文章目录
1. deepstream-l4t镜像
1.1 拉取镜像
通过以下命令拉取镜像
docker pull nvcr.io/nvidia/deepstream-l4t:5.0.1-20.09-samples
l4t means Linux for Tegra
关于Base，Samples，IoT镜像的说明见https://ngc.nvidia.com/catalog/containers/nvidia:deepstream-l4t
1.2 启动镜像
docker run --gpus all --name=jetson_test --privileged --ipc=host -p 23222:22 -p 34389:3389 -itd -v /data/yzm_iavs/:/data/yzm_iavs nvcr.io/nvidia/deepstream-l4t:5.0.1-20.09-samples /bin/bash
1.3 镜像换源
通过修改/etc/apt/sources.list，可以将jetson的apt源换为国内源
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-updates main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-updates main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-backports main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-backports main restricted universe multiverse
deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-security main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-security main restricted universe multiverse
deb http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ xenial main multiverse restricted universe # for opencv
# deb https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-proposed main restricted universe multiverse
# deb-src https://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-proposed main restricted universe multiverse
2. 安装软件
2.1 软件升级
apt-get update && apt-get upgrade -y
2.2 安装gstreamer
apt-get install libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev libgstrtspserver-1.0-dev libx11-dev
2.3 安装opencv
- opencv依赖
apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
apt-get install libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libdc1394-22-dev
add-apt-repository "deb http://security.ubuntu.com/ubuntu xenial-security main"
apt-get update
apt install libjasper1 libjasper-dev
apt-get install qtbase5-dev qtdeclarative5-dev
- 配置cmake
cmake -D WITH_QT=ON \
-D WITH_CUDA=ON \
-D BUILD_TIFF=ON \
-D BUILD_TESTS=OFF \
-D BUILD_PERF_TESTS=OFF \
-D OPENCV_GENERATE_PKGCONFIG=ON \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules/ \
-D BUILD_opencv_xfeatures2d=OFF ..
- build
make -j4
make install
3. 安装TensorRT
3.1TensorRT安装参考
3.2 下载安装包
安装包链接：https://developer.nvidia.com/20.09_Jetson_CUDA-X_AI_DP_Xavier，下载后并解压。
3.3 安装cuda
dpkg -i cuda-repo-l4t-10-2-local-10.2.89_1.0-1_arm64.deb
apt-key add /var/cuda-repo-10-2-local-10.2.89/7fa2af80.pub
apt-get -y update
apt-get -y install cuda-toolkit-10-2 libgomp1 libfreeimage-dev libopenmpi-dev
3.4 安装cudnn
dpkg -i libcudnn8_8.0.2.39-1+cuda10.2_arm64.deb
dpkg -i libcudnn8-dev_8.0.2.39-1+cuda10.2_arm64.deb
dpkg -i libcudnn8-doc_8.0.2.39-1+cuda10.2_arm64.deb
3.5 安装TensorRT
dpkg -i libnvinfer7_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvinfer-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvinfer-plugin7_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvinfer-plugin-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvonnxparsers7_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvonnxparsers-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvparsers7_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvparsers-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvinfer-bin_7.2.0-1+cuda10.2_arm64.deb
dpkg -i libnvinfer-doc_7.2.0-1+cuda10.2_all.deb
dpkg -i libnvinfer-samples_7.2.0-1+cuda10.2_all.deb
dpkg -i tensorrt_7.2.0.14-1+cuda10.2_arm64.deb
dpkg -i python-libnvinfer_7.2.0-1+cuda10.2_arm64.deb
dpkg -i python-libnvinfer-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i python3-libnvinfer_7.2.0-1+cuda10.2_arm64.deb
dpkg -i python3-libnvinfer-dev_7.2.0-1+cuda10.2_arm64.deb
dpkg -i graphsurgeon-tf_7.2.0-1+cuda10.2_arm64.deb
dpkg -i uff-converter-tf_7.2.0-1+cuda10.2_arm64.deb
4. 测试安装
- 下载TensorRT demo代码
git clone https://github.com/linghu8812/tensorrt_inference.git
- 测试yolov5 demo
将yolov5的PyTorch模型转为ONNX模型后，编译并进行测试
cd tensorrt_inference/yolov5
mkdir build && cd build
cmake ..
make -j
./yolov5_trt ../config.yaml ../samples