Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
• The pipeline being used
Hello.Information about my system will be provided in my second reply downstairs, but, it seems, i know source of my problem, so i want to discuss it first.
It seems i dont have TensorRT (or ahve the wrong version).How can i check if it exists ?And how can i check NVIDIA GPU Driver Version and cuda version ?
I tried to do the commands:
sudo apt update
sudo apt dist-upgrade
sudo apt install --fix-broken -o Dpkg::Options::=“–force-overwrite”
But it didnt change anything.Full log is here : log2.txt (10.7 KB)
What did i do wrong and how can i install correct version of the Jetpack ?
Do i need to edit the etc/apt/sources.list.d/nvidia-l4t-apt-source.list ?If so, how can i find it or where can i download it?(I didnt find it on my jetson.I inserted the name of this file in the search and didnt find anything)
Hello.Sorry for the late reply.I have a problems with steps 1 and 2, so i didnt try to complete step 3.
As for the problems in step 1, these commands installed jetpack 4…6.4 (same version with the version that was already installed).So i still have jetpack 4.6.4.It seems, i need instruction for the instalaltion of the specific version of the jetpack.Or I can use very old backup as a last resort.
Also i executed this command ls -l /lib/aarch64-linux-gnu/libnvinfer.so*. This library doesnt exist.So, in my point of view, i dont have TensorRT.(Because i saw name of this library in the insturction about intallation of the TensroRT)
Sequence of my actions:
1.I followed this instruction: https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit#write
and TensorRT booted fresh jetson nano operational system
2.ls -l /lib/aarch64-linux-gnu/libnvinfer.so*
“No such file or directory”
3…ls -l /lib/aarch64-linux-gnu/libnvinfer.so
“No such file or directory”
4.sudo apt-cache show nvidia-jetpack
N: Unable to locate package nvidia-jetpack
E: No packages found
5.sudo apt update
6.sudo apt install nvidia-jetpack
7.sudo apt-cache show nvidia-jetpack
Package: nvidia-jetpack
Version: 4.6.4-b39
8.ls -l /lib/aarch64-linux-gnu/libnvinfer.so
“No such file or directory”
9…ls -l /lib/aarch64-linux-gnu/libnvinfer.so*
“No such file or directory”
In my point of view, i didnt do any mistakes during the installation process.If so, this library didnt install with default system and didnt install with JetPack 4.6.1., so i need additional instructions to install it.
(Probably i need to install TensorRT?)
Unfortunatelly i still have exactly the same problem:
deepstream-app: error while loading shared libraries: libnvinfer.so.8: cannot open shared object file: No such file or directory
Sequence of my actions:
1.I copied my edited container (based on nvcr.io/nvidia/deepstream:6.0-samples) on the fresh sd card, with JetPack 4.6.1, in which i received the same output.
2.I launched the container.
3.I tried to: deepstream-app -c deepstream_app_config_USB.txt
7.In steps 5 and 6 i pulled 2 fresh containers.In this step i launched them and .I tried to: deepstream-app -c deepstream_app_config_USB.txt. Result was exactly the same:
deepstream-app: error while loading shared libraries: libnvinfer.so.8: cannot open shared object file: No such file or directory
12.sudo cp /home/atlas/librdkafka* /opt/nvidia/deepstream/deepstream-6.0/lib
(for some reason it was installed in: /home/atlas/ instead of /usr/local/lib/)
I changed this command, because original command didnt found the file:
Original command: sudo cp /usr/local/lib/librdkafka* /opt/nvidia/deepstream/deepstream-6.0/lib
Hello.I used these commands to run new deepstream container and my deepstream container with customized settings.I got new error.(And it is the same for both of them)
cd /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test1
make CUDA_VER=10.2
./deepstream-test1-app /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
What is deepstream_app_config_USB.txt?
If the above command line can see the results
I suggest you read the documentation of deepstream-app before trying to modify the configuration file.
Please refer to the source code and README in the /opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-app directory
