Overview

The Holoscan SDK Debian package is part of NVIDIA Holoscan, the AI sensor processing platform that combines hardware systems for low-latency sensor and network connectivity, optimized libraries for data processing and AI, and core microservices to run streaming, imaging, and other applications, from embedded to edge to cloud. It can be used to build streaming AI pipelines for a variety of domains, including Medical Devices, High Performance Computing at the Edge, Industrial Inspection and more.

Visit the NGC demo website for a live demonstration of some of Holoscan capabilities.

Prerequisites

Holoscan Debian packages were built for the Holoscan Developer Kits (aarch64) as well as x86_64 systems.

For a full list of Holoscan documentation, visit the Holoscan developer page.

For Clara AGX Developer Kit and NVIDIA IGX Orin Developer Kit (aarch64)

Set up your developer kit:

• Clara AGX Developer Kit User Guide, or
• NVIDIA IGX Orin Developer Kit User Guide.

Make sure you have joined the Holoscan SDK Program and, if needed, the RiverMax SDK Program before using the NVIDIA SDK Manager.

SDK Manager will install Holopack 1.1 as well as the nvgpuswitch.py script. Once configured for dGPU mode, your developer kit will include the following necessary components to use the Debian package:

• NVIDIA Jetson Linux: 34.1.2
• NVIDIA dGPU drivers: 510.73.08
• CUDA Toolkit: 11.6.1
• TensorRT: 8.2.3

Refer to the User Guide for additional steps to support the AJA capture card.

For x86_64 systems

You'll need the following to use the Holoscan Debian package on x86_64:

• OS: Ubuntu 20.04
• NVIDIA GPU
  • Ampere or above recommended for best performance
  • Quadro/NVIDIA RTX necessary for GPUDirect RDMA support
• NVIDIA dGPU drivers: 510.73.08
• The latest CUDA Linux GPG Repository Key to automatically install debian dependencies (CUDA, cuDNN, TensorRT)

Installing the Debian package

Manually (UI):

1. Select your version and download the adequate resource
2. Extract the debian package within the downloaded files.zip
3. Open the debian package with Software Install application

CLI:

version="v0.4.0-amd64" # for x86_64, or v0.4.0-arm64 on aarch64
name="holoscan_dev_deb"
folder="${name}_${version}"
zip="${folder}.zip"
wget -O ${zip} https://api.ngc.nvidia.com/v2/resources/nvidia/clara-holoscan/${name}/versions/${version}/zip
unzip ${zip} -d ${folder} && rm ${zip}
deb=$(find ${folder} -name '*.deb' -type file)
sudo apt install ./${deb}
rm -r ${folder}

Using the installed libraries and headers

The content of the Debian package is installed under /opt/nvidia/holoscan. It exports a CMake configuration file inside lib/cmake/holoscan allowing you to use holoscan as follow in your CMake project (link libraries + include headers):

find_package(holoscan REQUIRED CONFIG PATHS "/opt/nvidia/holoscan")
target_link_libraries(yourTarget PRIVATE holoscan::holoscan)

Alternatives to hardcoding PATHS inside find_package in CMake are listed under the Config Mode Search Procedure documentation.

Troubleshooting

The following packages have unmet dependencies: holoscan-dev : Depends: libnvinfer-bin (>= 8.2.3) but it is not installable ...

You have installed holoscan-dev without the CUDA Linux GPG Repository Key. You can either:

• Install CUDA, cuDNN, and TensorRT manually, or
• Install the cuda-keyring mentioned above, then run apt --fix-broken install