Linux 35.6 + JetPack v5.1.4@DeepStream安装
Linux 35.6 + JetPack v5.1.4@DeepStream安装
- 1. 源由
- 2. C/C++环境
- Step 1 安装Jetpack 5.1.4 L4T 35.6
- Step 2 安装依赖组件
- Step 3 安装librdkafka
- Step 4 安装 DeepStream SDK
- Step 5 测试 deepstream-app
- Step 6 运行 deepstream-app
- 3. Python环境
- Step 1 获取 deepstream_python版本
- Step 2 安装依赖环境
- Step 3 安装Gst-python
- Step 4 构建Python绑定whl文件
- Step 5 安装 pyds-1.1.8
- 4. 总结
- 4.1 版本问题
- 4.2 二进制help
- 5. 参考资料
1. 源由
为了确保在Jetson Orin平台上继续我们追求的 FPV Geek SDK 推进;奠定一些基础技术的经验和基础;
- Ardupilot开源无人机之Geek SDK讨论
- Ardupilot & OpenIPC & 基于WFB-NG构架分析和数据链路思考
- ArduPilot开源飞控之MAVProxy深入研读系列 - 2蜂群链路
目前,在Jetson Orin 8GB的板子上 jetson-fpv 性能不佳的情况,着实令人着急,呵呵!
2. C/C++环境
Step 1 安装Jetpack 5.1.4 L4T 35.6
参考:《Linux 36.3@Jetson Orin Nano之系统安装》
Step 2 安装依赖组件
$ sudo apt install \
libssl1.1 \
libgstreamer1.0-0 \
gstreamer1.0-tools \
gstreamer1.0-plugins-good \
gstreamer1.0-plugins-bad \
gstreamer1.0-plugins-ugly \
gstreamer1.0-libav \
libgstreamer-plugins-base1.0-dev \
libgstrtspserver-1.0-0 \
libjansson4 \
libyaml-cpp-dev
Step 3 安装librdkafka
- Clone the librdkafka repository from GitHub:
$ git clone https://github.com/edenhill/librdkafka.git
或者
git clone git@github.com:confluentinc/librdkafka.git
- Configure and build the library:
$ cd librdkafka
$ git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a
$ ./configure
$ make
$ sudo make install
- Copy the generated libraries to the deepstream directory:
$ sudo mkdir -p /opt/nvidia/deepstream/deepstream-6.3/lib
$ sudo cp /usr/local/lib/librdkafka* /opt/nvidia/deepstream/deepstream-6.3/lib
$ ls /opt/nvidia/deepstream/deepstream-6.3/lib
librdkafka++.a librdkafka.a librdkafka++.so librdkafka.so librdkafka++.so.1 librdkafka.so.1
Step 4 安装 DeepStream SDK
- Download DS SDK
$ wget --content-disposition 'https://api.ngc.nvidia.com/v2/resources/org/nvidia/deepstream/6.3/files?redirect=true&path=deepstream_sdk_v6.3.0_jetson.tbz2' -O deepstream_sdk_v6.3.0_jetson.tbz2
或者,通过网页下载:DeepStream SDK
- Install DS SDK
$ sudo tar -xvf deepstream_sdk_v6.3.0_jetson.tbz2 -C /
$ cd /opt/nvidia/deepstream/deepstream-6.3
$ sudo ./install.sh
$ sudo ldconfig
Step 5 测试 deepstream-app
$ ldd /usr/bin/deepstream-applinux-vdso.so.1 (0x0000ffff9420b000)libgstreamer-1.0.so.0 => /lib/aarch64-linux-gnu/libgstreamer-1.0.so.0 (0x0000ffff93f2f000)libgstvideo-1.0.so.0 => /lib/aarch64-linux-gnu/libgstvideo-1.0.so.0 (0x0000ffff93e7a000)libglib-2.0.so.0 => /lib/aarch64-linux-gnu/libglib-2.0.so.0 (0x0000ffff93d3f000)libgobject-2.0.so.0 => /lib/aarch64-linux-gnu/libgobject-2.0.so.0 (0x0000ffff93ccd000)libgstrtspserver-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtspserver-1.0.so.0 (0x0000ffff93c5a000)libjson-glib-1.0.so.0 => /lib/aarch64-linux-gnu/libjson-glib-1.0.so.0 (0x0000ffff93c21000)libyaml-cpp.so.0.6 => /lib/aarch64-linux-gnu/libyaml-cpp.so.0.6 (0x0000ffff93bc1000)libnvdsgst_meta.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvdsgst_meta.so (0x0000ffff93bab000)libnvdsgst_smartrecord.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvdsgst_smartrecord.so (0x0000ffff93b94000)libnvdsgst_helper.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvdsgst_helper.so (0x0000ffff93b7c000)libnvdsgst_customhelper.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvdsgst_customhelper.so (0x0000ffff93b63000)libnvds_meta.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvds_meta.so (0x0000ffff93b4c000)libnvds_utils.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvds_utils.so (0x0000ffff93542000)libnvds_msgbroker.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvds_msgbroker.so (0x0000ffff93528000)libX11.so.6 => /lib/aarch64-linux-gnu/libX11.so.6 (0x0000ffff933e3000)libdl.so.2 => /lib/aarch64-linux-gnu/libdl.so.2 (0x0000ffff933cf000)libstdc++.so.6 => /lib/aarch64-linux-gnu/libstdc++.so.6 (0x0000ffff931ea000)libpthread.so.0 => /lib/aarch64-linux-gnu/libpthread.so.0 (0x0000ffff931b9000)librt.so.1 => /lib/aarch64-linux-gnu/librt.so.1 (0x0000ffff931a1000)libm.so.6 => /lib/aarch64-linux-gnu/libm.so.6 (0x0000ffff930f6000)libc.so.6 => /lib/aarch64-linux-gnu/libc.so.6 (0x0000ffff92f83000)/lib/ld-linux-aarch64.so.1 (0x0000ffff941db000)libgcc_s.so.1 => /lib/aarch64-linux-gnu/libgcc_s.so.1 (0x0000ffff92f5f000)libgmodule-2.0.so.0 => /lib/aarch64-linux-gnu/libgmodule-2.0.so.0 (0x0000ffff92f4b000)libgstbase-1.0.so.0 => /lib/aarch64-linux-gnu/libgstbase-1.0.so.0 (0x0000ffff92ec6000)liborc-0.4.so.0 => /lib/aarch64-linux-gnu/liborc-0.4.so.0 (0x0000ffff92e37000)libpcre.so.3 => /lib/aarch64-linux-gnu/libpcre.so.3 (0x0000ffff92dc5000)libffi.so.7 => /lib/aarch64-linux-gnu/libffi.so.7 (0x0000ffff92dac000)libgstnet-1.0.so.0 => /lib/aarch64-linux-gnu/libgstnet-1.0.so.0 (0x0000ffff92d85000)libgstrtp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtp-1.0.so.0 (0x0000ffff92d4f000)libgstrtsp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtsp-1.0.so.0 (0x0000ffff92d1a000)libgstsdp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstsdp-1.0.so.0 (0x0000ffff92cf1000)libgstapp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstapp-1.0.so.0 (0x0000ffff92cd1000)libgio-2.0.so.0 => /lib/aarch64-linux-gnu/libgio-2.0.so.0 (0x0000ffff92ad4000)libgstpbutils-1.0.so.0 => /lib/aarch64-linux-gnu/libgstpbutils-1.0.so.0 (0x0000ffff92a86000)libnvinfer.so.8 => /lib/aarch64-linux-gnu/libnvinfer.so.8 (0x0000ffff8592d000)libnvds_logger.so => /opt/nvidia/deepstream/deepstream-6.3/lib/libnvds_logger.so (0x0000ffff8591b000)libxcb.so.1 => /lib/aarch64-linux-gnu/libxcb.so.1 (0x0000ffff858e4000)libz.so.1 => /lib/aarch64-linux-gnu/libz.so.1 (0x0000ffff858b8000)libmount.so.1 => /lib/aarch64-linux-gnu/libmount.so.1 (0x0000ffff8584a000)libselinux.so.1 => /lib/aarch64-linux-gnu/libselinux.so.1 (0x0000ffff85812000)libresolv.so.2 => /lib/aarch64-linux-gnu/libresolv.so.2 (0x0000ffff857ec000)libgstaudio-1.0.so.0 => /lib/aarch64-linux-gnu/libgstaudio-1.0.so.0 (0x0000ffff85768000)libgsttag-1.0.so.0 => /lib/aarch64-linux-gnu/libgsttag-1.0.so.0 (0x0000ffff8571b000)libnvdla_compiler.so => /usr/lib/aarch64-linux-gnu/tegra/libnvdla_compiler.so (0x0000ffff84fe0000)libcudla.so.1 => /usr/local/cuda/targets/aarch64-linux/lib/libcudla.so.1 (0x0000ffff84fa3000)libXau.so.6 => /lib/aarch64-linux-gnu/libXau.so.6 (0x0000ffff84f8f000)libXdmcp.so.6 => /lib/aarch64-linux-gnu/libXdmcp.so.6 (0x0000ffff84f79000)libblkid.so.1 => /lib/aarch64-linux-gnu/libblkid.so.1 (0x0000ffff84f13000)libpcre2-8.so.0 => /lib/aarch64-linux-gnu/libpcre2-8.so.0 (0x0000ffff84e83000)libnvos.so => /usr/lib/aarch64-linux-gnu/tegra/libnvos.so (0x0000ffff84e63000)libnvdla_runtime.so => /usr/lib/aarch64-linux-gnu/tegra/libnvdla_runtime.so (0x0000ffff8480b000)libcuda.so.1 => /usr/lib/aarch64-linux-gnu/tegra/libcuda.so.1 (0x0000ffff831b4000)libbsd.so.0 => /lib/aarch64-linux-gnu/libbsd.so.0 (0x0000ffff8318d000)libnvrm_host1x.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_host1x.so (0x0000ffff8316a000)libnvrm_mem.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_mem.so (0x0000ffff83152000)libnvsocsys.so => /usr/lib/aarch64-linux-gnu/tegra/libnvsocsys.so (0x0000ffff8313e000)libnvrm_gpu.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_gpu.so (0x0000ffff830d1000)libnvrm_sync.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_sync.so (0x0000ffff830ba000)libnvrm_chip.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_chip.so (0x0000ffff830a4000)libnvsciipc.so => /usr/lib/aarch64-linux-gnu/tegra/libnvsciipc.so (0x0000ffff8307f000)
Step 6 运行 deepstream-app
$ cd /opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/
$ deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml
3. Python环境
首先,确保C/C++环境安装成功!
Step 1 获取 deepstream_python版本
$ cd /opt/nvidia/deepstream/deepstream-6.3/
$ sudo chown <user>:<user> sources -R
$ cd sources
$ git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps.git
$ git fetch --tag
$ git checkout v1.1.8
Step 2 安装依赖环境
$ sudo apt install python3-gi python3-dev python3-gst-1.0 python-gi-dev git \python3 python3-pip python3.8-dev cmake g++ build-essential libglib2.0-dev \libglib2.0-dev-bin libgstreamer1.0-dev libtool m4 autoconf automake libgirepository1.0-dev libcairo2-dev
$ sudo apt-get install -y apt-transport-https ca-certificates -y
$ sudo apt-get install update-ca-certificates
Step 3 安装Gst-python
$ cd 3rdparty/gst-python/
$ ./autogen.sh
$ make
$ sudo make install
Step 4 构建Python绑定whl文件
$ cd deepstream_python_apps/bindings
$ mkdir build
$ cd build
$ cmake .. -DPYTHON_MAJOR_VERSION=3 -DPYTHON_MINOR_VERSION=8 -DPIP_PLATFORM=linux_aarch64 -DDS_PATH=/opt/nvidia/deepstream/deepstrea
$ make -j$(nproc)
Step 5 安装 pyds-1.1.8
$ sudo pip install ./pyds-1.1.8-py3-none-linux_aarch64.whl
Processing ./pyds-1.1.8-py3-none-linux_aarch64.whl
Collecting pgiDownloading pgi-0.0.11.2.tar.gz (239 kB)|████████████████████████████████| 239 kB 27 kB/s
Requirement already satisfied: PyGObject in /usr/lib/python3/dist-packages (from pyds==1.1.8) (3.36.0)
Requirement already satisfied: pycairo>=1.11.1 in /usr/lib/python3/dist-packages (from PyGObject->pyds==1.1.8) (1.16.2)
Building wheels for collected packages: pgiBuilding wheel for pgi (setup.py) ... doneCreated wheel for pgi: filename=pgi-0.0.11.2-py3-none-any.whl size=181783 sha256=09607e9ec5495cad5fc8cf827e22861ddc83ea2b4fbe64d1697d9888c28bed3eStored in directory: /root/.cache/pip/wheels/17/ee/39/e8766b9714c8a5534fa309b8b2a64f358196d8b951e573a153
Successfully built pgi
Installing collected packages: pgi, pyds
Successfully installed pgi-0.0.11.2 pyds-1.1.8
4. 总结
NVIDIA提供的硬件及其相关库,原厂维护,不开源。应用相关示例代码开源或者提供源代码。
因此,在安装这些性能加速软件时,尤其要注意其版本的对应关系。
若需要进行大型开发,必须关注原厂开发动态以及版本支持情况。进而,公司软件在规划时需要充分考虑进度、里程碑等相应适配。
- Which DS version for Jetson Orin Nano/Jetpack 5.1.4/L4T 35.6.0?
版本信息获取方式:
$ cat /opt/nvidia/deepstream/deepstream/version
Version: 6.3
GCID: 33782405
EABI:
DATE: Wed Jul 12 18:29:21 UTC 2023
4.1 版本问题
- Download DS SDK 6.4.0
$ wget --content-disposition 'https://api.ngc.nvidia.com/v2/resources/org/nvidia/deepstream/6.4/files?redirect=true&path=deepstream_sdk_v6.4.0_jetson.tbz2' -O deepstream_sdk_v6.4.0_jetson.tbz2
或者,通过网页下载:DeepStream SDK
- Install DS SDK 6.4.0
$ sudo tar -xvf deepstream_sdk_v6.4.0_jetson.tbz2 -C /
$ cd /opt/nvidia/deepstream/deepstream-6.4
$ sudo ./install.sh
$ sudo ldconfig
- ldd deepstream-app
出现so文件不存在等问题,基本都是链接环节出现的,也就是二进制在编译链接的路径或者库版本不一致的问题。
daniel@daniel-nvidia:~/Work$ ldd /usr/bin/deepstream-app
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libstdc++.so.6: version `GLIBCXX_3.4.29' not found (required by /usr/bin/deepstream-app)
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found (required by /usr/bin/deepstream-app)
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libc.so.6: version `GLIBC_2.34' not found (required by /usr/bin/deepstream-app)
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libc.so.6: version `GLIBC_2.34' not found (required by /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_utils.so)
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libstdc++.so.6: version `GLIBCXX_3.4.29' not found (required by /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_msgbroker.so)
/usr/bin/deepstream-app: /lib/aarch64-linux-gnu/libc.so.6: version `GLIBC_2.34' not found (required by /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_msgbroker.so)linux-vdso.so.1 (0x0000ffffa8400000)libgstreamer-1.0.so.0 => /lib/aarch64-linux-gnu/libgstreamer-1.0.so.0 (0x0000ffffa80f1000)libgstvideo-1.0.so.0 => /lib/aarch64-linux-gnu/libgstvideo-1.0.so.0 (0x0000ffffa803c000)libglib-2.0.so.0 => /lib/aarch64-linux-gnu/libglib-2.0.so.0 (0x0000ffffa7f01000)libgobject-2.0.so.0 => /lib/aarch64-linux-gnu/libgobject-2.0.so.0 (0x0000ffffa7e8f000)libgstrtspserver-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtspserver-1.0.so.0 (0x0000ffffa7e1c000)libjson-glib-1.0.so.0 => /lib/aarch64-linux-gnu/libjson-glib-1.0.so.0 (0x0000ffffa7de3000)libyaml-cpp.so.0.7 => not foundlibnvdsgst_meta.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvdsgst_meta.so (0x0000ffffa7dcd000)libnvdsgst_smartrecord.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvdsgst_smartrecord.so (0x0000ffffa7db6000)libnvdsgst_helper.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvdsgst_helper.so (0x0000ffffa7d9d000)libnvdsgst_customhelper.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvdsgst_customhelper.so (0x0000ffffa7d83000)libnvds_meta.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_meta.so (0x0000ffffa7d6b000)libnvds_utils.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_utils.so (0x0000ffffa749a000)libnvds_msgbroker.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_msgbroker.so (0x0000ffffa747f000)libX11.so.6 => /lib/aarch64-linux-gnu/libX11.so.6 (0x0000ffffa733a000)libstdc++.so.6 => /lib/aarch64-linux-gnu/libstdc++.so.6 (0x0000ffffa7155000)libm.so.6 => /lib/aarch64-linux-gnu/libm.so.6 (0x0000ffffa70aa000)libc.so.6 => /lib/aarch64-linux-gnu/libc.so.6 (0x0000ffffa6f37000)/lib/ld-linux-aarch64.so.1 (0x0000ffffa83d0000)libgcc_s.so.1 => /lib/aarch64-linux-gnu/libgcc_s.so.1 (0x0000ffffa6f13000)libgmodule-2.0.so.0 => /lib/aarch64-linux-gnu/libgmodule-2.0.so.0 (0x0000ffffa6eff000)libdl.so.2 => /lib/aarch64-linux-gnu/libdl.so.2 (0x0000ffffa6eeb000)libpthread.so.0 => /lib/aarch64-linux-gnu/libpthread.so.0 (0x0000ffffa6eba000)libgstbase-1.0.so.0 => /lib/aarch64-linux-gnu/libgstbase-1.0.so.0 (0x0000ffffa6e35000)liborc-0.4.so.0 => /lib/aarch64-linux-gnu/liborc-0.4.so.0 (0x0000ffffa6da6000)libpcre.so.3 => /lib/aarch64-linux-gnu/libpcre.so.3 (0x0000ffffa6d34000)libffi.so.7 => /lib/aarch64-linux-gnu/libffi.so.7 (0x0000ffffa6d1b000)libgstnet-1.0.so.0 => /lib/aarch64-linux-gnu/libgstnet-1.0.so.0 (0x0000ffffa6cf4000)libgstrtp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtp-1.0.so.0 (0x0000ffffa6cbe000)libgstrtsp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstrtsp-1.0.so.0 (0x0000ffffa6c89000)libgstsdp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstsdp-1.0.so.0 (0x0000ffffa6c60000)libgstapp-1.0.so.0 => /lib/aarch64-linux-gnu/libgstapp-1.0.so.0 (0x0000ffffa6c40000)libgio-2.0.so.0 => /lib/aarch64-linux-gnu/libgio-2.0.so.0 (0x0000ffffa6a43000)libgstpbutils-1.0.so.0 => /lib/aarch64-linux-gnu/libgstpbutils-1.0.so.0 (0x0000ffffa69f7000)libnvinfer.so.8 => /lib/aarch64-linux-gnu/libnvinfer.so.8 (0x0000ffff9989c000)libnvds_logger.so => /opt/nvidia/deepstream/deepstream-6.4/lib/libnvds_logger.so (0x0000ffff9988a000)libxcb.so.1 => /lib/aarch64-linux-gnu/libxcb.so.1 (0x0000ffff99853000)libz.so.1 => /lib/aarch64-linux-gnu/libz.so.1 (0x0000ffff99829000)libmount.so.1 => /lib/aarch64-linux-gnu/libmount.so.1 (0x0000ffff997b9000)libselinux.so.1 => /lib/aarch64-linux-gnu/libselinux.so.1 (0x0000ffff99781000)libresolv.so.2 => /lib/aarch64-linux-gnu/libresolv.so.2 (0x0000ffff9975b000)libgstaudio-1.0.so.0 => /lib/aarch64-linux-gnu/libgstaudio-1.0.so.0 (0x0000ffff996d7000)libgsttag-1.0.so.0 => /lib/aarch64-linux-gnu/libgsttag-1.0.so.0 (0x0000ffff9968c000)librt.so.1 => /lib/aarch64-linux-gnu/librt.so.1 (0x0000ffff99672000)libnvdla_compiler.so => /usr/lib/aarch64-linux-gnu/tegra/libnvdla_compiler.so (0x0000ffff98f37000)libcudla.so.1 => /usr/local/cuda/targets/aarch64-linux/lib/libcudla.so.1 (0x0000ffff98efa000)libXau.so.6 => /lib/aarch64-linux-gnu/libXau.so.6 (0x0000ffff98ee6000)libXdmcp.so.6 => /lib/aarch64-linux-gnu/libXdmcp.so.6 (0x0000ffff98ed0000)libblkid.so.1 => /lib/aarch64-linux-gnu/libblkid.so.1 (0x0000ffff98e68000)libpcre2-8.so.0 => /lib/aarch64-linux-gnu/libpcre2-8.so.0 (0x0000ffff98dda000)libnvos.so => /usr/lib/aarch64-linux-gnu/tegra/libnvos.so (0x0000ffff98dba000)libnvdla_runtime.so => /usr/lib/aarch64-linux-gnu/tegra/libnvdla_runtime.so (0x0000ffff98762000)libcuda.so.1 => /usr/lib/aarch64-linux-gnu/tegra/libcuda.so.1 (0x0000ffff9710b000)libbsd.so.0 => /lib/aarch64-linux-gnu/libbsd.so.0 (0x0000ffff970e2000)libnvrm_host1x.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_host1x.so (0x0000ffff970c1000)libnvrm_mem.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_mem.so (0x0000ffff970a9000)libnvsocsys.so => /usr/lib/aarch64-linux-gnu/tegra/libnvsocsys.so (0x0000ffff97095000)libnvrm_gpu.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_gpu.so (0x0000ffff97028000)libnvrm_sync.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_sync.so (0x0000ffff9700f000)libnvrm_chip.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_chip.so (0x0000ffff96ffb000)libnvsciipc.so => /usr/lib/aarch64-linux-gnu/tegra/libnvsciipc.so (0x0000ffff96fd6000)
检查本地依赖库的当前情况:glibc版本不对,
- GLIBC_2.34 or GLIBC_2.32 //存在,版本不对
- GLIBCXX_3.4.29 //存在,版本不对
- libyaml-cpp.so //存在,版本不对
$ whereis libyaml-cpp
libyaml-cpp: /usr/lib/aarch64-linux-gnu/libyaml-cpp.so /usr/lib/aarch64-linux-gnu/libyaml-cpp.a$ whereis libc.so
libc: /usr/lib/aarch64-linux-gnu/libc.a /usr/lib/aarch64-linux-gnu/libc.so$ strings /lib/aarch64-linux-gnu/libstdc++.so.6 | grep GLIBCXX
GLIBCXX_3.4
GLIBCXX_3.4.1
GLIBCXX_3.4.2
GLIBCXX_3.4.3
GLIBCXX_3.4.4
GLIBCXX_3.4.5
GLIBCXX_3.4.6
GLIBCXX_3.4.7
GLIBCXX_3.4.8
GLIBCXX_3.4.9
GLIBCXX_3.4.10
GLIBCXX_3.4.11
GLIBCXX_3.4.12
GLIBCXX_3.4.13
GLIBCXX_3.4.14
GLIBCXX_3.4.15
GLIBCXX_3.4.16
GLIBCXX_3.4.17
GLIBCXX_3.4.18
GLIBCXX_3.4.19
GLIBCXX_3.4.20
GLIBCXX_3.4.21
GLIBCXX_3.4.22
GLIBCXX_3.4.23
GLIBCXX_3.4.24
GLIBCXX_3.4.25
GLIBCXX_3.4.26
GLIBCXX_3.4.27
GLIBCXX_3.4.28
GLIBCXX_DEBUG_MESSAGE_LENGTH
4.2 二进制help
本能的认为“-i 输入文件”;“-c 配置文件”。实际存在两个问题:
- 示例代码
deepstream-app
代码hardcoded
一个txt文件 - 这个txt文件若存在,会导入这个配置文件里面的视频文件
$ deepstream-app --help
Usage:deepstream-app [OPTION?] Nvidia DeepStream DemoHelp Options:-h, --help Show help options--help-all Show all help options--help-gst Show GStreamer OptionsApplication Options:-v, --version Print DeepStreamSDK version-t, --tiledtext Display Bounding box labels in tiled mode--version-all Print DeepStreamSDK and dependencies version-c, --cfg-file Set the config file-i, --input-uri Set the input uri (file://stream or rtsp://stream)
5. 参考资料
【1】DeepStream SDK
【2】DeepStream 6.3 Quick Start