-bin python-gi-dev libtool m4 autoconf automake
4.克隆python示例项目及子项目
cd /opt/nvidia/deepstream/deepstream/sources
export GIT_SSL_NO_VERIFY=true
git clone /NVIDIA-AI-IOT/deepstream_python_apps.git
cd deepstream_python_apps
git submodule update --init
如果克隆慢,手动用gitee镜像下载
cd /opt/nvidia/deepstream/deepstream/sources
export GIT_SSL_NO_VERIFY=true
git clone /qst1998/deepstream_python_apps.git
cd deepstream_python_apps/3rdparty
rm -rf *
git clone /qst1998/
cd gst-python
git checkout 1a8f48a
git clone /qst1998/
cd ../pybind11
git checkout 3b1dbeb
5. 安装gst-python
cd ../gst-python
./
make
make install
6. 编译安装python-binding
cd ../../bindings/
mkdir build
cd build
cmake .. -DPYTHON_MAJOR_VERSION=3 -DPYTHON_MINOR_VERSION=8
make
pip3 install ./pyds-1.1.2-py3-none*.whl
参考:
/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/bindings