Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU AWS instance g4dn.xlarge
• DeepStream Version
5.1
• TensorRT Version
Installed according to the manual *
TensorRT 7.2.0.14rc for Ubuntu 1804 and CUDA 11.0 DEB local repo package
• NVIDIA GPU Driver Version (valid for GPU only)
Install NVIDIA driver 460.32
• Issue Type( questions, new requirements, bugs)
question
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
I am trying to install the deepstream on AWS instances on os Ubuntu x86_64 version 18.04 and instance type g4dn.xlarge. I am getting the following error
sudo apt-get install ./deepstream-5.1_5.1.0-1_amd64.deb
Reading package lists... Done
Building dependency tree
Reading state information... Done
Note, selecting 'deepstream-5.1' instead of './deepstream-5.1_5.1.0-1_amd64.deb'
Some packages could not be installed. This may mean that you have
requested an impossible situation or if you are using the unstable
distribution that some required packages have not yet been created
or been moved out of Incoming.
The following information may help to resolve the situation:
The following packages have unmet dependencies:
deepstream-5.1 : Depends: libnvinfer7 (>= 7.2.1) but it is not going to be installed
Depends: libnvparsers7 (>= 7.2.1) but it is not going to be installed
Depends: libnvonnxparsers7 (>= 7.2.1) but it is not going to be installed
Depends: libnvinfer-plugin7 (>= 7.2.1) but it is not going to be installed
E: Unable to correct problems, you have held broken packages.
I checked the Cuda version :
dpkg-query -W | grep cuda
cuda 11.4.2-1
cuda-11-4 11.4.2-1
cuda-cccl-11-4 11.4.122-1
cuda-command-line-tools-11-4 11.4.2-1
cuda-compiler-11-4 11.4.2-1
cuda-cudart-11-4 11.4.108-1
cuda-cudart-dev-11-4 11.4.108-1
cuda-cuobjdump-11-4 11.4.120-1
cuda-cupti-11-4 11.4.120-1
cuda-cupti-dev-11-4 11.4.120-1
cuda-cuxxfilt-11-4 11.4.120-1
cuda-demo-suite-11-4 11.4.100-1
cuda-documentation-11-4 11.4.126-1
cuda-driver-dev-11-4 11.4.108-1
cuda-drivers 470.57.02-1
cuda-drivers-470 470.57.02-1
cuda-gdb-11-4 11.4.120-1
cuda-libraries-11-4 11.4.2-1
cuda-libraries-dev-11-4 11.4.2-1
cuda-memcheck-11-4 11.4.120-1
cuda-nsight-11-4 11.4.120-1
cuda-nsight-compute-11-4 11.4.2-1
cuda-nsight-systems-11-4 11.4.2-1
cuda-nvcc-11-4 11.4.120-1
cuda-nvdisasm-11-4 11.4.120-1
cuda-nvml-dev-11-4 11.4.120-1
cuda-nvprof-11-4 11.4.120-1
cuda-nvprune-11-4 11.4.120-1
cuda-nvrtc-11-4 11.4.120-1
cuda-nvrtc-dev-11-4 11.4.120-1
cuda-nvtx-11-4 11.4.120-1
cuda-nvvp-11-4 11.4.120-1
cuda-runtime-11-4 11.4.2-1
cuda-samples-11-4 11.4.120-1
cuda-sanitizer-11-4 11.4.120-1
cuda-toolkit-11-4 11.4.2-1
cuda-toolkit-11-4-config-common 11.4.108-1
cuda-toolkit-11-config-common 11.4.108-1
cuda-toolkit-config-common 11.4.108-1
cuda-tools-11-4 11.4.2-1
cuda-visual-tools-11-4 11.4.2-1
nv-tensorrt-repo-ubuntu1804-cuda11.0-trt7.2.0.14-rc-20200901 1-1
ubuntu@ip-10-0-0-78:~$ apt-cache show python3-libnvinfer-dev python3-libnvinfer
Package: python3-libnvinfer-dev
Version: 8.0.3-1+cuda11.3
Architecture: amd64
Priority: optional
Section: multiverse/devel
Source: tensorrt
Maintainer: cudatools <cudatools@nvidia.com>
Installed-Size: 10
Depends: python3-libnvinfer (= 8.0.3-1+cuda11.3), libnvinfer-dev (= 8.0.3-1+cuda11.3), libnvinfer-plugin-dev (= 8.0.3-1+cuda11.3), libnvparsers-dev (= 8.0.3-1+cuda11.3), libnvonnxparsers-dev (= 8.0.3-1+cuda11.3)
Filename: ./python3-libnvinfer-dev_8.0.3-1+cuda11.3_amd64.deb
Size: 3612
MD5sum: 3849d47c054da76d2e83f99d4f6a10e4
SHA1: dbb2e5b9f7ad14f2f961bc01bb7c463a73b556b8
SHA256: 42ac181519fb1581970c700e123128d04696a453afd8aceb14cfba064d294280
SHA512: 3e0cb95156080c81a3c4ee877f2f3c4d5893f87f07b77ac615d5d60778dd93271afbf072fe35294264395c8784b8abfe2ed48daacfe3016d7e3ca2f878e7cae6
Description: Python 3 development package for TensorRT
Python 3 development package for TensorRT.
Description-md5: 858edc4abbfaf2883142085c85b93202
Package: python3-libnvinfer-dev
Version: 8.0.3-1+cuda10.2
Architecture: amd64
Priority: optional
Section: multiverse/devel
Source: tensorrt
Maintainer: cudatools <cudatools@nvidia.com>
How I can resolve this issue?
Regards