deepstream6.0 python环境安装

deepstream6.0 python环境安装 1.下载docker镜像

在官方网址可以选择可以选择合适的版本：https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_docker_containers.html

docker pull nvcr.io/nvidia/deepstream:6.0-triton

2.启动容器

nvidia-docker run --shm-size=12g --ulimit memlock=-1 --ulimit stack=67108864 -it --name ds-demo nvcr.io/nvidia/deepstream:6.0-triton

3.安装库

apt-get update
apt install -y 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

这个镜像默认python版本3.8。

4.克隆python示例项目及子项目

cd /opt/nvidia/deepstream/deepstream-6.0/sources
export GIT_SSL_NO_VERIFY=true 
git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps.git
cd deepstream_python_apps
git submodule update --init

如果克隆慢，手动用cnpmjs.org镜像下载

cd /opt/nvidia/deepstream/deepstream-6.0/sources
export GIT_SSL_NO_VERIFY=true 
git clone https://github.com.cnpmjs.org/NVIDIA-AI-IOT/deepstream_python_apps.git
cd deepstream_python_apps/3rdparty
rm -rf *
git clone https://github.com.cnpmjs.org/GStreamer/gst-python.git
git clone https://github.com.cnpmjs.org/pybind/pybind11.git

5. 安装gst-python

cd gst-python
git checkout 1a8f48a
./autogen.sh
make
make install

6. 编译安装python-binding

cd /opt/nvidia/deepstream/deepstream-6.0/sources/deepstream_python_apps/bindings
mkdir build
cd build
cmake ..  -DPYTHON_MAJOR_VERSION=3 -DPYTHON_MINOR_VERSION=8
make
pip3 install ./pyds-1.1.0-py3-none*.whl

这里注意python的版本是3.8

参考：https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/blob/master/bindings/README.md