> For the complete documentation index, see [llms.txt](https://doc.celantur.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.celantur.com/sdk/requirements-and-installation/installation.md).

# Installation

## Install prerequisites:

```bash
apt install -y \
    ffmpeg \
    libexif-dev \
    libprotobuf-dev \
    libopenexr25 \
    libgstreamer1.0-0 \
    libgstreamer-plugins-base1.0-0 \
    wget
```

## Install Celantur dependencies

Celantur will provide you links to Debian packages:

* Celantur SDK (`cpp-processing`)
* Boost
* OpenCV
* ONNX Runtime

Install them with:

```bash
apt install ./celantur-*.deb
```

### Optional: Install OpenVINO 2024

For compiling and running [OpenVINO models](https://docs.openvino.ai/2026/get-started/install-openvino.html?). 

```bash
wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB && \
    apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB && \
    echo "deb https://apt.repos.intel.com/openvino/2024 ubuntu22 main" | tee /etc/apt/sources.list.d/intel-openvino-2024.list && \
    apt update && \
    apt install -y openvino && \
    rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
```

### Optional: Install TensorRT 10

For compiling and running TensorRT (TRT) models (GPU inference with data in CPU memory as input and output), see [official NVIDIA installation guide](https://docs.nvidia.com/deeplearning/tensorrt/latest/installing-tensorrt/install-debian.html#installing-debian).

### Optional: Install CUDA 11.7

For running full inference on NVIDIA GPU (with data in GPU memory as input and output), [install CUDA 11.7](https://developer.nvidia.com/cuda-11-7-0-download-archive).    

## Download the model

Celantur will provide you link to download the model.

## Test the installation

Try out the [SDK examples](https://github.com/celantur/SDKExample/).