Deepstream6.0-Jetpark4.6-yolov5-v6.0-tensorRT。。。Jetback在4.6版本改动较多，对应的Deepstream也增加了python版本的插件
1. 开机后，给root⽤户设置密码:
sudo passwd root
Root⽤户下python3的版本对应的应该是3.6.9
检测python版本：
python3 –V
如果需要固定版本，将软连接指向python3.6
输⼊Python3进⼊python环境
Import tensorrt然后回车检测是否安装的有trt
tensorRT安装
系统查看
#驱动版本
head -n 1/etc/nv_tegra_release
#内核版本查看命令：uname -r
#操作系统查看命令：lsb_release -i -r
#CUDA版本查看命令：nvcc -V
#cuDNN版本查看命令：dpkg -l libcudnn8
#opencv版本查看命令：dpkg -l libopencv / pkg-config opencv --modversion
#Tensorrt版本查看：dpkg -l tensorrt
2. CUDA配置
将下载好的CUDA转移到Jetson，或者可检测以下Jetson是否内置了CUDA，⼤部分都已经是内置了只要配置⼀下环境变量即可。vim ~/.bashrc
#在最后⾯添加
export PATH=/usr/local/cuda-10.2/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export CUDA_ROOT=/usr/local/cuda
#刷新，让配置⽣效
Source ~/.bashrc
辣目洋子换源
#备份原有软件源
sudo cp /etc/apt/sources.list/etc/apt/sources.list.bak
sudo vi /etc/apt/sources.list
#清华源
deb mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic main multiverse restricted universe
deb mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-security main multiverse restricted universe
deb mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-updates main multiverse restricted universe
deb mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-backports main multiverse restricted universe
deb-src mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic main multiverse restricted universe
deb-src mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-security main multiverse restricted universe
deb-src mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-updates main multiverse restricted universe
deb-src mirrors.tuna.tsinghua.edu/ubuntu-ports/ bionic-backports main multiverse restricted universe
更新
sudo apt-get update
3. 安装pip3
sudo apt-get update
sudo apt-get install python3-pip python3-dev –y
4. 安装⼀些库和⼯具
sudo -H pip3 install jetson-stats
sudo jtop #运⾏jtop（第⼀次可能不⾏，第⼆次就好了） 按【q】退出
sudo apt-get install build-essential make cmake cmake-curses-gui -y
sudo apt-get install git g++ pkg-config curl -y
sudo apt-get install libatlas-base-dev gfortran libcanberra-gtk-module libcanberra-gtk3-module -y
sudo apt-get install libhdf5-serial-dev hdf5-tools -y
sudo apt-get install nano locate screen –y
sudo apt-get install libfreetype6-dev -y
sudo apt-get install protobuf-compiler libprotobuf-dev openssl -y
sudo apt-get install libssl-dev libcurl4-openssl-dev -y
sudo apt-get install cython3 –y
sudo apt-get install build-essential -y
去世的明星sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev -y
sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff5-dev libdc1394-22-dev -y sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev liblapacke-dev -y
sudo apt-get install libxvidcore-dev libx264-dev -y
sudo apt-get install libatlas-base-dev gfortran -y
sudo apt-get install ffmpeg -y
sudo apt-get install libopenmpi2
sudo apt-get install libopenblas-dev
sudo apt-get install libjpeg-dev zlib1g-dev
sudo apt-get install python-gi-dev
5. 安装CMake
wget /files/v3.13/cmake-3.13.
tar xpvf cmake-3.13. cmake-3.13.0/#解压
cd cmake-3.13.0/
./bootstrap --system-curl # 漫长的等待，做⼀套眼保健操...
李沁挽张若昀make -j4 #编译同样是漫长的等待...
echo 'export PATH=~/cmake-3.13.0/bin/:$PATH'>>~/.bashrc
source ~/.bashrc #更新.bashrc
6. 安装torch和tenchvision
将下载好的torch1.8 和torchvision0.9.0版本需要对应
Torch安装指令
Sudo pip3 install torch-1.8-0-cp36-cp36-m-linux_aarch64.whl
git clone --branch v0.9.0 github/pytorch/vision torchvision
cd torchvision # 进⼊到这个包的⽬录下
export BUILD_VERSION=0.9.0
sudo python3 setup.py install # 安装（估计要20分钟不⽌吧）
检测是否安装成功
python3
张冬玲资料
import torch
import torchvision
print(torch.version)
print(torchvision.version)
wanglihongexit()
7. 安装yolov5需要的包
8. 安装Deepstream-JDK，Gstreamer
安装deepstream6.0
安装Deepstream-sdk6.0版本的，或者⽀持的Jetback的版本是4.6版本，如果是Jetback其他版本的话，
检查需要是4.5或者4.5.1的版本，然后两个不同版本的代码还有轻微的区别，Deepstream6.0的版本增加了python的⼀些插件，和更改了追踪器的使⽤⽅法，具体可以阅读，英伟达的说明⽂档，接下来先说明安装Jetback4.6 + Deepstream-sdk6.0的 版本，也是⽐较新的，最近更新就在两个⽉前。JetBack 4.6 Deepstream-sdk 6.0版本
版本需求：
Jetson Xavier Nx Ubuntu 18.04
Gstreamer 1.0
CUDA = 10.2
TensorRT = 8.0.1
$ 安装相关依赖
sudo apt install libssl1.0.0 libgstreamer1.0-0 gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreame r1.0-libav libgstrtspserver-1.0-0 libjansson4 gcc make git python3
$安装librdkafka
$安装SDK
#安装 Gstreamer
sudo apt-get install libgstrtspserver-1.0-0 gstreamer1.0-rtsp
sudo apt-get install libgirepository1.0-dev
sudo apt-get install gobject-introspection gir1.2-gst-rtsp-server-1.0
sudo apt-get install libgstreamer1.0-0 gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio libssl1.0.0 libgstrtspserver-1.0-0
libjansson4你还好吗
检查是否安装成功：
dpkg -l | grep gstreamer
安装⼀下 python 接⼝：
sudo apt update
sudo apt install python3-gi python3-dev python3-gst-1.0 -y
cd /opt/nvidia/deepstream/deepstream/lib
python3 setup.py install
下载deepstream _python_apps
下载gst-python
cd /opt/nvidia/deepstream/deepstream/sources/deepstream_python_apps/3rdparty
如果遇到pip版本问题if you report an error here, please pip3 to the latest version.
python3 -m pip install --upgrade pip
这⾥python的⼀些接⼝安装完毕了可以运⾏⼀个案例进⾏测试
cd /opt/nvidia/deepstream/deepstream/sources/deepstream_python_apps/apps/deepstream-test1
python3 deepstream_test_1.py /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
接下来⽣成部署代码。
Deepstream6.0的需要⽤这个代码去⽣成engine⽂件
⾸先克隆yolov5和tensorrt项⽬
cd /opt/nvidia/deepstream/deepstream-6.0/source/deepstream-python-apps/apps/
克隆YOLOV5项⽬：git clone github/ultralytics/yolov5.git
[class-attrs-all]
pre-cluster-threshold=0.25
~
这个是配置⽂件。标黄的位置是需要动态修改的
然后执⾏测试运⾏deepstream-app –c deepstream_
运⾏会先⽣存engine ⽂件， 然后出效果。
⾃⼰的代码逻辑，需要根据⾃⼰的需求去完成
9. 风扇控制（板⼦过热会导致⽹络连接不稳定，可以⼿动开启风扇）
echo 255 > /sys/devices/pwm-fan/target_pwm #0：表⽰关闭风扇 0-255可选，
运⾏后可以通过VLC等软件进⾏播放播放⽹络串流rtsp://192.168.1.62:8554/ds-test
远程运⾏项⽬的时候会遇到
需要在~/.bashrc 的后⾯加上
从命令⾏模式切换成桌⾯模式的命令
sudo systemctl set-default graphical.target
部分安装内容来源CSDN博主，很感谢但是忘记收藏了