Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GTX 1650
• DeepStream Version 5
• TensorRT Version 7.0.0.11
• NVIDIA GPU Driver Version (valid for GPU only) 450.51
• Issue Type( questions, new requirements, bugs) bugs
I am trying to install deepstream-5 inside a docker container. I used a container with the following specs: 10.2-cudnn7-tensorrt7-devel-ubuntu18.04 (cuda 10.2.89, nccl 2.7.8, cudnn 7.6.5.32, tensorrt 7.0.0.11)
I get this error. I don’t know how to fix it.
I tried to remove the cache as suggested in here now I have warnings beside the errors :D. I checked, and already have the two files that in the warning.
Amycao
October 13, 2020, 4:48am
3
Yes I used the devel container but I can’t find this path in it /usr/src/tensorrt/bin/
. That’s why I installed trt and nvidia-deepstream manually.
Is there a way to solve this bug in the manual installation approach?. What is it’s cause?
Thanks
Amycao
October 13, 2020, 7:35am
5
TensorRT installed by default,
root@b371c4cf76e9:~# ll /usr/lib/x86_64-linux-gnu/libnvinfer
libnvinfer.so libnvinfer.so.7.0.0 libnvinfer_plugin.so.7 libnvinfer_plugin_static.a
libnvinfer.so.7 libnvinfer_plugin.so libnvinfer_plugin.so.7.0.0 libnvinfer_static.a
the warning you see “GStreamer-WARNING: Failed to load plugin ‘…libnvdsgst_inferserver.so’: libtrtserver.so: cannot open shared object file: No such file or directory”
This is a harmless. check this,
https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream_Faq_2019/deepstream_plugin_faq.html#
Why am I getting following waring when running deepstream app for first time?
your issue is can not find libGLESv2.so.2, i used the docker as suggested, but i can find it.
root@b371c4cf76e9:~# ll /usr/lib/x86_64-linux-gnu/libGLESv2.so.2
lrwxrwxrwx 1 root root 18 May 10 2019 /usr/lib/x86_64-linux-gnu/libGLESv2.so.2 → libGLESv2.so.2.0.0
please check your environments. you may pull one clean docker and try again.
Yes I know that tensorRT is on the docker, but as I said I can’t find this path on the docker
/usr/src/tensorrt/bin/
That’s why I turned to manual installation.
I tried your ll
line and it outputs same as you, but I still have the same GLIB critical error. Why?
Amycao
October 13, 2020, 8:23am
7
Can you share output of ldd /usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_eglglessink.so
root@b371c4cf76e9:/opt/nvidia/deepstream/deepstream-5.0# ldd /usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_eglglessink.so
linux-vdso.so.1 (0x00007ffd93b0a000)
libcudart.so.10.2 => /usr/local/cuda-10.2/lib64/libcudart.so.10.2 (0x00007f0548350000)
libcuda.so.1 => /usr/lib/x86_64-linux-gnu/libcuda.so.1 (0x00007f0546eb2000)
libGLESv2.so.2 => /usr/lib/x86_64-linux-gnu/libGLESv2.so.2 (0x00007f0546ca0000)
libEGL.so.1 => /usr/lib/x86_64-linux-gnu/libEGL.so.1 (0x00007f0546a8c000)
libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007f0546754000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f05463b6000)
libgstreamer-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstreamer-1.0.so.0 (0x00007f054607b000)
libgstbase-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstbase-1.0.so.0 (0x00007f0545e06000)
libgstvideo-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstvideo-1.0.so.0 (0x00007f0545b6d000)
libglib-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libglib-2.0.so.0 (0x00007f0545856000)
libgobject-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libgobject-2.0.so.0 (0x00007f0545602000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f0545211000)
/lib64/ld-linux-x86-64.so.2 (0x00007f05487ed000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f054500d000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f0544dee000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f0544be6000)
libGLdispatch.so.0 => /usr/lib/x86_64-linux-gnu/libGLdispatch.so.0 (0x00007f0544930000)
libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007f0544708000)
libgmodule-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libgmodule-2.0.so.0 (0x00007f0544504000)
liborc-0.4.so.0 => /usr/lib/x86_64-linux-gnu/liborc-0.4.so.0 (0x00007f0544288000)
libpcre.so.3 => /lib/x86_64-linux-gnu/libpcre.so.3 (0x00007f0544016000)
libffi.so.6 => /usr/lib/x86_64-linux-gnu/libffi.so.6 (0x00007f0543e0e000)
libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007f0543c0a000)
libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007f0543a04000)
libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 (0x00007f05437ef000)
Thank you so much for your help :-)
root@0bda866f2d9c:/home/fadwa/workspace/model_conversion# ldd /usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_eglglessink.so
linux-vdso.so.1 (0x00007fff800ef000)
libcudart.so.10.2 => /usr/local/cuda-10.2/lib64/libcudart.so.10.2 (0x00007f7366001000)
libcuda.so.1 => /usr/lib/x86_64-linux-gnu/libcuda.so.1 (0x00007f7364b4e000)
libGLESv2.so.2 => /usr/lib/x86_64-linux-gnu/libGLESv2.so.2 (0x00007f736493c000)
libEGL.so.1 => /usr/lib/x86_64-linux-gnu/libEGL.so.1 (0x00007f7364728000)
libX11.so.6 => /usr/lib/x86_64-linux-gnu/libX11.so.6 (0x00007f73643f0000)
libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f7364052000)
libgstreamer-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstreamer-1.0.so.0 (0x00007f7363d17000)
libgstbase-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstbase-1.0.so.0 (0x00007f7363aa2000)
libgstvideo-1.0.so.0 => /usr/lib/x86_64-linux-gnu/libgstvideo-1.0.so.0 (0x00007f7363809000)
libglib-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libglib-2.0.so.0 (0x00007f73634f2000)
libgobject-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libgobject-2.0.so.0 (0x00007f736329e000)
libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f7362ead000)
/lib64/ld-linux-x86-64.so.2 (0x00007f736649e000)
libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f7362ca9000)
libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f7362a8a000)
librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f7362882000)
libGLdispatch.so.0 => /usr/lib/x86_64-linux-gnu/libGLdispatch.so.0 (0x00007f73625cc000)
libxcb.so.1 => /usr/lib/x86_64-linux-gnu/libxcb.so.1 (0x00007f73623a4000)
libgmodule-2.0.so.0 => /usr/lib/x86_64-linux-gnu/libgmodule-2.0.so.0 (0x00007f73621a0000)
liborc-0.4.so.0 => /usr/lib/x86_64-linux-gnu/liborc-0.4.so.0 (0x00007f7361f24000)
libpcre.so.3 => /lib/x86_64-linux-gnu/libpcre.so.3 (0x00007f7361cb2000)
libffi.so.6 => /usr/lib/x86_64-linux-gnu/libffi.so.6 (0x00007f7361aaa000)
libXau.so.6 => /usr/lib/x86_64-linux-gnu/libXau.so.6 (0x00007f73618a6000)
libXdmcp.so.6 => /usr/lib/x86_64-linux-gnu/libXdmcp.so.6 (0x00007f73616a0000)
libbsd.so.0 => /lib/x86_64-linux-gnu/libbsd.so.0 (0x00007f736148b000)
Amycao
October 20, 2020, 8:36am
11
Did you still get the element create fail error?
Amycao
October 21, 2020, 1:27pm
13
Can you get one clean docker and try again? i do not have these issues using docker .
fadwa.fawzy:
Yes I used the devel container but I can’t find this path in it /usr/src/tensorrt/bin/
. That’s why I installed trt and nvidia-deepstream manually.
Is there a way to solve this bug in the manual installation approach?. What is it’s cause?
Yes I used the devel container but I can’t find this path in it /usr/src/tensorrt/bin/
. That’s why I installed trt and nvidia-deepstream manually.
Is there a way to solve this bug in the manual installation approach?. What is it’s cause?
Amycao
October 30, 2020, 1:35am
16
You can not find the path /usr/src/tensorrt/bin/ in devel docker?
which docker you are using?
Amycao
November 3, 2020, 6:40am
18
If you need tensorrt source samples, you need to install it by yourself.
but your error is not related to tensorrt samples.
My error is when I install deep-stream manually
Amycao
November 3, 2020, 10:05am
20
if you use devel docker, you do not need to install deepstream manually. it’s installed by default.
I am feeling that we are running in circles here. Please take a look at the thread from the beginning to get a better understanding about my issue.
Amycao
November 5, 2020, 2:46am
22
As stated before, please try clean docker, you will not meet the error “can not create render bin”, but you also raised another issue as you said you can not find the path /usr/src/tensorrt/bin, please see comment 17
Yes I used a clean docker and it was working fine. Now I have this error when installing manually. Please help.
Amycao
November 6, 2020, 1:51pm
24
download the same version as used in the docker from nvidia TensorRT download center, remove the trt package from the docker, reinstall using the package you downloaded.